hyperparameters_&_pipeline.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "toc": true,
        "id": "EDw8H-ZZH1bB"
      },
      "source": [
        "<h1>Table of Contents<span class=\"tocSkip\"></span></h1>\n",
        "<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Objectives\" data-toc-modified-id=\"Objectives-1\"><span class=\"toc-item-num\">1&nbsp;&nbsp;</span>Objectives</a></span></li><li><span><a href=\"#Model-Tuning\" data-toc-modified-id=\"Model-Tuning-2\"><span class=\"toc-item-num\">2&nbsp;&nbsp;</span>Model Tuning</a></span><ul class=\"toc-item\"><li><span><a href=\"#Hyperparameters\" data-toc-modified-id=\"Hyperparameters-2.1\"><span class=\"toc-item-num\">2.1&nbsp;&nbsp;</span>Hyperparameters</a></span><ul class=\"toc-item\"><li><span><a href=\"#Difference-from-Parametric-/-Non-Parametric-Models\" data-toc-modified-id=\"Difference-from-Parametric-/-Non-Parametric-Models-2.1.1\"><span class=\"toc-item-num\">2.1.1&nbsp;&nbsp;</span>Difference from Parametric / Non-Parametric Models</a></span></li></ul></li><li><span><a href=\"#Data-Example\" data-toc-modified-id=\"Data-Example-2.2\"><span class=\"toc-item-num\">2.2&nbsp;&nbsp;</span>Data Example</a></span><ul class=\"toc-item\"><li><span><a href=\"#Data-Prep\" data-toc-modified-id=\"Data-Prep-2.2.1\"><span class=\"toc-item-num\">2.2.1&nbsp;&nbsp;</span>Data Prep</a></span><ul class=\"toc-item\"><li><span><a href=\"#Preparing-the-Test-Set\" data-toc-modified-id=\"Preparing-the-Test-Set-2.2.1.1\"><span class=\"toc-item-num\">2.2.1.1&nbsp;&nbsp;</span>Preparing the Test Set</a></span></li></ul></li><li><span><a href=\"#Trying-Different-Models-&amp;-Values\" data-toc-modified-id=\"Trying-Different-Models-&amp;-Values-2.2.2\"><span class=\"toc-item-num\">2.2.2&nbsp;&nbsp;</span>Trying Different Models &amp; Values</a></span><ul class=\"toc-item\"><li><span><a href=\"#$k$-Nearest-Neighbors-Model\" data-toc-modified-id=\"$k$-Nearest-Neighbors-Model-2.2.2.1\"><span class=\"toc-item-num\">2.2.2.1&nbsp;&nbsp;</span>$k$-Nearest Neighbors Model</a></span></li><li><span><a href=\"#Decision-Tree\" data-toc-modified-id=\"Decision-Tree-2.2.2.2\"><span class=\"toc-item-num\">2.2.2.2&nbsp;&nbsp;</span>Decision Tree</a></span></li></ul></li></ul></li></ul></li><li><span><a href=\"#Automatically-Searching-with-Grid-Search\" data-toc-modified-id=\"Automatically-Searching-with-Grid-Search-3\"><span class=\"toc-item-num\">3&nbsp;&nbsp;</span>Automatically Searching with Grid Search</a></span><ul class=\"toc-item\"><li><ul class=\"toc-item\"><li><span><a href=\"#GridSearchCV\" data-toc-modified-id=\"GridSearchCV-3.0.1\"><span class=\"toc-item-num\">3.0.1&nbsp;&nbsp;</span><code>GridSearchCV</code></a></span></li><li><span><a href=\"#Choice-of-Grid-Values\" data-toc-modified-id=\"Choice-of-Grid-Values-3.0.2\"><span class=\"toc-item-num\">3.0.2&nbsp;&nbsp;</span>Choice of Grid Values</a></span></li><li><span><a href=\"#Exercise\" data-toc-modified-id=\"Exercise-3.0.3\"><span class=\"toc-item-num\">3.0.3&nbsp;&nbsp;</span>Exercise</a></span></li></ul></li></ul></li><li><span><a href=\"#Better-Process:-Pipelines\" data-toc-modified-id=\"Better-Process:-Pipelines-4\"><span class=\"toc-item-num\">4&nbsp;&nbsp;</span>Better Process: Pipelines</a></span><ul class=\"toc-item\"><li><span><a href=\"#Advantages-of-Pipeline\" data-toc-modified-id=\"Advantages-of-Pipeline-4.1\"><span class=\"toc-item-num\">4.1&nbsp;&nbsp;</span>Advantages of <code>Pipeline</code></a></span><ul class=\"toc-item\"><li><span><a href=\"#Reduces-Complexity\" data-toc-modified-id=\"Reduces-Complexity-4.1.1\"><span class=\"toc-item-num\">4.1.1&nbsp;&nbsp;</span>Reduces Complexity</a></span></li><li><span><a href=\"#Convenient\" data-toc-modified-id=\"Convenient-4.1.2\"><span class=\"toc-item-num\">4.1.2&nbsp;&nbsp;</span>Convenient</a></span></li><li><span><a href=\"#Flexible\" data-toc-modified-id=\"Flexible-4.1.3\"><span class=\"toc-item-num\">4.1.3&nbsp;&nbsp;</span>Flexible</a></span></li><li><span><a href=\"#Prevent-Mistakes\" data-toc-modified-id=\"Prevent-Mistakes-4.1.4\"><span class=\"toc-item-num\">4.1.4&nbsp;&nbsp;</span>Prevent Mistakes</a></span></li></ul></li><li><span><a href=\"#Example-of-Using-Pipeline\" data-toc-modified-id=\"Example-of-Using-Pipeline-4.2\"><span class=\"toc-item-num\">4.2&nbsp;&nbsp;</span>Example of Using <code>Pipeline</code></a></span><ul class=\"toc-item\"><li><span><a href=\"#Without-the-Pipeline-class\" data-toc-modified-id=\"Without-the-Pipeline-class-4.2.1\"><span class=\"toc-item-num\">4.2.1&nbsp;&nbsp;</span>Without the Pipeline class</a></span></li><li><span><a href=\"#With-Pipeline-Class\" data-toc-modified-id=\"With-Pipeline-Class-4.2.2\"><span class=\"toc-item-num\">4.2.2&nbsp;&nbsp;</span>With <code>Pipeline</code> Class</a></span></li></ul></li><li><span><a href=\"#Grid-Searching-a-Pipeline\" data-toc-modified-id=\"Grid-Searching-a-Pipeline-4.3\"><span class=\"toc-item-num\">4.3&nbsp;&nbsp;</span>Grid Searching a Pipeline</a></span><ul class=\"toc-item\"><li><span><a href=\"#Using-ColumnTransformer\" data-toc-modified-id=\"Using-ColumnTransformer-4.3.1\"><span class=\"toc-item-num\">4.3.1&nbsp;&nbsp;</span>Using <code>ColumnTransformer</code></a></span></li></ul></li><li><span><a href=\"#A-Note-on-Data-Leakage\" data-toc-modified-id=\"A-Note-on-Data-Leakage-4.4\"><span class=\"toc-item-num\">4.4&nbsp;&nbsp;</span>A Note on Data Leakage</a></span><ul class=\"toc-item\"><li><span><a href=\"#Example-of-leaking-information\" data-toc-modified-id=\"Example-of-leaking-information-4.4.1\"><span class=\"toc-item-num\">4.4.1&nbsp;&nbsp;</span>Example of leaking information</a></span></li><li><span><a href=\"#Example-of-Grid-Search-with-no-leakage\" data-toc-modified-id=\"Example-of-Grid-Search-with-no-leakage-4.4.2\"><span class=\"toc-item-num\">4.4.2&nbsp;&nbsp;</span>Example of Grid Search with no leakage</a></span></li></ul></li></ul></li><li><span><a href=\"#Grid-Search-Exercise\" data-toc-modified-id=\"Grid-Search-Exercise-5\"><span class=\"toc-item-num\">5&nbsp;&nbsp;</span>Grid Search Exercise</a></span></li><li><span><a href=\"#Level-Up:-Random-Searching\" data-toc-modified-id=\"Level-Up:-Random-Searching-6\"><span class=\"toc-item-num\">6&nbsp;&nbsp;</span>Level Up: Random Searching</a></span><ul class=\"toc-item\"><li><ul class=\"toc-item\"><li><span><a href=\"#RandomizedSearchCV-with-LogisticRegression\" data-toc-modified-id=\"RandomizedSearchCV-with-LogisticRegression-6.0.1\"><span class=\"toc-item-num\">6.0.1&nbsp;&nbsp;</span><code>RandomizedSearchCV</code> with <code>LogisticRegression</code></a></span></li></ul></li></ul></li><li><span><a href=\"#Level-Up:-SMOTE\" data-toc-modified-id=\"Level-Up:-SMOTE-7\"><span class=\"toc-item-num\">7&nbsp;&nbsp;</span>Level Up: SMOTE</a></span></li></ul></div>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T04:05:08.822957Z",
          "start_time": "2021-10-28T04:05:08.819534Z"
        },
        "id": "Hl7IPaeUH1bG"
      },
      "outputs": [],
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "from matplotlib import pyplot as plt\n",
        "import seaborn as sns\n",
        "from scipy import stats as stats\n",
        "\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "\n",
        "from sklearn.metrics import precision_score, recall_score\n",
        "from sklearn.model_selection import train_test_split, GridSearchCV,\\\n",
        "cross_val_score, RandomizedSearchCV\n",
        "\n",
        "from sklearn.preprocessing import OneHotEncoder, StandardScaler\n",
        "from sklearn.impute import SimpleImputer\n",
        "from sklearn.pipeline import Pipeline\n",
        "from sklearn.compose import ColumnTransformer\n",
        "\n",
        "\n",
        "import warnings\n",
        "warnings.filterwarnings('ignore')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "id": "_1Iv8Oz7H1bH"
      },
      "source": [
        "# Objectives"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "Z1V5CfhnH1bH"
      },
      "source": [
        "- Explain what hyperparameters are\n",
        "- Describe the purpose of grid searching\n",
        "- Implement grid searching for the purposes of model optimization\n",
        "- Understand the Data Science pipeline\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "id": "cMngAsmDH1bI"
      },
      "source": [
        "# Model Tuning"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "itX3hJCtH1bI"
      },
      "source": [
        "![](https://imgs.xkcd.com/comics/machine_learning.png)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "2WlZxi05H1bI"
      },
      "source": [
        "## Hyperparameters"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "AQYk17bNH1bJ"
      },
      "source": [
        "Many of the models we have looked at are really *families* of models in the sense that they make use of **hyperparameters**. Hyperparameters are also called *tuning parameters,* *meta parameters*, or *free parameters*.\n",
        "\n",
        "While the term hyperparameter is used in a particular way within data science, **parameter** is used ambiguously. Parameter has a broad meaning that includes hyperparameters. Parameter is also used in a narrow sense that can be stated in contrast to a hyperparameter.\n",
        "\n",
        "In general, a parameter is a term in a mathematical function that is not an argument of the function, but it can still take a range of values. For example, the equation of the regression line\n",
        "\n",
        "$$y = \\beta_0 + \\beta_1  x$$ \n",
        "\n",
        "has $x$ and $y$ as the variables, but the *y*-intercept $\\beta_0$ and the slope $\\beta_1$ are the parameters of the model.\n",
        "\n",
        "A hyperparameter is a parameter that is used to control the learning process of the algorithm. The hyperparameter values cannot be estimated from the data. (The regression model above does not have any hyperparameters.) The purpose of this lecture is to understand how to pick hyperparameters, i.e. tune the model, and implement this process into the data science pipeline.\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "jUIWXoj6H1bL"
      },
      "source": [
        "> We can think of these **hyperparameters** as _radio dials_ of the base model. Since our model is a representation of reality, it will always have static, but tuning the hyperparametrs will allow us to have the clearist signal.\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Sometimes the term parameter is used in opposition to the term hyperparameter. In this specific usuage, a model parameter is learned from the training data set.\n",
        "\n",
        "Here are some examples of parameters and their corresponding models that we are already familiar with:\n",
        "\n",
        "*   The estimated probabilities for a variable are parameters in logistic regression\n",
        "*   The Gini impurity is a parameter for decision trees\n",
        "\n",
        "In this strict usage of the word parameter, we say that parameters result from training and hyperparameters from tuning.\n",
        "\n",
        "Typically it should be clear from context whether *parameter* is being used in the broad or narrow sense."
      ],
      "metadata": {
        "id": "uemAMivI2MpZ"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "aOODuuqLH1bK"
      },
      "source": [
        "We are going to look at model turning, i.e. tuning hyperparameters, with the decision tree algorithm that we saw earlier as well as an extension of that model called *random forests*. Recall that a decision tree allows us to make\n",
        "\n",
        "- a classifier that branches according to information gain\n",
        "- a classifier that branches according to Gini impurity\n",
        "- a regressor that branches according to mean squared error\n",
        "\n",
        "A random forests, as the name suggests, is an esemble of decision trees. We'll see the details of them momentarily."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "Z2pD99xKH1bK"
      },
      "source": [
        "It is natural to experiment via model tuning with different values of these hyperparameters to try to improve model performance. This experimentation is part of the reason that data science is a science."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "05KiRJKcH1bL"
      },
      "source": [
        "### Difference from Parametric / Nonparametric Models"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "4uKg2VtsH1bL"
      },
      "source": [
        "Just as there is a difference between parameters (in the narrow sense) and hyperparameters, there is related a distinction between parametric and nonparametric models."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "TzYpom8MH1bL"
      },
      "source": [
        "A model is parametric if the mathematical model is assumed before hand. Linear and logistic regression are both parametric models since the data is assumed to fit a particular mathematical function. For parametric algorithms, we start with a given model *form* and we then search for the optimal parameters to fill in that form.\n",
        "\n",
        "For example, with linear regression we start with this form\n",
        "$$y = \\beta_0 + \\beta_1  x$$ \n",
        "and find the optimal $\\beta_i$'s, which are its parameters.\n",
        "\n",
        "Since the relationship between the inputs and outputs is defined, parametric models typically are faster and easier to run than nonparametric models. As such, parametric models work well for when the input data is well-defined and predictable.\n",
        "\n",
        "Nonparametric models are not based on a mathematical model, but rather learn the mathematical model from the data. These models are flexible and work well when the input data that is not well-defiend or complex, however they can be computationally expensive. Decision trees are an example of a nonparametric model.\n",
        "\n",
        "Thus, somewhat confusingly, models that have hyperparameters are called nonparametric models (even though they have parameters!) and those that do not have hyperparameters are called parametric."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "f6Naj1VwH1bL"
      },
      "source": [
        "## Data Example"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "f-uDYYYmH1bL"
      },
      "source": [
        "![Penguins](https://raw.githubusercontent.com/allisonhorst/palmerpenguins/69530276d74b99df81cc385f4e95c644da69ebfa/man/figures/lter_penguins.png)\n",
        "\n",
        "> Images source: @allison_horst [github.com/allisonhorst/penguins](github.com/allisonhorst/penguins)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:19.245056Z",
          "start_time": "2021-10-28T03:33:19.234933Z"
        },
        "hidden": true,
        "id": "vN7ocv63H1bM"
      },
      "outputs": [],
      "source": [
        "penguins = sns.load_dataset('penguins')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "jfYX6fWGH1bM"
      },
      "source": [
        "![Bill length & depth](https://raw.githubusercontent.com/allisonhorst/palmerpenguins/69530276d74b99df81cc385f4e95c644da69ebfa/man/figures/culmen_depth.png)\n",
        "\n",
        "> Images source: @allison_horst [github.com/allisonhorst/penguins](github.com/allisonhorst/penguins)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:20.583442Z",
          "start_time": "2021-10-28T03:33:20.566368Z"
        },
        "hidden": true,
        "id": "HbKf2qHEH1bM",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "outputId": "54dd3f18-3234-4b14-a7d5-3b5bd67f835d"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  species     island  bill_length_mm  bill_depth_mm  flipper_length_mm  \\\n",
              "0  Adelie  Torgersen            39.1           18.7              181.0   \n",
              "1  Adelie  Torgersen            39.5           17.4              186.0   \n",
              "2  Adelie  Torgersen            40.3           18.0              195.0   \n",
              "3  Adelie  Torgersen             NaN            NaN                NaN   \n",
              "4  Adelie  Torgersen            36.7           19.3              193.0   \n",
              "\n",
              "   body_mass_g     sex  \n",
              "0       3750.0    Male  \n",
              "1       3800.0  Female  \n",
              "2       3250.0  Female  \n",
              "3          NaN     NaN  \n",
              "4       3450.0  Female  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d58bd05d-9c7e-484c-8bb3-b355ee329c3f\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>species</th>\n",
              "      <th>island</th>\n",
              "      <th>bill_length_mm</th>\n",
              "      <th>bill_depth_mm</th>\n",
              "      <th>flipper_length_mm</th>\n",
              "      <th>body_mass_g</th>\n",
              "      <th>sex</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Adelie</td>\n",
              "      <td>Torgersen</td>\n",
              "      <td>39.1</td>\n",
              "      <td>18.7</td>\n",
              "      <td>181.0</td>\n",
              "      <td>3750.0</td>\n",
              "      <td>Male</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Adelie</td>\n",
              "      <td>Torgersen</td>\n",
              "      <td>39.5</td>\n",
              "      <td>17.4</td>\n",
              "      <td>186.0</td>\n",
              "      <td>3800.0</td>\n",
              "      <td>Female</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Adelie</td>\n",
              "      <td>Torgersen</td>\n",
              "      <td>40.3</td>\n",
              "      <td>18.0</td>\n",
              "      <td>195.0</td>\n",
              "      <td>3250.0</td>\n",
              "      <td>Female</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Adelie</td>\n",
              "      <td>Torgersen</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Adelie</td>\n",
              "      <td>Torgersen</td>\n",
              "      <td>36.7</td>\n",
              "      <td>19.3</td>\n",
              "      <td>193.0</td>\n",
              "      <td>3450.0</td>\n",
              "      <td>Female</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d58bd05d-9c7e-484c-8bb3-b355ee329c3f')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-d58bd05d-9c7e-484c-8bb3-b355ee329c3f button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-d58bd05d-9c7e-484c-8bb3-b355ee329c3f');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ],
      "source": [
        "penguins.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:21.461254Z",
          "start_time": "2021-10-28T03:33:21.450522Z"
        },
        "id": "kH8bDkvtH1bM",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "55ff4cf2-13e3-4308-ec8c-833988020cdf"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 344 entries, 0 to 343\n",
            "Data columns (total 7 columns):\n",
            " #   Column             Non-Null Count  Dtype  \n",
            "---  ------             --------------  -----  \n",
            " 0   species            344 non-null    object \n",
            " 1   island             344 non-null    object \n",
            " 2   bill_length_mm     342 non-null    float64\n",
            " 3   bill_depth_mm      342 non-null    float64\n",
            " 4   flipper_length_mm  342 non-null    float64\n",
            " 5   body_mass_g        342 non-null    float64\n",
            " 6   sex                333 non-null    object \n",
            "dtypes: float64(4), object(3)\n",
            "memory usage: 18.9+ KB\n"
          ]
        }
      ],
      "source": [
        "penguins.info()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "b1g2jSp_H1bM"
      },
      "source": [
        "### Data Prep"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "v-EYjtxBH1bM"
      },
      "source": [
        "We'll try to predict species given the other columns' values. Let's dummy-out `island` and `sex`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:22.756858Z",
          "start_time": "2021-10-28T03:33:22.751784Z"
        },
        "hidden": true,
        "id": "SKLLj2MAH1bN",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f97244c1-2294-4973-f9da-5d279be5f01c"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "19"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ],
      "source": [
        "penguins.isna().sum().sum()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:23.129535Z",
          "start_time": "2021-10-28T03:33:23.109712Z"
        },
        "hidden": true,
        "id": "7l_zx-DvH1bN"
      },
      "outputs": [],
      "source": [
        "penguins = penguins.dropna()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:23.154283Z",
          "start_time": "2021-10-28T03:33:23.151406Z"
        },
        "hidden": true,
        "id": "ygqjs6sQH1bN"
      },
      "outputs": [],
      "source": [
        "y = penguins.pop('species')"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "penguins.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "OkU3kHO0X6vV",
        "outputId": "8f29bd8e-85e2-4406-ac04-ad21d5ce1f54"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      island  bill_length_mm  bill_depth_mm  flipper_length_mm  body_mass_g  \\\n",
              "0  Torgersen            39.1           18.7              181.0       3750.0   \n",
              "1  Torgersen            39.5           17.4              186.0       3800.0   \n",
              "2  Torgersen            40.3           18.0              195.0       3250.0   \n",
              "4  Torgersen            36.7           19.3              193.0       3450.0   \n",
              "5  Torgersen            39.3           20.6              190.0       3650.0   \n",
              "\n",
              "      sex  \n",
              "0    Male  \n",
              "1  Female  \n",
              "2  Female  \n",
              "4  Female  \n",
              "5    Male  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-7261cdad-0ea8-4417-a2d4-2c3f29e8ccf3\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>island</th>\n",
              "      <th>bill_length_mm</th>\n",
              "      <th>bill_depth_mm</th>\n",
              "      <th>flipper_length_mm</th>\n",
              "      <th>body_mass_g</th>\n",
              "      <th>sex</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Torgersen</td>\n",
              "      <td>39.1</td>\n",
              "      <td>18.7</td>\n",
              "      <td>181.0</td>\n",
              "      <td>3750.0</td>\n",
              "      <td>Male</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Torgersen</td>\n",
              "      <td>39.5</td>\n",
              "      <td>17.4</td>\n",
              "      <td>186.0</td>\n",
              "      <td>3800.0</td>\n",
              "      <td>Female</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Torgersen</td>\n",
              "      <td>40.3</td>\n",
              "      <td>18.0</td>\n",
              "      <td>195.0</td>\n",
              "      <td>3250.0</td>\n",
              "      <td>Female</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Torgersen</td>\n",
              "      <td>36.7</td>\n",
              "      <td>19.3</td>\n",
              "      <td>193.0</td>\n",
              "      <td>3450.0</td>\n",
              "      <td>Female</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>Torgersen</td>\n",
              "      <td>39.3</td>\n",
              "      <td>20.6</td>\n",
              "      <td>190.0</td>\n",
              "      <td>3650.0</td>\n",
              "      <td>Male</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7261cdad-0ea8-4417-a2d4-2c3f29e8ccf3')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-7261cdad-0ea8-4417-a2d4-2c3f29e8ccf3 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-7261cdad-0ea8-4417-a2d4-2c3f29e8ccf3');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:23.343753Z",
          "start_time": "2021-10-28T03:33:23.339442Z"
        },
        "hidden": true,
        "id": "ZbbsJysMH1bN"
      },
      "outputs": [],
      "source": [
        "# Note we're dedicating a lot of data to the testing set just for demonstrative purposes\n",
        "np.random.seed(1882) # You can pick any positive integer you want, but this will allow us to have reproducbility\n",
        "X_train, X_test, y_train, y_test = train_test_split(\n",
        "    penguins, y, test_size=0.5, random_state=42)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:23.689260Z",
          "start_time": "2021-10-28T03:33:23.683728Z"
        },
        "hidden": true,
        "id": "_hLb9NY3H1bN"
      },
      "outputs": [],
      "source": [
        "X_train_cat = X_train.select_dtypes('object')\n",
        "\n",
        "ohe = OneHotEncoder(\n",
        "    drop='first',\n",
        "    sparse=False)\n",
        "\n",
        "dums = ohe.fit_transform(X_train_cat)\n",
        "dums_df = pd.DataFrame(dums,\n",
        "                       columns=ohe.get_feature_names(),\n",
        "                       index=X_train_cat.index)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:23.903884Z",
          "start_time": "2021-10-28T03:33:23.896009Z"
        },
        "hidden": true,
        "id": "D713-rGCH1bN"
      },
      "outputs": [],
      "source": [
        "X_train_nums = X_train.select_dtypes('float64')\n",
        "\n",
        "ss = StandardScaler()\n",
        "\n",
        "ss.fit(X_train_nums)\n",
        "nums_df = pd.DataFrame(ss.transform(X_train_nums),\n",
        "                      index=X_train_nums.index)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:24.209621Z",
          "start_time": "2021-10-28T03:33:24.206439Z"
        },
        "hidden": true,
        "scrolled": true,
        "id": "95oYOqEjH1bN"
      },
      "outputs": [],
      "source": [
        "X_train_clean = pd.concat([nums_df, dums_df], axis=1)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:24.632509Z",
          "start_time": "2021-10-28T03:33:24.620549Z"
        },
        "hidden": true,
        "id": "Fml5d3d3H1bN",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "outputId": "3eaafa51-d2a6-4d56-f226-cc106567dd79"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "            0         1         2         3  x0_Dream  x0_Torgersen  x1_Male\n",
              "160  0.362748  0.903276 -0.472344 -0.094599       1.0           0.0      0.0\n",
              "237  0.973499 -0.977375  1.408317  2.512546       0.0           0.0      1.0\n",
              "2   -0.725152  0.445820 -0.472344 -1.185963       0.0           1.0      0.0\n",
              "121 -1.221387  1.360731 -0.255345 -0.882806       0.0           1.0      1.0\n",
              "179  1.030757  0.954104 -0.110678 -0.519018       1.0           0.0      1.0"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-3b23ee74-0864-41eb-bd51-e261276d2378\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>0</th>\n",
              "      <th>1</th>\n",
              "      <th>2</th>\n",
              "      <th>3</th>\n",
              "      <th>x0_Dream</th>\n",
              "      <th>x0_Torgersen</th>\n",
              "      <th>x1_Male</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>160</th>\n",
              "      <td>0.362748</td>\n",
              "      <td>0.903276</td>\n",
              "      <td>-0.472344</td>\n",
              "      <td>-0.094599</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>237</th>\n",
              "      <td>0.973499</td>\n",
              "      <td>-0.977375</td>\n",
              "      <td>1.408317</td>\n",
              "      <td>2.512546</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>-0.725152</td>\n",
              "      <td>0.445820</td>\n",
              "      <td>-0.472344</td>\n",
              "      <td>-1.185963</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>121</th>\n",
              "      <td>-1.221387</td>\n",
              "      <td>1.360731</td>\n",
              "      <td>-0.255345</td>\n",
              "      <td>-0.882806</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>179</th>\n",
              "      <td>1.030757</td>\n",
              "      <td>0.954104</td>\n",
              "      <td>-0.110678</td>\n",
              "      <td>-0.519018</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3b23ee74-0864-41eb-bd51-e261276d2378')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-3b23ee74-0864-41eb-bd51-e261276d2378 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-3b23ee74-0864-41eb-bd51-e261276d2378');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ],
      "source": [
        "X_train_clean.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "HNIuFwx3H1bO"
      },
      "source": [
        "#### Preparing the Test Set"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:25.300049Z",
          "start_time": "2021-10-28T03:33:25.294945Z"
        },
        "hidden": true,
        "id": "5QSlIR02H1bO"
      },
      "outputs": [],
      "source": [
        "X_test_cat = X_test.select_dtypes('object')\n",
        "\n",
        "test_dums = ohe.transform(X_test_cat)\n",
        "test_dums_df = pd.DataFrame(test_dums,\n",
        "                       columns=ohe.get_feature_names(),\n",
        "                      index=X_test_cat.index)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:25.700016Z",
          "start_time": "2021-10-28T03:33:25.695249Z"
        },
        "hidden": true,
        "id": "CbZvSlHFH1bO"
      },
      "outputs": [],
      "source": [
        "X_test_nums = X_test.select_dtypes('float64')\n",
        "\n",
        "test_nums = ss.transform(X_test_nums)\n",
        "test_nums_df = pd.DataFrame(test_nums,\n",
        "                           index=X_test_nums.index)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:25.735115Z",
          "start_time": "2021-10-28T03:33:25.732029Z"
        },
        "hidden": true,
        "id": "HmZ3b3QeH1bO"
      },
      "outputs": [],
      "source": [
        "X_test_clean = pd.concat([test_nums_df,\n",
        "                 test_dums_df], axis=1)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 17,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:25.869137Z",
          "start_time": "2021-10-28T03:33:25.857740Z"
        },
        "hidden": true,
        "id": "bsvUuTU8H1bO",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "outputId": "a61edd62-1e35-4a17-827f-6cd9663de961"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "            0         1         2         3  x0_Dream  x0_Torgersen  x1_Male\n",
              "30  -0.877839 -0.214949 -1.702007 -1.185963       1.0           0.0      0.0\n",
              "317  0.534522 -1.282345  1.480650  0.784554       0.0           0.0      0.0\n",
              "79  -0.381604  1.004932 -0.472344 -0.276493       0.0           1.0      1.0\n",
              "201  1.088015  0.090021 -0.255345 -0.670597       1.0           0.0      0.0\n",
              "63  -0.572464  0.547477 -0.689343 -0.215862       0.0           0.0      1.0"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-9b265d4a-ef9d-436b-af3b-4921eb82ffc6\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>0</th>\n",
              "      <th>1</th>\n",
              "      <th>2</th>\n",
              "      <th>3</th>\n",
              "      <th>x0_Dream</th>\n",
              "      <th>x0_Torgersen</th>\n",
              "      <th>x1_Male</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>30</th>\n",
              "      <td>-0.877839</td>\n",
              "      <td>-0.214949</td>\n",
              "      <td>-1.702007</td>\n",
              "      <td>-1.185963</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>317</th>\n",
              "      <td>0.534522</td>\n",
              "      <td>-1.282345</td>\n",
              "      <td>1.480650</td>\n",
              "      <td>0.784554</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>79</th>\n",
              "      <td>-0.381604</td>\n",
              "      <td>1.004932</td>\n",
              "      <td>-0.472344</td>\n",
              "      <td>-0.276493</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>201</th>\n",
              "      <td>1.088015</td>\n",
              "      <td>0.090021</td>\n",
              "      <td>-0.255345</td>\n",
              "      <td>-0.670597</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>63</th>\n",
              "      <td>-0.572464</td>\n",
              "      <td>0.547477</td>\n",
              "      <td>-0.689343</td>\n",
              "      <td>-0.215862</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9b265d4a-ef9d-436b-af3b-4921eb82ffc6')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-9b265d4a-ef9d-436b-af3b-4921eb82ffc6 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-9b265d4a-ef9d-436b-af3b-4921eb82ffc6');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ],
      "source": [
        "X_test_clean.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "M6dGBlb4H1bO"
      },
      "source": [
        "### Trying Different Models & Values"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "DiUclnHWH1bP"
      },
      "source": [
        "#### Decision Tree"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:29.217048Z",
          "start_time": "2021-10-28T03:33:29.210785Z"
        },
        "hidden": true,
        "id": "wHqQL8hfH1bP",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7c898ffb-bd3c-44db-ca39-84c733f0f749"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "DecisionTreeClassifier(random_state=42)"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ],
      "source": [
        "dt = DecisionTreeClassifier(random_state=42)\n",
        "\n",
        "dt.fit(X_train_clean, y_train)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "Gizvn0T5H1bP"
      },
      "source": [
        "##### Changing the branching criterion"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:29.257276Z",
          "start_time": "2021-10-28T03:33:29.251732Z"
        },
        "hidden": true,
        "id": "natKWWXWH1bP",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "82c934f4-ac20-49da-adba-c6db7c850106"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.9520958083832335"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ],
      "source": [
        "dt.score(X_test_clean, y_test)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "FyQ0xJyxH1bO"
      },
      "source": [
        "#### Random Forest"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "A random forest is a generalization of decision trees and as such is called an **ensemble method**.\n",
        "\n",
        "The key idea behind ensemble methods is the same as the *wisdom of crowds*.\n",
        "\n",
        "An example of the wisdom of crowds is the follwoing. If you ask 100 people individually how many jelly beans are in a jar, you'll get a wide variety of answers; however, if you take the mean of those 100 answers, you'll get a number that is close to the actual value.\n",
        "\n",
        "To continue the wisdome of the crowds metaphor for machine learning. If you have a 100 different decision trees that are each trained on a different random subset of the training data, you get a 100 predictions. The class that gets the most votes is the ensemble prediction.\n",
        "\n",
        "From this idea, we get a random forest. Happily since we are using `scikit-learn` the syntax is consistent to what we are used to for decision trees."
      ],
      "metadata": {
        "id": "F5MCkl_UZkBu"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "To create a random forest in `scikit-learn`, we use `RandomForestCLassifer()`, which is in the `ensemble` module. The [documentation](https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html) for the random forest is up to the usual excellent standards of `scikit-learn`.\n",
        "\n",
        "While there are over a dozen parameters for `RandomForestCLassifer()`, we'll focus on a few key ones.\n",
        "*   \"n_estimator\" is the number of trees in the forest\n",
        "*   the function to measure the quality of the split is the \"criterion\"\n",
        "*   \"max_depth\" is how far the tree can grow down\n",
        "*   setting \"random_state\" to a particular value allows us to reproduce our results"
      ],
      "metadata": {
        "id": "VIcxG1Nf3DFe"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:29.988524Z",
          "start_time": "2021-10-28T03:33:29.982468Z"
        },
        "hidden": true,
        "id": "Oovsy-iyH1bP",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ad6e0eb1-6267-4a06-f622-75b9df79e256"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "RandomForestClassifier(criterion='entropy', max_depth=5, n_estimators=5,\n",
              "                       random_state=42)"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ],
      "source": [
        "rfc = RandomForestClassifier(n_estimators=5, criterion='entropy', max_depth = 5,\n",
        "                          random_state=42)\n",
        "\n",
        "rfc.fit(X_train_clean, y_train)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 21,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:30.469779Z",
          "start_time": "2021-10-28T03:33:30.463825Z"
        },
        "hidden": true,
        "id": "Ojke-uu9H1bP",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "e0b8f514-ac04-4392-dbfa-82d16bd34b0a"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.9640718562874252"
            ]
          },
          "metadata": {},
          "execution_count": 21
        }
      ],
      "source": [
        "rfc.score(X_test_clean, y_test)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "We cab see that the random forest has performed a little better than a single decision tree."
      ],
      "metadata": {
        "id": "gVptsEJzsqgG"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "id": "IOnP-lQyH1bP"
      },
      "source": [
        "# Automatically Searching with Grid Search"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "GJLddAQVH1bP"
      },
      "source": [
        "It's not a bad idea to experiment with the values of your models' hyperparameters a bit as you're getting a feel for your models' performance. But there are more systematic ways of going about the search for optimal hyperparameters. One method of hyperparameter tuning is **grid searching**. "
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "h9XOi2hiH1bP"
      },
      "source": [
        "The idea is to build multiple models with different hyperparameter values and then see which one performs the best. The hyperparameters and the values to try form a sort of *grid* along which we are looking for the best performance. For example, here is a snapshot of the grid that we'll be creating.\n",
        "\n",
        "\n",
        "    4           | 'gini'    | 'auto'       | 100\n",
        "    4           | 'gini'    | 'sqrt'       | 100\n",
        "    4           | 'gini'    | 'log2'       | 100\n",
        "    4           | 'entropy' | 'auto'       | 100\n",
        "    4           | 'entropy' | 'sqrt'       | 100\n",
        "    4           | 'entropy' | 'log2'       | 100\n",
        "    4           | 'gini'    | 'auto'       | 200\n",
        "    4           | 'gini'    | 'sqrt'       | 200\n",
        "    4           | 'gini'    | 'log2'       | 200\n",
        "    4           | 'entropy' | 'auto'       | 200\n",
        "    4           | 'entropy' | 'sqrt'       | 200\n",
        "    4           | 'entropy' | 'log2'       | 200\n",
        "    ...         |   ...     |   ...        | ...\n",
        "    8           | 'entropy' | 'log2'       | 200\n",
        "    ___________________________________________________________\n",
        "    max_depth   | criterion | max_features | n_estimators"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Below, we'll see how to see the essential elements in the grid as well as where we can see all of the different combination that the alogirithm is trying."
      ],
      "metadata": {
        "id": "5ebPSW-M8vJV"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "f1LMKAPbH1bP"
      },
      "source": [
        "Scikit-Learn has a [`GridSearchCV`](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html) class whose `fit()` method runs this procedure. Note that this can be quite computationally expensive since:\n",
        "\n",
        "- A model is constructed for each combination of hyperparameter values that we input; and\n",
        "- Each model is cross-validated."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "OgeUvnkLH1bQ"
      },
      "source": [
        "### `GridSearchCV`"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 22,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:34.611150Z",
          "start_time": "2021-10-28T03:33:34.608300Z"
        },
        "hidden": true,
        "id": "X45qTOtRH1bQ"
      },
      "outputs": [],
      "source": [
        "# Define the parameter grid\n",
        "\n",
        "param_grid = { \n",
        "    'n_estimators': [100, 200],\n",
        "    'max_features': ['auto', 'sqrt', 'log2'],\n",
        "    'max_depth' : [4,5,6,7,8],\n",
        "    'criterion' :['gini', 'entropy']\n",
        "}"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "0-BK2FL-H1bQ"
      },
      "source": [
        "**Question: How many models will we be constructing with this grid?**\n",
        "\n",
        "*Hint: you'll be able to confirm your answer below after running the cross-validation.*"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 23,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:35.802959Z",
          "start_time": "2021-10-28T03:33:35.800647Z"
        },
        "hidden": true,
        "id": "zG-FHQdWH1bQ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f59b2d83-35ae-4aea-c83b-9d2041df0892"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(cv=5,\n",
              "             estimator=RandomForestClassifier(criterion='entropy', max_depth=5,\n",
              "                                              n_estimators=5, random_state=42),\n",
              "             param_grid={'criterion': ['gini', 'entropy'],\n",
              "                         'max_depth': [4, 5, 6, 7, 8],\n",
              "                         'max_features': ['auto', 'sqrt', 'log2'],\n",
              "                         'n_estimators': [100, 200]})"
            ]
          },
          "metadata": {},
          "execution_count": 23
        }
      ],
      "source": [
        "# Initialize the grid search object with five-fold cross-validation\n",
        "CV_rfc = GridSearchCV(estimator=rfc, param_grid=param_grid, cv= 5)\n",
        "CV_rfc.fit(X_train_clean, y_train)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 24,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:38.438408Z",
          "start_time": "2021-10-28T03:33:38.435309Z"
        },
        "hidden": true,
        "id": "uOJ3ibF0H1bQ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "10f39630-3696-4cea-8426-11196db2e9c9"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'criterion': 'gini',\n",
              " 'max_depth': 4,\n",
              " 'max_features': 'auto',\n",
              " 'n_estimators': 100}"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ],
      "source": [
        "# Whare the best combination of parameters?\n",
        "CV_rfc.best_params_"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 25,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:38.739396Z",
          "start_time": "2021-10-28T03:33:38.736044Z"
        },
        "hidden": true,
        "id": "khhl0377H1bQ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "106ba97e-3a30-4039-b567-87ed89c59e9f"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1.0"
            ]
          },
          "metadata": {},
          "execution_count": 25
        }
      ],
      "source": [
        "CV_rfc.best_score_"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 26,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:40.999187Z",
          "start_time": "2021-10-28T03:33:40.984761Z"
        },
        "hidden": true,
        "scrolled": true,
        "id": "h2mkgF50H1bQ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "6b62bfc6-5962-4bdc-df2a-4d0291ca4e6b"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.9820359281437125"
            ]
          },
          "metadata": {},
          "execution_count": 26
        }
      ],
      "source": [
        "# What is the best score?\n",
        "CV_rfc.best_estimator_.score(X_test_clean, y_test)"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "How does the above score compare to the decision tree? To the random forest we did without cross-validation?"
      ],
      "metadata": {
        "id": "QGqLD9pOCWsZ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Here are the parameters as a grid.\n",
        "CV_rfc.param_grid\n",
        "\n",
        "# When we learn about the data science pipeline below, we cna copy and past this output."
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9WRqsXvg9AON",
        "outputId": "f5d20c46-eddc-49b4-fb79-03a34873da0a"
      },
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'n_estimators': [100, 200],\n",
              " 'max_features': ['auto', 'sqrt', 'log2'],\n",
              " 'max_depth': [4, 5, 6, 7, 8],\n",
              " 'criterion': ['gini', 'entropy']}"
            ]
          },
          "metadata": {},
          "execution_count": 27
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 28,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:41.214030Z",
          "start_time": "2021-10-28T03:33:41.205532Z"
        },
        "hidden": true,
        "id": "a5Yge1dzH1bQ",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "51d218b2-f409-46f0-f882-83cf440c7ecc"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'mean_fit_time': array([0.10040274, 0.32743878, 0.18885036, 0.37687998, 0.18123322,\n",
              "        0.37814856, 0.1929318 , 0.44014945, 0.19391336, 0.46178055,\n",
              "        0.19387689, 0.1761723 , 0.08769259, 0.1776967 , 0.08875403,\n",
              "        0.17761922, 0.0907177 , 0.17822123, 0.08829217, 0.18440657,\n",
              "        0.09221444, 0.17848439, 0.08749561, 0.17879634, 0.09350615,\n",
              "        0.17858634, 0.08865108, 0.17769995, 0.09091773, 0.17973986,\n",
              "        0.09324346, 0.18223844, 0.09303279, 0.18747058, 0.09186587,\n",
              "        0.18382578, 0.09118729, 0.18089318, 0.09191728, 0.18194022,\n",
              "        0.0923502 , 0.18273125, 0.09240813, 0.18274565, 0.09326253,\n",
              "        0.18339281, 0.09482398, 0.18545847, 0.09325066, 0.18108506,\n",
              "        0.09207311, 0.18538451, 0.09328184, 0.18473802, 0.09184375,\n",
              "        0.18431678, 0.09233432, 0.18280568, 0.09235291, 0.18469062]),\n",
              " 'std_fit_time': array([0.00676299, 0.05413984, 0.01569627, 0.0845695 , 0.02217113,\n",
              "        0.02526072, 0.01882697, 0.09009616, 0.02487344, 0.09313067,\n",
              "        0.02646518, 0.00618699, 0.00243188, 0.00231588, 0.0004256 ,\n",
              "        0.00440367, 0.00231168, 0.00261353, 0.00114251, 0.00316229,\n",
              "        0.00145249, 0.00303916, 0.00056879, 0.00386317, 0.00373002,\n",
              "        0.0044828 , 0.00057533, 0.00583236, 0.00217744, 0.00348285,\n",
              "        0.00210279, 0.00178114, 0.00168187, 0.00632208, 0.00190508,\n",
              "        0.00349403, 0.00338618, 0.00482724, 0.00163195, 0.00401019,\n",
              "        0.00155696, 0.00444538, 0.00194587, 0.00319651, 0.00128419,\n",
              "        0.00190422, 0.00472032, 0.00208338, 0.00193393, 0.00280354,\n",
              "        0.0016438 , 0.00204678, 0.00195797, 0.00204182, 0.00163729,\n",
              "        0.00195948, 0.00157185, 0.00291803, 0.00121479, 0.00408829]),\n",
              " 'mean_score_time': array([0.00966015, 0.03707614, 0.01850877, 0.03441658, 0.01929598,\n",
              "        0.03685827, 0.01645555, 0.03051143, 0.01658754, 0.04051199,\n",
              "        0.0146986 , 0.01688695, 0.00906172, 0.01770992, 0.00930009,\n",
              "        0.01847649, 0.0106132 , 0.0190691 , 0.00920067, 0.01813784,\n",
              "        0.00968838, 0.01854849, 0.0093195 , 0.01747789, 0.01047301,\n",
              "        0.01855316, 0.00994616, 0.01901903, 0.0109345 , 0.01777854,\n",
              "        0.0096837 , 0.01813459, 0.01043487, 0.01754088, 0.01013618,\n",
              "        0.01765714, 0.00916405, 0.01735487, 0.00965376, 0.01858153,\n",
              "        0.01060658, 0.01756964, 0.00950146, 0.01730928, 0.01014357,\n",
              "        0.01743107, 0.00976062, 0.01836476, 0.00948658, 0.01715636,\n",
              "        0.00992808, 0.01806512, 0.00956759, 0.01754665, 0.00925651,\n",
              "        0.01745687, 0.01040254, 0.01702213, 0.00955114, 0.01743593]),\n",
              " 'std_score_time': array([1.58583637e-04, 1.34449921e-02, 4.45739379e-03, 9.06133329e-03,\n",
              "        7.47313128e-03, 7.66309012e-03, 2.68188666e-03, 5.88184165e-03,\n",
              "        1.67904189e-03, 2.03940261e-02, 1.91284960e-03, 8.29040512e-04,\n",
              "        3.12346378e-04, 8.76433434e-04, 1.50339247e-04, 1.76002340e-03,\n",
              "        9.66077849e-04, 3.72674867e-03, 1.60366341e-04, 7.58055711e-04,\n",
              "        3.64564851e-04, 2.20565393e-03, 2.31654460e-04, 2.02066496e-04,\n",
              "        1.75469350e-03, 3.12854112e-03, 1.12631068e-03, 2.72519791e-03,\n",
              "        2.48458687e-03, 3.94221659e-04, 8.28943514e-05, 1.76043931e-03,\n",
              "        2.08453296e-03, 2.13614181e-04, 1.41791593e-03, 2.03972109e-04,\n",
              "        2.73066093e-04, 3.00733888e-04, 1.37279869e-04, 2.30929516e-03,\n",
              "        1.98960038e-03, 4.65944415e-04, 1.26916370e-04, 5.96205816e-04,\n",
              "        7.96156718e-04, 1.56190586e-04, 4.57875094e-04, 1.23507424e-03,\n",
              "        3.94095875e-04, 3.92115201e-04, 8.53647441e-04, 2.91338162e-04,\n",
              "        1.07945507e-04, 1.02190573e-03, 1.46117611e-04, 2.17755226e-04,\n",
              "        2.10764495e-03, 2.46759290e-04, 4.41162425e-04, 2.52943870e-04]),\n",
              " 'param_criterion': masked_array(data=['gini', 'gini', 'gini', 'gini', 'gini', 'gini', 'gini',\n",
              "                    'gini', 'gini', 'gini', 'gini', 'gini', 'gini', 'gini',\n",
              "                    'gini', 'gini', 'gini', 'gini', 'gini', 'gini', 'gini',\n",
              "                    'gini', 'gini', 'gini', 'gini', 'gini', 'gini', 'gini',\n",
              "                    'gini', 'gini', 'entropy', 'entropy', 'entropy',\n",
              "                    'entropy', 'entropy', 'entropy', 'entropy', 'entropy',\n",
              "                    'entropy', 'entropy', 'entropy', 'entropy', 'entropy',\n",
              "                    'entropy', 'entropy', 'entropy', 'entropy', 'entropy',\n",
              "                    'entropy', 'entropy', 'entropy', 'entropy', 'entropy',\n",
              "                    'entropy', 'entropy', 'entropy', 'entropy', 'entropy',\n",
              "                    'entropy', 'entropy'],\n",
              "              mask=[False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False],\n",
              "        fill_value='?',\n",
              "             dtype=object),\n",
              " 'param_max_depth': masked_array(data=[4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6,\n",
              "                    7, 7, 7, 7, 7, 7, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 4, 4,\n",
              "                    5, 5, 5, 5, 5, 5, 6, 6, 6, 6, 6, 6, 7, 7, 7, 7, 7, 7,\n",
              "                    8, 8, 8, 8, 8, 8],\n",
              "              mask=[False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False],\n",
              "        fill_value='?',\n",
              "             dtype=object),\n",
              " 'param_max_features': masked_array(data=['auto', 'auto', 'sqrt', 'sqrt', 'log2', 'log2', 'auto',\n",
              "                    'auto', 'sqrt', 'sqrt', 'log2', 'log2', 'auto', 'auto',\n",
              "                    'sqrt', 'sqrt', 'log2', 'log2', 'auto', 'auto', 'sqrt',\n",
              "                    'sqrt', 'log2', 'log2', 'auto', 'auto', 'sqrt', 'sqrt',\n",
              "                    'log2', 'log2', 'auto', 'auto', 'sqrt', 'sqrt', 'log2',\n",
              "                    'log2', 'auto', 'auto', 'sqrt', 'sqrt', 'log2', 'log2',\n",
              "                    'auto', 'auto', 'sqrt', 'sqrt', 'log2', 'log2', 'auto',\n",
              "                    'auto', 'sqrt', 'sqrt', 'log2', 'log2', 'auto', 'auto',\n",
              "                    'sqrt', 'sqrt', 'log2', 'log2'],\n",
              "              mask=[False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False],\n",
              "        fill_value='?',\n",
              "             dtype=object),\n",
              " 'param_n_estimators': masked_array(data=[100, 200, 100, 200, 100, 200, 100, 200, 100, 200, 100,\n",
              "                    200, 100, 200, 100, 200, 100, 200, 100, 200, 100, 200,\n",
              "                    100, 200, 100, 200, 100, 200, 100, 200, 100, 200, 100,\n",
              "                    200, 100, 200, 100, 200, 100, 200, 100, 200, 100, 200,\n",
              "                    100, 200, 100, 200, 100, 200, 100, 200, 100, 200, 100,\n",
              "                    200, 100, 200, 100, 200],\n",
              "              mask=[False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False, False, False, False, False,\n",
              "                    False, False, False, False],\n",
              "        fill_value='?',\n",
              "             dtype=object),\n",
              " 'params': [{'criterion': 'gini',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'gini',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 4,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 5,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 6,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 7,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'auto',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'sqrt',\n",
              "   'n_estimators': 200},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 100},\n",
              "  {'criterion': 'entropy',\n",
              "   'max_depth': 8,\n",
              "   'max_features': 'log2',\n",
              "   'n_estimators': 200}],\n",
              " 'split0_test_score': array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1.]),\n",
              " 'split1_test_score': array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1.]),\n",
              " 'split2_test_score': array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1.]),\n",
              " 'split3_test_score': array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1.]),\n",
              " 'split4_test_score': array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1.]),\n",
              " 'mean_test_score': array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
              "        1., 1., 1., 1., 1., 1., 1., 1., 1.]),\n",
              " 'std_test_score': array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
              "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
              "        0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
              "        0., 0., 0., 0., 0., 0., 0., 0., 0.]),\n",
              " 'rank_test_score': array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
              "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
              "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], dtype=int32)}"
            ]
          },
          "metadata": {},
          "execution_count": 28
        }
      ],
      "source": [
        "# All of the results of the cross-validation on the random forest\n",
        "CV_rfc.cv_results_"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 29,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:41.818645Z",
          "start_time": "2021-10-28T03:33:41.790982Z"
        },
        "hidden": true,
        "id": "F-IIDgQdH1bQ",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "outputId": "7a2e9de9-9f63-405c-f861-62dca62828fd"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "    mean_fit_time  std_fit_time  mean_score_time  std_score_time  \\\n",
              "0        0.100403      0.006763         0.009660        0.000159   \n",
              "1        0.327439      0.054140         0.037076        0.013445   \n",
              "2        0.188850      0.015696         0.018509        0.004457   \n",
              "3        0.376880      0.084570         0.034417        0.009061   \n",
              "4        0.181233      0.022171         0.019296        0.007473   \n",
              "5        0.378149      0.025261         0.036858        0.007663   \n",
              "6        0.192932      0.018827         0.016456        0.002682   \n",
              "7        0.440149      0.090096         0.030511        0.005882   \n",
              "8        0.193913      0.024873         0.016588        0.001679   \n",
              "9        0.461781      0.093131         0.040512        0.020394   \n",
              "10       0.193877      0.026465         0.014699        0.001913   \n",
              "11       0.176172      0.006187         0.016887        0.000829   \n",
              "12       0.087693      0.002432         0.009062        0.000312   \n",
              "13       0.177697      0.002316         0.017710        0.000876   \n",
              "14       0.088754      0.000426         0.009300        0.000150   \n",
              "15       0.177619      0.004404         0.018476        0.001760   \n",
              "16       0.090718      0.002312         0.010613        0.000966   \n",
              "17       0.178221      0.002614         0.019069        0.003727   \n",
              "18       0.088292      0.001143         0.009201        0.000160   \n",
              "19       0.184407      0.003162         0.018138        0.000758   \n",
              "20       0.092214      0.001452         0.009688        0.000365   \n",
              "21       0.178484      0.003039         0.018548        0.002206   \n",
              "22       0.087496      0.000569         0.009319        0.000232   \n",
              "23       0.178796      0.003863         0.017478        0.000202   \n",
              "24       0.093506      0.003730         0.010473        0.001755   \n",
              "25       0.178586      0.004483         0.018553        0.003129   \n",
              "26       0.088651      0.000575         0.009946        0.001126   \n",
              "27       0.177700      0.005832         0.019019        0.002725   \n",
              "28       0.090918      0.002177         0.010934        0.002485   \n",
              "29       0.179740      0.003483         0.017779        0.000394   \n",
              "30       0.093243      0.002103         0.009684        0.000083   \n",
              "31       0.182238      0.001781         0.018135        0.001760   \n",
              "32       0.093033      0.001682         0.010435        0.002085   \n",
              "33       0.187471      0.006322         0.017541        0.000214   \n",
              "34       0.091866      0.001905         0.010136        0.001418   \n",
              "35       0.183826      0.003494         0.017657        0.000204   \n",
              "36       0.091187      0.003386         0.009164        0.000273   \n",
              "37       0.180893      0.004827         0.017355        0.000301   \n",
              "38       0.091917      0.001632         0.009654        0.000137   \n",
              "39       0.181940      0.004010         0.018582        0.002309   \n",
              "40       0.092350      0.001557         0.010607        0.001990   \n",
              "41       0.182731      0.004445         0.017570        0.000466   \n",
              "42       0.092408      0.001946         0.009501        0.000127   \n",
              "43       0.182746      0.003197         0.017309        0.000596   \n",
              "44       0.093263      0.001284         0.010144        0.000796   \n",
              "45       0.183393      0.001904         0.017431        0.000156   \n",
              "46       0.094824      0.004720         0.009761        0.000458   \n",
              "47       0.185458      0.002083         0.018365        0.001235   \n",
              "48       0.093251      0.001934         0.009487        0.000394   \n",
              "49       0.181085      0.002804         0.017156        0.000392   \n",
              "50       0.092073      0.001644         0.009928        0.000854   \n",
              "51       0.185385      0.002047         0.018065        0.000291   \n",
              "52       0.093282      0.001958         0.009568        0.000108   \n",
              "53       0.184738      0.002042         0.017547        0.001022   \n",
              "54       0.091844      0.001637         0.009257        0.000146   \n",
              "55       0.184317      0.001959         0.017457        0.000218   \n",
              "56       0.092334      0.001572         0.010403        0.002108   \n",
              "57       0.182806      0.002918         0.017022        0.000247   \n",
              "58       0.092353      0.001215         0.009551        0.000441   \n",
              "59       0.184691      0.004088         0.017436        0.000253   \n",
              "\n",
              "   param_criterion param_max_depth param_max_features param_n_estimators  \\\n",
              "0             gini               4               auto                100   \n",
              "1             gini               4               auto                200   \n",
              "2             gini               4               sqrt                100   \n",
              "3             gini               4               sqrt                200   \n",
              "4             gini               4               log2                100   \n",
              "5             gini               4               log2                200   \n",
              "6             gini               5               auto                100   \n",
              "7             gini               5               auto                200   \n",
              "8             gini               5               sqrt                100   \n",
              "9             gini               5               sqrt                200   \n",
              "10            gini               5               log2                100   \n",
              "11            gini               5               log2                200   \n",
              "12            gini               6               auto                100   \n",
              "13            gini               6               auto                200   \n",
              "14            gini               6               sqrt                100   \n",
              "15            gini               6               sqrt                200   \n",
              "16            gini               6               log2                100   \n",
              "17            gini               6               log2                200   \n",
              "18            gini               7               auto                100   \n",
              "19            gini               7               auto                200   \n",
              "20            gini               7               sqrt                100   \n",
              "21            gini               7               sqrt                200   \n",
              "22            gini               7               log2                100   \n",
              "23            gini               7               log2                200   \n",
              "24            gini               8               auto                100   \n",
              "25            gini               8               auto                200   \n",
              "26            gini               8               sqrt                100   \n",
              "27            gini               8               sqrt                200   \n",
              "28            gini               8               log2                100   \n",
              "29            gini               8               log2                200   \n",
              "30         entropy               4               auto                100   \n",
              "31         entropy               4               auto                200   \n",
              "32         entropy               4               sqrt                100   \n",
              "33         entropy               4               sqrt                200   \n",
              "34         entropy               4               log2                100   \n",
              "35         entropy               4               log2                200   \n",
              "36         entropy               5               auto                100   \n",
              "37         entropy               5               auto                200   \n",
              "38         entropy               5               sqrt                100   \n",
              "39         entropy               5               sqrt                200   \n",
              "40         entropy               5               log2                100   \n",
              "41         entropy               5               log2                200   \n",
              "42         entropy               6               auto                100   \n",
              "43         entropy               6               auto                200   \n",
              "44         entropy               6               sqrt                100   \n",
              "45         entropy               6               sqrt                200   \n",
              "46         entropy               6               log2                100   \n",
              "47         entropy               6               log2                200   \n",
              "48         entropy               7               auto                100   \n",
              "49         entropy               7               auto                200   \n",
              "50         entropy               7               sqrt                100   \n",
              "51         entropy               7               sqrt                200   \n",
              "52         entropy               7               log2                100   \n",
              "53         entropy               7               log2                200   \n",
              "54         entropy               8               auto                100   \n",
              "55         entropy               8               auto                200   \n",
              "56         entropy               8               sqrt                100   \n",
              "57         entropy               8               sqrt                200   \n",
              "58         entropy               8               log2                100   \n",
              "59         entropy               8               log2                200   \n",
              "\n",
              "                                               params  split0_test_score  \\\n",
              "0   {'criterion': 'gini', 'max_depth': 4, 'max_fea...                1.0   \n",
              "1   {'criterion': 'gini', 'max_depth': 4, 'max_fea...                1.0   \n",
              "2   {'criterion': 'gini', 'max_depth': 4, 'max_fea...                1.0   \n",
              "3   {'criterion': 'gini', 'max_depth': 4, 'max_fea...                1.0   \n",
              "4   {'criterion': 'gini', 'max_depth': 4, 'max_fea...                1.0   \n",
              "5   {'criterion': 'gini', 'max_depth': 4, 'max_fea...                1.0   \n",
              "6   {'criterion': 'gini', 'max_depth': 5, 'max_fea...                1.0   \n",
              "7   {'criterion': 'gini', 'max_depth': 5, 'max_fea...                1.0   \n",
              "8   {'criterion': 'gini', 'max_depth': 5, 'max_fea...                1.0   \n",
              "9   {'criterion': 'gini', 'max_depth': 5, 'max_fea...                1.0   \n",
              "10  {'criterion': 'gini', 'max_depth': 5, 'max_fea...                1.0   \n",
              "11  {'criterion': 'gini', 'max_depth': 5, 'max_fea...                1.0   \n",
              "12  {'criterion': 'gini', 'max_depth': 6, 'max_fea...                1.0   \n",
              "13  {'criterion': 'gini', 'max_depth': 6, 'max_fea...                1.0   \n",
              "14  {'criterion': 'gini', 'max_depth': 6, 'max_fea...                1.0   \n",
              "15  {'criterion': 'gini', 'max_depth': 6, 'max_fea...                1.0   \n",
              "16  {'criterion': 'gini', 'max_depth': 6, 'max_fea...                1.0   \n",
              "17  {'criterion': 'gini', 'max_depth': 6, 'max_fea...                1.0   \n",
              "18  {'criterion': 'gini', 'max_depth': 7, 'max_fea...                1.0   \n",
              "19  {'criterion': 'gini', 'max_depth': 7, 'max_fea...                1.0   \n",
              "20  {'criterion': 'gini', 'max_depth': 7, 'max_fea...                1.0   \n",
              "21  {'criterion': 'gini', 'max_depth': 7, 'max_fea...                1.0   \n",
              "22  {'criterion': 'gini', 'max_depth': 7, 'max_fea...                1.0   \n",
              "23  {'criterion': 'gini', 'max_depth': 7, 'max_fea...                1.0   \n",
              "24  {'criterion': 'gini', 'max_depth': 8, 'max_fea...                1.0   \n",
              "25  {'criterion': 'gini', 'max_depth': 8, 'max_fea...                1.0   \n",
              "26  {'criterion': 'gini', 'max_depth': 8, 'max_fea...                1.0   \n",
              "27  {'criterion': 'gini', 'max_depth': 8, 'max_fea...                1.0   \n",
              "28  {'criterion': 'gini', 'max_depth': 8, 'max_fea...                1.0   \n",
              "29  {'criterion': 'gini', 'max_depth': 8, 'max_fea...                1.0   \n",
              "30  {'criterion': 'entropy', 'max_depth': 4, 'max_...                1.0   \n",
              "31  {'criterion': 'entropy', 'max_depth': 4, 'max_...                1.0   \n",
              "32  {'criterion': 'entropy', 'max_depth': 4, 'max_...                1.0   \n",
              "33  {'criterion': 'entropy', 'max_depth': 4, 'max_...                1.0   \n",
              "34  {'criterion': 'entropy', 'max_depth': 4, 'max_...                1.0   \n",
              "35  {'criterion': 'entropy', 'max_depth': 4, 'max_...                1.0   \n",
              "36  {'criterion': 'entropy', 'max_depth': 5, 'max_...                1.0   \n",
              "37  {'criterion': 'entropy', 'max_depth': 5, 'max_...                1.0   \n",
              "38  {'criterion': 'entropy', 'max_depth': 5, 'max_...                1.0   \n",
              "39  {'criterion': 'entropy', 'max_depth': 5, 'max_...                1.0   \n",
              "40  {'criterion': 'entropy', 'max_depth': 5, 'max_...                1.0   \n",
              "41  {'criterion': 'entropy', 'max_depth': 5, 'max_...                1.0   \n",
              "42  {'criterion': 'entropy', 'max_depth': 6, 'max_...                1.0   \n",
              "43  {'criterion': 'entropy', 'max_depth': 6, 'max_...                1.0   \n",
              "44  {'criterion': 'entropy', 'max_depth': 6, 'max_...                1.0   \n",
              "45  {'criterion': 'entropy', 'max_depth': 6, 'max_...                1.0   \n",
              "46  {'criterion': 'entropy', 'max_depth': 6, 'max_...                1.0   \n",
              "47  {'criterion': 'entropy', 'max_depth': 6, 'max_...                1.0   \n",
              "48  {'criterion': 'entropy', 'max_depth': 7, 'max_...                1.0   \n",
              "49  {'criterion': 'entropy', 'max_depth': 7, 'max_...                1.0   \n",
              "50  {'criterion': 'entropy', 'max_depth': 7, 'max_...                1.0   \n",
              "51  {'criterion': 'entropy', 'max_depth': 7, 'max_...                1.0   \n",
              "52  {'criterion': 'entropy', 'max_depth': 7, 'max_...                1.0   \n",
              "53  {'criterion': 'entropy', 'max_depth': 7, 'max_...                1.0   \n",
              "54  {'criterion': 'entropy', 'max_depth': 8, 'max_...                1.0   \n",
              "55  {'criterion': 'entropy', 'max_depth': 8, 'max_...                1.0   \n",
              "56  {'criterion': 'entropy', 'max_depth': 8, 'max_...                1.0   \n",
              "57  {'criterion': 'entropy', 'max_depth': 8, 'max_...                1.0   \n",
              "58  {'criterion': 'entropy', 'max_depth': 8, 'max_...                1.0   \n",
              "59  {'criterion': 'entropy', 'max_depth': 8, 'max_...                1.0   \n",
              "\n",
              "    split1_test_score  split2_test_score  split3_test_score  \\\n",
              "0                 1.0                1.0                1.0   \n",
              "1                 1.0                1.0                1.0   \n",
              "2                 1.0                1.0                1.0   \n",
              "3                 1.0                1.0                1.0   \n",
              "4                 1.0                1.0                1.0   \n",
              "5                 1.0                1.0                1.0   \n",
              "6                 1.0                1.0                1.0   \n",
              "7                 1.0                1.0                1.0   \n",
              "8                 1.0                1.0                1.0   \n",
              "9                 1.0                1.0                1.0   \n",
              "10                1.0                1.0                1.0   \n",
              "11                1.0                1.0                1.0   \n",
              "12                1.0                1.0                1.0   \n",
              "13                1.0                1.0                1.0   \n",
              "14                1.0                1.0                1.0   \n",
              "15                1.0                1.0                1.0   \n",
              "16                1.0                1.0                1.0   \n",
              "17                1.0                1.0                1.0   \n",
              "18                1.0                1.0                1.0   \n",
              "19                1.0                1.0                1.0   \n",
              "20                1.0                1.0                1.0   \n",
              "21                1.0                1.0                1.0   \n",
              "22                1.0                1.0                1.0   \n",
              "23                1.0                1.0                1.0   \n",
              "24                1.0                1.0                1.0   \n",
              "25                1.0                1.0                1.0   \n",
              "26                1.0                1.0                1.0   \n",
              "27                1.0                1.0                1.0   \n",
              "28                1.0                1.0                1.0   \n",
              "29                1.0                1.0                1.0   \n",
              "30                1.0                1.0                1.0   \n",
              "31                1.0                1.0                1.0   \n",
              "32                1.0                1.0                1.0   \n",
              "33                1.0                1.0                1.0   \n",
              "34                1.0                1.0                1.0   \n",
              "35                1.0                1.0                1.0   \n",
              "36                1.0                1.0                1.0   \n",
              "37                1.0                1.0                1.0   \n",
              "38                1.0                1.0                1.0   \n",
              "39                1.0                1.0                1.0   \n",
              "40                1.0                1.0                1.0   \n",
              "41                1.0                1.0                1.0   \n",
              "42                1.0                1.0                1.0   \n",
              "43                1.0                1.0                1.0   \n",
              "44                1.0                1.0                1.0   \n",
              "45                1.0                1.0                1.0   \n",
              "46                1.0                1.0                1.0   \n",
              "47                1.0                1.0                1.0   \n",
              "48                1.0                1.0                1.0   \n",
              "49                1.0                1.0                1.0   \n",
              "50                1.0                1.0                1.0   \n",
              "51                1.0                1.0                1.0   \n",
              "52                1.0                1.0                1.0   \n",
              "53                1.0                1.0                1.0   \n",
              "54                1.0                1.0                1.0   \n",
              "55                1.0                1.0                1.0   \n",
              "56                1.0                1.0                1.0   \n",
              "57                1.0                1.0                1.0   \n",
              "58                1.0                1.0                1.0   \n",
              "59                1.0                1.0                1.0   \n",
              "\n",
              "    split4_test_score  mean_test_score  std_test_score  rank_test_score  \n",
              "0                 1.0              1.0             0.0                1  \n",
              "1                 1.0              1.0             0.0                1  \n",
              "2                 1.0              1.0             0.0                1  \n",
              "3                 1.0              1.0             0.0                1  \n",
              "4                 1.0              1.0             0.0                1  \n",
              "5                 1.0              1.0             0.0                1  \n",
              "6                 1.0              1.0             0.0                1  \n",
              "7                 1.0              1.0             0.0                1  \n",
              "8                 1.0              1.0             0.0                1  \n",
              "9                 1.0              1.0             0.0                1  \n",
              "10                1.0              1.0             0.0                1  \n",
              "11                1.0              1.0             0.0                1  \n",
              "12                1.0              1.0             0.0                1  \n",
              "13                1.0              1.0             0.0                1  \n",
              "14                1.0              1.0             0.0                1  \n",
              "15                1.0              1.0             0.0                1  \n",
              "16                1.0              1.0             0.0                1  \n",
              "17                1.0              1.0             0.0                1  \n",
              "18                1.0              1.0             0.0                1  \n",
              "19                1.0              1.0             0.0                1  \n",
              "20                1.0              1.0             0.0                1  \n",
              "21                1.0              1.0             0.0                1  \n",
              "22                1.0              1.0             0.0                1  \n",
              "23                1.0              1.0             0.0                1  \n",
              "24                1.0              1.0             0.0                1  \n",
              "25                1.0              1.0             0.0                1  \n",
              "26                1.0              1.0             0.0                1  \n",
              "27                1.0              1.0             0.0                1  \n",
              "28                1.0              1.0             0.0                1  \n",
              "29                1.0              1.0             0.0                1  \n",
              "30                1.0              1.0             0.0                1  \n",
              "31                1.0              1.0             0.0                1  \n",
              "32                1.0              1.0             0.0                1  \n",
              "33                1.0              1.0             0.0                1  \n",
              "34                1.0              1.0             0.0                1  \n",
              "35                1.0              1.0             0.0                1  \n",
              "36                1.0              1.0             0.0                1  \n",
              "37                1.0              1.0             0.0                1  \n",
              "38                1.0              1.0             0.0                1  \n",
              "39                1.0              1.0             0.0                1  \n",
              "40                1.0              1.0             0.0                1  \n",
              "41                1.0              1.0             0.0                1  \n",
              "42                1.0              1.0             0.0                1  \n",
              "43                1.0              1.0             0.0                1  \n",
              "44                1.0              1.0             0.0                1  \n",
              "45                1.0              1.0             0.0                1  \n",
              "46                1.0              1.0             0.0                1  \n",
              "47                1.0              1.0             0.0                1  \n",
              "48                1.0              1.0             0.0                1  \n",
              "49                1.0              1.0             0.0                1  \n",
              "50                1.0              1.0             0.0                1  \n",
              "51                1.0              1.0             0.0                1  \n",
              "52                1.0              1.0             0.0                1  \n",
              "53                1.0              1.0             0.0                1  \n",
              "54                1.0              1.0             0.0                1  \n",
              "55                1.0              1.0             0.0                1  \n",
              "56                1.0              1.0             0.0                1  \n",
              "57                1.0              1.0             0.0                1  \n",
              "58                1.0              1.0             0.0                1  \n",
              "59                1.0              1.0             0.0                1  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e3775b5c-e80d-474e-83dc-f7415f294c44\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>mean_fit_time</th>\n",
              "      <th>std_fit_time</th>\n",
              "      <th>mean_score_time</th>\n",
              "      <th>std_score_time</th>\n",
              "      <th>param_criterion</th>\n",
              "      <th>param_max_depth</th>\n",
              "      <th>param_max_features</th>\n",
              "      <th>param_n_estimators</th>\n",
              "      <th>params</th>\n",
              "      <th>split0_test_score</th>\n",
              "      <th>split1_test_score</th>\n",
              "      <th>split2_test_score</th>\n",
              "      <th>split3_test_score</th>\n",
              "      <th>split4_test_score</th>\n",
              "      <th>mean_test_score</th>\n",
              "      <th>std_test_score</th>\n",
              "      <th>rank_test_score</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.100403</td>\n",
              "      <td>0.006763</td>\n",
              "      <td>0.009660</td>\n",
              "      <td>0.000159</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 4, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.327439</td>\n",
              "      <td>0.054140</td>\n",
              "      <td>0.037076</td>\n",
              "      <td>0.013445</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 4, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.188850</td>\n",
              "      <td>0.015696</td>\n",
              "      <td>0.018509</td>\n",
              "      <td>0.004457</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 4, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.376880</td>\n",
              "      <td>0.084570</td>\n",
              "      <td>0.034417</td>\n",
              "      <td>0.009061</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 4, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.181233</td>\n",
              "      <td>0.022171</td>\n",
              "      <td>0.019296</td>\n",
              "      <td>0.007473</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 4, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>0.378149</td>\n",
              "      <td>0.025261</td>\n",
              "      <td>0.036858</td>\n",
              "      <td>0.007663</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 4, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>0.192932</td>\n",
              "      <td>0.018827</td>\n",
              "      <td>0.016456</td>\n",
              "      <td>0.002682</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 5, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>0.440149</td>\n",
              "      <td>0.090096</td>\n",
              "      <td>0.030511</td>\n",
              "      <td>0.005882</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 5, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>0.193913</td>\n",
              "      <td>0.024873</td>\n",
              "      <td>0.016588</td>\n",
              "      <td>0.001679</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 5, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>0.461781</td>\n",
              "      <td>0.093131</td>\n",
              "      <td>0.040512</td>\n",
              "      <td>0.020394</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 5, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>10</th>\n",
              "      <td>0.193877</td>\n",
              "      <td>0.026465</td>\n",
              "      <td>0.014699</td>\n",
              "      <td>0.001913</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 5, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>11</th>\n",
              "      <td>0.176172</td>\n",
              "      <td>0.006187</td>\n",
              "      <td>0.016887</td>\n",
              "      <td>0.000829</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 5, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>12</th>\n",
              "      <td>0.087693</td>\n",
              "      <td>0.002432</td>\n",
              "      <td>0.009062</td>\n",
              "      <td>0.000312</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 6, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>13</th>\n",
              "      <td>0.177697</td>\n",
              "      <td>0.002316</td>\n",
              "      <td>0.017710</td>\n",
              "      <td>0.000876</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 6, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>14</th>\n",
              "      <td>0.088754</td>\n",
              "      <td>0.000426</td>\n",
              "      <td>0.009300</td>\n",
              "      <td>0.000150</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 6, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15</th>\n",
              "      <td>0.177619</td>\n",
              "      <td>0.004404</td>\n",
              "      <td>0.018476</td>\n",
              "      <td>0.001760</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 6, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>16</th>\n",
              "      <td>0.090718</td>\n",
              "      <td>0.002312</td>\n",
              "      <td>0.010613</td>\n",
              "      <td>0.000966</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 6, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17</th>\n",
              "      <td>0.178221</td>\n",
              "      <td>0.002614</td>\n",
              "      <td>0.019069</td>\n",
              "      <td>0.003727</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 6, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>18</th>\n",
              "      <td>0.088292</td>\n",
              "      <td>0.001143</td>\n",
              "      <td>0.009201</td>\n",
              "      <td>0.000160</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 7, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>19</th>\n",
              "      <td>0.184407</td>\n",
              "      <td>0.003162</td>\n",
              "      <td>0.018138</td>\n",
              "      <td>0.000758</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 7, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>20</th>\n",
              "      <td>0.092214</td>\n",
              "      <td>0.001452</td>\n",
              "      <td>0.009688</td>\n",
              "      <td>0.000365</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 7, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>21</th>\n",
              "      <td>0.178484</td>\n",
              "      <td>0.003039</td>\n",
              "      <td>0.018548</td>\n",
              "      <td>0.002206</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 7, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>22</th>\n",
              "      <td>0.087496</td>\n",
              "      <td>0.000569</td>\n",
              "      <td>0.009319</td>\n",
              "      <td>0.000232</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 7, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>23</th>\n",
              "      <td>0.178796</td>\n",
              "      <td>0.003863</td>\n",
              "      <td>0.017478</td>\n",
              "      <td>0.000202</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 7, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>24</th>\n",
              "      <td>0.093506</td>\n",
              "      <td>0.003730</td>\n",
              "      <td>0.010473</td>\n",
              "      <td>0.001755</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 8, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25</th>\n",
              "      <td>0.178586</td>\n",
              "      <td>0.004483</td>\n",
              "      <td>0.018553</td>\n",
              "      <td>0.003129</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 8, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26</th>\n",
              "      <td>0.088651</td>\n",
              "      <td>0.000575</td>\n",
              "      <td>0.009946</td>\n",
              "      <td>0.001126</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 8, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>27</th>\n",
              "      <td>0.177700</td>\n",
              "      <td>0.005832</td>\n",
              "      <td>0.019019</td>\n",
              "      <td>0.002725</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 8, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>28</th>\n",
              "      <td>0.090918</td>\n",
              "      <td>0.002177</td>\n",
              "      <td>0.010934</td>\n",
              "      <td>0.002485</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 8, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>29</th>\n",
              "      <td>0.179740</td>\n",
              "      <td>0.003483</td>\n",
              "      <td>0.017779</td>\n",
              "      <td>0.000394</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'gini', 'max_depth': 8, 'max_fea...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>30</th>\n",
              "      <td>0.093243</td>\n",
              "      <td>0.002103</td>\n",
              "      <td>0.009684</td>\n",
              "      <td>0.000083</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 4, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>31</th>\n",
              "      <td>0.182238</td>\n",
              "      <td>0.001781</td>\n",
              "      <td>0.018135</td>\n",
              "      <td>0.001760</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 4, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>32</th>\n",
              "      <td>0.093033</td>\n",
              "      <td>0.001682</td>\n",
              "      <td>0.010435</td>\n",
              "      <td>0.002085</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 4, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>33</th>\n",
              "      <td>0.187471</td>\n",
              "      <td>0.006322</td>\n",
              "      <td>0.017541</td>\n",
              "      <td>0.000214</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 4, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>34</th>\n",
              "      <td>0.091866</td>\n",
              "      <td>0.001905</td>\n",
              "      <td>0.010136</td>\n",
              "      <td>0.001418</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 4, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>35</th>\n",
              "      <td>0.183826</td>\n",
              "      <td>0.003494</td>\n",
              "      <td>0.017657</td>\n",
              "      <td>0.000204</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 4, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>36</th>\n",
              "      <td>0.091187</td>\n",
              "      <td>0.003386</td>\n",
              "      <td>0.009164</td>\n",
              "      <td>0.000273</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 5, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>37</th>\n",
              "      <td>0.180893</td>\n",
              "      <td>0.004827</td>\n",
              "      <td>0.017355</td>\n",
              "      <td>0.000301</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 5, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>38</th>\n",
              "      <td>0.091917</td>\n",
              "      <td>0.001632</td>\n",
              "      <td>0.009654</td>\n",
              "      <td>0.000137</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 5, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>39</th>\n",
              "      <td>0.181940</td>\n",
              "      <td>0.004010</td>\n",
              "      <td>0.018582</td>\n",
              "      <td>0.002309</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 5, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>40</th>\n",
              "      <td>0.092350</td>\n",
              "      <td>0.001557</td>\n",
              "      <td>0.010607</td>\n",
              "      <td>0.001990</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 5, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>41</th>\n",
              "      <td>0.182731</td>\n",
              "      <td>0.004445</td>\n",
              "      <td>0.017570</td>\n",
              "      <td>0.000466</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 5, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>42</th>\n",
              "      <td>0.092408</td>\n",
              "      <td>0.001946</td>\n",
              "      <td>0.009501</td>\n",
              "      <td>0.000127</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 6, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>43</th>\n",
              "      <td>0.182746</td>\n",
              "      <td>0.003197</td>\n",
              "      <td>0.017309</td>\n",
              "      <td>0.000596</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 6, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>44</th>\n",
              "      <td>0.093263</td>\n",
              "      <td>0.001284</td>\n",
              "      <td>0.010144</td>\n",
              "      <td>0.000796</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 6, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>45</th>\n",
              "      <td>0.183393</td>\n",
              "      <td>0.001904</td>\n",
              "      <td>0.017431</td>\n",
              "      <td>0.000156</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 6, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>46</th>\n",
              "      <td>0.094824</td>\n",
              "      <td>0.004720</td>\n",
              "      <td>0.009761</td>\n",
              "      <td>0.000458</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 6, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>47</th>\n",
              "      <td>0.185458</td>\n",
              "      <td>0.002083</td>\n",
              "      <td>0.018365</td>\n",
              "      <td>0.001235</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 6, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>48</th>\n",
              "      <td>0.093251</td>\n",
              "      <td>0.001934</td>\n",
              "      <td>0.009487</td>\n",
              "      <td>0.000394</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 7, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49</th>\n",
              "      <td>0.181085</td>\n",
              "      <td>0.002804</td>\n",
              "      <td>0.017156</td>\n",
              "      <td>0.000392</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 7, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50</th>\n",
              "      <td>0.092073</td>\n",
              "      <td>0.001644</td>\n",
              "      <td>0.009928</td>\n",
              "      <td>0.000854</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 7, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>51</th>\n",
              "      <td>0.185385</td>\n",
              "      <td>0.002047</td>\n",
              "      <td>0.018065</td>\n",
              "      <td>0.000291</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 7, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>52</th>\n",
              "      <td>0.093282</td>\n",
              "      <td>0.001958</td>\n",
              "      <td>0.009568</td>\n",
              "      <td>0.000108</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 7, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>53</th>\n",
              "      <td>0.184738</td>\n",
              "      <td>0.002042</td>\n",
              "      <td>0.017547</td>\n",
              "      <td>0.001022</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 7, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>54</th>\n",
              "      <td>0.091844</td>\n",
              "      <td>0.001637</td>\n",
              "      <td>0.009257</td>\n",
              "      <td>0.000146</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 8, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>55</th>\n",
              "      <td>0.184317</td>\n",
              "      <td>0.001959</td>\n",
              "      <td>0.017457</td>\n",
              "      <td>0.000218</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 8, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>56</th>\n",
              "      <td>0.092334</td>\n",
              "      <td>0.001572</td>\n",
              "      <td>0.010403</td>\n",
              "      <td>0.002108</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 8, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>57</th>\n",
              "      <td>0.182806</td>\n",
              "      <td>0.002918</td>\n",
              "      <td>0.017022</td>\n",
              "      <td>0.000247</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 8, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>58</th>\n",
              "      <td>0.092353</td>\n",
              "      <td>0.001215</td>\n",
              "      <td>0.009551</td>\n",
              "      <td>0.000441</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 8, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>59</th>\n",
              "      <td>0.184691</td>\n",
              "      <td>0.004088</td>\n",
              "      <td>0.017436</td>\n",
              "      <td>0.000253</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'criterion': 'entropy', 'max_depth': 8, 'max_...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e3775b5c-e80d-474e-83dc-f7415f294c44')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-e3775b5c-e80d-474e-83dc-f7415f294c44 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-e3775b5c-e80d-474e-83dc-f7415f294c44');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 29
        }
      ],
      "source": [
        "# The params column has all of the options that we gave the snapshot of above.\n",
        "pd.DataFrame(CV_rfc.cv_results_)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "0GZDrjfuH1bQ"
      },
      "source": [
        "### Choice of Grid Values"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "i2zG5DzFH1bQ"
      },
      "source": [
        "Which values should you pick for your grid? Intuitively, you should try both \"large\" and \"small\" values, but of course what counts as large and small will really depend on the type of hyperparameter."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "Q9NM-N2tH1bQ"
      },
      "source": [
        "- For a decision tree model, what counts as a small `max_depth` will really depend on the size of your training data. A `max_depth` of 5 would likely have little effect on a very small dataset but, at the same time, it would probably significantly decrease the variance of a model where the dataset is large.\n",
        "- For a logistic regression's regularization constant, you may want to try a set of values that are exponentially separated, like \\[1, 10, 100, 1000\\].\n",
        "- **If a grid search finds optimal values at the ends of your hyperparameter ranges, you might try another grid search with more extreme values.**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "67TrOmgmH1bQ"
      },
      "source": [
        "### Exercise"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "xZdpFtroH1bR"
      },
      "source": [
        "Do a grid search on a **decision tree model** of penguin species. What are the optimal values for the hyperparameters you've chosen?"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Grid search on decision tree model\n"
      ],
      "metadata": {
        "id": "KierGFiJCH4-"
      },
      "execution_count": 30,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "If your decision tree performs as well as your random forest, then by Occam's Razor it is best to pick the simplest model, i.e. the decision tree."
      ],
      "metadata": {
        "id": "mDJ5AXsRBMht"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "id": "Ik0eUjwKH1bR"
      },
      "source": [
        "# Better Process: Pipelines"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "lfrFDaSvH1bR"
      },
      "source": [
        "> **Pipelines** can keep our code neat and clean all the way from gathering & cleaning our data, to creating models & fine-tuning them!"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "bxHTArPPH1bR"
      },
      "source": [
        "![](https://imgs.xkcd.com/comics/data_pipeline.png)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "KP06lO_6H1bR"
      },
      "source": [
        "The `Pipeline` class from [Scikit-Learn's API](https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html) is especially convenient since it allows us to use our other Estimators that we know and love!"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "pOZZBx0OH1bR"
      },
      "source": [
        "## Advantages of `Pipeline`"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "FtLgU5CNH1bR"
      },
      "source": [
        "### Reduces Complexity"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "6o2vwDUEH1bR"
      },
      "source": [
        "> You can focus on particular parts of the pipeline one at a time and debug or adjust parts as needed."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "P-ENI9MtH1bR"
      },
      "source": [
        "### Convenient"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "xW5TvN1fH1bR"
      },
      "source": [
        "> The pipeline summarizes your fine-detail steps. That way you can focus on the big-picture aspects."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "zrpyS_Z8H1bR"
      },
      "source": [
        "### Flexible"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "Qp87KSHPH1bR"
      },
      "source": [
        "> You can use pipelines with different models and with GridSearch."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "RK21KxfYH1bR"
      },
      "source": [
        "### Prevent Mistakes"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "Rw4lPhZEH1bR"
      },
      "source": [
        "> We can focus on one section at a time.\n",
        ">\n",
        "> We also can ensure data leakage between our training and doesn't occur between our training dataset and validation/testing datasets!"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "p7KeF3pHH1bR"
      },
      "source": [
        "## Example of Using `Pipeline`"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 31,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:53.002370Z",
          "start_time": "2021-10-28T03:33:52.905962Z"
        },
        "hidden": true,
        "id": "vSZGC1ulH1bR"
      },
      "outputs": [],
      "source": [
        "# Getting some data\n",
        "from sklearn import datasets\n",
        "\n",
        "iris = datasets.load_iris()\n",
        "X = iris.data\n",
        "y = iris.target\n",
        "\n",
        "# Split\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, \n",
        "                                                    random_state=27)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "AKdwjg3cH1bR"
      },
      "source": [
        "### Without the Pipeline class"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 32,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:54.664937Z",
          "start_time": "2021-10-28T03:33:54.657819Z"
        },
        "hidden": true,
        "id": "gpIb3xbTH1bS",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7e7bd0c1-9fb0-4720-fe16-e115e58271d1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[2 0 2 2 1 1 1 2 2 0 1 1 0 1 1 1 0 2 2 2 1 0 1 0 2 2 1 0 1 2]\n"
          ]
        }
      ],
      "source": [
        "# Define transformers (will adjust/massage the data)\n",
        "imputer = SimpleImputer(strategy=\"median\") # replaces missing values\n",
        "std_scaler = StandardScaler() # scales the data\n",
        "\n",
        "# Define the classifier (predictor) to train\n",
        "rf_clf = DecisionTreeClassifier(random_state=42)\n",
        "\n",
        "# Have the classifer (and full pipeline) learn/train/fit from the data\n",
        "X_train_filled = imputer.fit_transform(X_train)\n",
        "X_train_scaled = std_scaler.fit_transform(X_train_filled)\n",
        "rf_clf.fit(X_train_scaled, y_train)\n",
        "\n",
        "# Predict using the trained classifier (still need to do the transformations)\n",
        "X_test_filled = imputer.transform(X_test)\n",
        "X_test_scaled = std_scaler.transform(X_test_filled)\n",
        "y_pred = rf_clf.predict(X_test_scaled)\n",
        "print(y_pred)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "ZgThvR8rH1bS"
      },
      "source": [
        "> Note that if we were to add more steps in this process, we'd have to change both the *training* and *testing* processes."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "x-mcUVblH1bS"
      },
      "source": [
        "### With `Pipeline` Class"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 33,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:33:58.205429Z",
          "start_time": "2021-10-28T03:33:58.198897Z"
        },
        "hidden": true,
        "id": "_pVdI0jAH1bS",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "a028bb2b-35bd-451f-8a02-0d7bc44f43ce"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[2 0 2 2 1 1 1 2 2 0 1 1 0 1 1 1 0 2 2 2 1 0 1 0 2 2 1 0 1 2]\n"
          ]
        }
      ],
      "source": [
        "pipeline = Pipeline([\n",
        "        ('imputer', SimpleImputer(strategy=\"median\")), \n",
        "        ('std_scaler', StandardScaler()),\n",
        "        ('rf_clf', DecisionTreeClassifier(random_state=42)),\n",
        "])\n",
        "\n",
        "\n",
        "# Train the pipeline (tranformations & predictor)\n",
        "pipeline.fit(X_train, y_train)\n",
        "\n",
        "# Predict using the pipeline (includes the transfomers & trained predictor)\n",
        "predicted = pipeline.predict(X_test)\n",
        "print(predicted)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 34,
      "metadata": {
        "id": "zyTvCzpLH1bS",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "6b73a7ea-7095-4f5c-e356-fa96cb4f7b2d"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "SimpleImputer(strategy='median')"
            ]
          },
          "metadata": {},
          "execution_count": 34
        }
      ],
      "source": [
        "pipeline['imputer']"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "21fz2dmDH1bS"
      },
      "source": [
        "> If we need to change our process, we change it _just once_ in the Pipeline"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "2aFEzCDmH1bS"
      },
      "source": [
        "## Grid Searching a Pipeline"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "yEa0HL-_H1bS"
      },
      "source": [
        "> Let's first get our data prepared like we did before"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 35,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:01.754929Z",
          "start_time": "2021-10-28T03:34:01.746719Z"
        },
        "hidden": true,
        "id": "9yScprwbH1bS"
      },
      "outputs": [],
      "source": [
        "penguins = sns.load_dataset('penguins')\n",
        "penguins = penguins.dropna()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 36,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:02.556723Z",
          "start_time": "2021-10-28T03:34:02.552362Z"
        },
        "hidden": true,
        "id": "_cmykqvyH1bS"
      },
      "outputs": [],
      "source": [
        "y = penguins.pop('species')\n",
        "X_train, X_test, y_train, y_test = train_test_split(\n",
        "    penguins, y, test_size=0.5, random_state=42)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 37,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:03.045865Z",
          "start_time": "2021-10-28T03:34:03.037423Z"
        },
        "hidden": true,
        "id": "cyYmixqOH1bS"
      },
      "outputs": [],
      "source": [
        "X_train_nums = X_train.select_dtypes('float64')\n",
        "\n",
        "ss = StandardScaler()\n",
        "\n",
        "ss.fit(X_train_nums)\n",
        "nums_df = pd.DataFrame(ss.transform(X_train_nums),\n",
        "                      index=X_train_nums.index)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 38,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:04.617701Z",
          "start_time": "2021-10-28T03:34:04.611557Z"
        },
        "hidden": true,
        "id": "b99qmmabH1bS"
      },
      "outputs": [],
      "source": [
        "X_train_cat = X_train.select_dtypes('object')\n",
        "\n",
        "ohe = OneHotEncoder(\n",
        "    drop='first',\n",
        "    sparse=False)\n",
        "\n",
        "dums = ohe.fit_transform(X_train_cat)\n",
        "dums_df = pd.DataFrame(dums,\n",
        "                       columns=ohe.get_feature_names(),\n",
        "                       index=X_train_cat.index)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "_hlCek-JH1bS"
      },
      "source": [
        "> Intermediary step to treat categorical and numerical data differently"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "QDAoODBUH1bS"
      },
      "source": [
        "### Using `ColumnTransformer`"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 39,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:07.230978Z",
          "start_time": "2021-10-28T03:34:07.226999Z"
        },
        "id": "ffe_ylWZH1bS",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "2ef3cc1e-7c5f-4681-c121-de5c2c586fed"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Index(['bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g'], dtype='object')"
            ]
          },
          "metadata": {},
          "execution_count": 39
        }
      ],
      "source": [
        "X_train_nums.columns"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 40,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:07.623709Z",
          "start_time": "2021-10-28T03:34:07.620047Z"
        },
        "hidden": true,
        "id": "CFCktUV7H1bT"
      },
      "outputs": [],
      "source": [
        "numerical_pipeline = Pipeline(steps=[\n",
        "    ('ss', StandardScaler())\n",
        "])\n",
        "                \n",
        "categorical_pipeline = Pipeline(steps=[\n",
        "    ('ohe', OneHotEncoder(drop='first',\n",
        "                         sparse=False))\n",
        "])\n",
        "\n",
        "trans = ColumnTransformer(transformers=[\n",
        "    ('numerical', numerical_pipeline, X_train_nums.columns),\n",
        "    ('categorical', categorical_pipeline, X_train_cat.columns)\n",
        "])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 41,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:09.542917Z",
          "start_time": "2021-10-28T03:34:09.540088Z"
        },
        "hidden": true,
        "id": "ygtqjud2H1bT"
      },
      "outputs": [],
      "source": [
        "model_pipe = Pipeline(steps=[\n",
        "    ('trans', trans),\n",
        "    ('rfc', RandomForestClassifier(random_state = 42))\n",
        "])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "yrdABNH3H1bT"
      },
      "source": [
        "> Finally showing we can fit the full pipeline"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 42,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:13.295438Z",
          "start_time": "2021-10-28T03:34:13.263487Z"
        },
        "hidden": true,
        "id": "IOkja9UfH1bT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b4c1b7b1-6691-47f1-eb5d-2b53cde3acb4"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Pipeline(steps=[('trans',\n",
              "                 ColumnTransformer(transformers=[('numerical',\n",
              "                                                  Pipeline(steps=[('ss',\n",
              "                                                                   StandardScaler())]),\n",
              "                                                  Index(['bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g'], dtype='object')),\n",
              "                                                 ('categorical',\n",
              "                                                  Pipeline(steps=[('ohe',\n",
              "                                                                   OneHotEncoder(drop='first',\n",
              "                                                                                 sparse=False))]),\n",
              "                                                  Index(['island', 'sex'], dtype='object'))])),\n",
              "                ('rfc', RandomForestClassifier(random_state=42))])"
            ]
          },
          "metadata": {},
          "execution_count": 42
        }
      ],
      "source": [
        "model_pipe.fit(X_train, y_train)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 43,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:13.618940Z",
          "start_time": "2021-10-28T03:34:13.603520Z"
        },
        "hidden": true,
        "id": "xWmjBZo5H1bT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "78451be8-90d3-47c5-ced6-9593ddc115e9"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1.0"
            ]
          },
          "metadata": {},
          "execution_count": 43
        }
      ],
      "source": [
        "model_pipe.score(X_train, y_train)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "_eWR3axbH1bT"
      },
      "source": [
        "> Performing grid search on the full pipeline.\n",
        "Copy and past the result from `CV_rfc.param_grid'."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 44,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:16.220781Z",
          "start_time": "2021-10-28T03:34:16.217965Z"
        },
        "hidden": true,
        "id": "TYQcIy7aH1bT"
      },
      "outputs": [],
      "source": [
        "# For the .fit to work correctly in the next block of code, the parameters with the grid must be appended by rfc__ .\n",
        "# This is since that is the name we gave the RamdomTreeClassifer() when we defined Pipeline().\n",
        "# N.B. That is two underscores after rfc!\n",
        "\n",
        "pipe_grid = {'rfc__n_estimators': [100, 200],\n",
        " 'rfc__max_features': ['auto', 'sqrt', 'log2'],\n",
        " 'rfc__max_depth': [4, 5, 6, 7, 8],\n",
        " 'rfc__criterion': ['gini', 'entropy']}\n",
        "\n",
        "gs_pipe = GridSearchCV(estimator=model_pipe, param_grid=pipe_grid)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 45,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:17.181559Z",
          "start_time": "2021-10-28T03:34:16.542973Z"
        },
        "hidden": true,
        "id": "vp6aB5q-H1bT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "13d13417-2777-4541-fe5e-44d566363973"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(estimator=Pipeline(steps=[('trans',\n",
              "                                        ColumnTransformer(transformers=[('numerical',\n",
              "                                                                         Pipeline(steps=[('ss',\n",
              "                                                                                          StandardScaler())]),\n",
              "                                                                         Index(['bill_length_mm', 'bill_depth_mm', 'flipper_length_mm', 'body_mass_g'], dtype='object')),\n",
              "                                                                        ('categorical',\n",
              "                                                                         Pipeline(steps=[('ohe',\n",
              "                                                                                          OneHotEncoder(drop='first',\n",
              "                                                                                                        sparse=False))]),\n",
              "                                                                         Index(['island', 'sex'], dtype='object'))])),\n",
              "                                       ('rfc',\n",
              "                                        RandomForestClassifier(random_state=42))]),\n",
              "             param_grid={'rfc__criterion': ['gini', 'entropy'],\n",
              "                         'rfc__max_depth': [4, 5, 6, 7, 8],\n",
              "                         'rfc__max_features': ['auto', 'sqrt', 'log2'],\n",
              "                         'rfc__n_estimators': [100, 200]})"
            ]
          },
          "metadata": {},
          "execution_count": 45
        }
      ],
      "source": [
        "gs_pipe.fit(X_train, y_train)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 46,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:17.201665Z",
          "start_time": "2021-10-28T03:34:17.183254Z"
        },
        "hidden": true,
        "id": "7-be2VIiH1bT",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "3d70a698-9a3d-4117-ff20-e8d7eeb76378"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "    mean_fit_time  std_fit_time  mean_score_time  std_score_time  \\\n",
              "0        0.111023      0.011433         0.012563        0.001503   \n",
              "1        0.183906      0.002403         0.020397        0.002105   \n",
              "2        0.094998      0.002342         0.012999        0.001786   \n",
              "3        0.254508      0.138868         0.026519        0.014778   \n",
              "4        0.168174      0.124877         0.021047        0.012063   \n",
              "5        0.257884      0.149015         0.024631        0.007732   \n",
              "6        0.095281      0.001626         0.011678        0.000376   \n",
              "7        0.185602      0.004091         0.022044        0.002133   \n",
              "8        0.097428      0.002938         0.012592        0.001029   \n",
              "9        0.185458      0.002650         0.019903        0.000311   \n",
              "10       0.098786      0.009012         0.012090        0.000686   \n",
              "11       0.185033      0.004874         0.022337        0.002588   \n",
              "12       0.095849      0.002064         0.011578        0.000098   \n",
              "13       0.186085      0.003390         0.019865        0.000199   \n",
              "14       0.095479      0.003102         0.011547        0.000162   \n",
              "15       0.184624      0.004396         0.021759        0.001806   \n",
              "16       0.095781      0.003191         0.011549        0.000239   \n",
              "17       0.188229      0.002127         0.021187        0.002142   \n",
              "18       0.096282      0.003817         0.012591        0.001928   \n",
              "19       0.184800      0.002830         0.020975        0.001519   \n",
              "20       0.095722      0.001888         0.012681        0.001614   \n",
              "21       0.184990      0.004245         0.020375        0.001161   \n",
              "22       0.097488      0.006296         0.011720        0.000201   \n",
              "23       0.187842      0.005468         0.021441        0.002259   \n",
              "24       0.093332      0.000974         0.011548        0.000186   \n",
              "25       0.183427      0.004882         0.023013        0.003690   \n",
              "26       0.094893      0.002178         0.013211        0.002181   \n",
              "27       0.182575      0.003168         0.024601        0.004880   \n",
              "28       0.094627      0.000937         0.012775        0.001017   \n",
              "29       0.184692      0.003012         0.021543        0.003715   \n",
              "30       0.105584      0.009489         0.014673        0.002832   \n",
              "31       0.275020      0.011384         0.025412        0.000663   \n",
              "32       0.096465      0.002041         0.012641        0.001959   \n",
              "33       0.188252      0.005504         0.020808        0.001840   \n",
              "34       0.102124      0.006069         0.012724        0.001448   \n",
              "35       0.190200      0.004527         0.019312        0.000737   \n",
              "36       0.094715      0.000886         0.011673        0.000190   \n",
              "37       0.185882      0.003682         0.020216        0.001987   \n",
              "38       0.097725      0.001652         0.011071        0.000129   \n",
              "39       0.186276      0.001131         0.020351        0.002086   \n",
              "40       0.093506      0.003323         0.012343        0.001831   \n",
              "41       0.182880      0.001534         0.019117        0.000648   \n",
              "42       0.097344      0.005491         0.014179        0.001873   \n",
              "43       0.184524      0.003262         0.020037        0.001794   \n",
              "44       0.094403      0.002175         0.011156        0.000389   \n",
              "45       0.185083      0.003988         0.022371        0.003091   \n",
              "46       0.096014      0.003153         0.011179        0.000345   \n",
              "47       0.186285      0.002189         0.020154        0.001718   \n",
              "48       0.099635      0.003457         0.011257        0.000502   \n",
              "49       0.184550      0.001906         0.020074        0.002434   \n",
              "50       0.093693      0.000567         0.011006        0.000260   \n",
              "51       0.185253      0.005284         0.020315        0.002665   \n",
              "52       0.097362      0.003008         0.011231        0.000246   \n",
              "53       0.185700      0.005131         0.020181        0.002238   \n",
              "54       0.092985      0.001066         0.011812        0.001788   \n",
              "55       0.186557      0.004201         0.021094        0.003369   \n",
              "56       0.097084      0.003346         0.011214        0.000163   \n",
              "57       0.183019      0.002741         0.018897        0.000668   \n",
              "58       0.094486      0.002788         0.011581        0.000817   \n",
              "59       0.184231      0.005874         0.020041        0.001369   \n",
              "\n",
              "   param_rfc__criterion param_rfc__max_depth param_rfc__max_features  \\\n",
              "0                  gini                    4                    auto   \n",
              "1                  gini                    4                    auto   \n",
              "2                  gini                    4                    sqrt   \n",
              "3                  gini                    4                    sqrt   \n",
              "4                  gini                    4                    log2   \n",
              "5                  gini                    4                    log2   \n",
              "6                  gini                    5                    auto   \n",
              "7                  gini                    5                    auto   \n",
              "8                  gini                    5                    sqrt   \n",
              "9                  gini                    5                    sqrt   \n",
              "10                 gini                    5                    log2   \n",
              "11                 gini                    5                    log2   \n",
              "12                 gini                    6                    auto   \n",
              "13                 gini                    6                    auto   \n",
              "14                 gini                    6                    sqrt   \n",
              "15                 gini                    6                    sqrt   \n",
              "16                 gini                    6                    log2   \n",
              "17                 gini                    6                    log2   \n",
              "18                 gini                    7                    auto   \n",
              "19                 gini                    7                    auto   \n",
              "20                 gini                    7                    sqrt   \n",
              "21                 gini                    7                    sqrt   \n",
              "22                 gini                    7                    log2   \n",
              "23                 gini                    7                    log2   \n",
              "24                 gini                    8                    auto   \n",
              "25                 gini                    8                    auto   \n",
              "26                 gini                    8                    sqrt   \n",
              "27                 gini                    8                    sqrt   \n",
              "28                 gini                    8                    log2   \n",
              "29                 gini                    8                    log2   \n",
              "30              entropy                    4                    auto   \n",
              "31              entropy                    4                    auto   \n",
              "32              entropy                    4                    sqrt   \n",
              "33              entropy                    4                    sqrt   \n",
              "34              entropy                    4                    log2   \n",
              "35              entropy                    4                    log2   \n",
              "36              entropy                    5                    auto   \n",
              "37              entropy                    5                    auto   \n",
              "38              entropy                    5                    sqrt   \n",
              "39              entropy                    5                    sqrt   \n",
              "40              entropy                    5                    log2   \n",
              "41              entropy                    5                    log2   \n",
              "42              entropy                    6                    auto   \n",
              "43              entropy                    6                    auto   \n",
              "44              entropy                    6                    sqrt   \n",
              "45              entropy                    6                    sqrt   \n",
              "46              entropy                    6                    log2   \n",
              "47              entropy                    6                    log2   \n",
              "48              entropy                    7                    auto   \n",
              "49              entropy                    7                    auto   \n",
              "50              entropy                    7                    sqrt   \n",
              "51              entropy                    7                    sqrt   \n",
              "52              entropy                    7                    log2   \n",
              "53              entropy                    7                    log2   \n",
              "54              entropy                    8                    auto   \n",
              "55              entropy                    8                    auto   \n",
              "56              entropy                    8                    sqrt   \n",
              "57              entropy                    8                    sqrt   \n",
              "58              entropy                    8                    log2   \n",
              "59              entropy                    8                    log2   \n",
              "\n",
              "   param_rfc__n_estimators                                             params  \\\n",
              "0                      100  {'rfc__criterion': 'gini', 'rfc__max_depth': 4...   \n",
              "1                      200  {'rfc__criterion': 'gini', 'rfc__max_depth': 4...   \n",
              "2                      100  {'rfc__criterion': 'gini', 'rfc__max_depth': 4...   \n",
              "3                      200  {'rfc__criterion': 'gini', 'rfc__max_depth': 4...   \n",
              "4                      100  {'rfc__criterion': 'gini', 'rfc__max_depth': 4...   \n",
              "5                      200  {'rfc__criterion': 'gini', 'rfc__max_depth': 4...   \n",
              "6                      100  {'rfc__criterion': 'gini', 'rfc__max_depth': 5...   \n",
              "7                      200  {'rfc__criterion': 'gini', 'rfc__max_depth': 5...   \n",
              "8                      100  {'rfc__criterion': 'gini', 'rfc__max_depth': 5...   \n",
              "9                      200  {'rfc__criterion': 'gini', 'rfc__max_depth': 5...   \n",
              "10                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 5...   \n",
              "11                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 5...   \n",
              "12                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 6...   \n",
              "13                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 6...   \n",
              "14                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 6...   \n",
              "15                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 6...   \n",
              "16                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 6...   \n",
              "17                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 6...   \n",
              "18                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 7...   \n",
              "19                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 7...   \n",
              "20                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 7...   \n",
              "21                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 7...   \n",
              "22                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 7...   \n",
              "23                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 7...   \n",
              "24                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 8...   \n",
              "25                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 8...   \n",
              "26                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 8...   \n",
              "27                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 8...   \n",
              "28                     100  {'rfc__criterion': 'gini', 'rfc__max_depth': 8...   \n",
              "29                     200  {'rfc__criterion': 'gini', 'rfc__max_depth': 8...   \n",
              "30                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "31                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "32                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "33                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "34                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "35                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "36                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "37                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "38                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "39                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "40                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "41                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "42                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "43                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "44                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "45                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "46                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "47                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "48                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "49                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "50                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "51                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "52                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "53                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "54                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "55                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "56                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "57                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "58                     100  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "59                     200  {'rfc__criterion': 'entropy', 'rfc__max_depth'...   \n",
              "\n",
              "    split0_test_score  split1_test_score  split2_test_score  \\\n",
              "0                 1.0                1.0                1.0   \n",
              "1                 1.0                1.0                1.0   \n",
              "2                 1.0                1.0                1.0   \n",
              "3                 1.0                1.0                1.0   \n",
              "4                 1.0                1.0                1.0   \n",
              "5                 1.0                1.0                1.0   \n",
              "6                 1.0                1.0                1.0   \n",
              "7                 1.0                1.0                1.0   \n",
              "8                 1.0                1.0                1.0   \n",
              "9                 1.0                1.0                1.0   \n",
              "10                1.0                1.0                1.0   \n",
              "11                1.0                1.0                1.0   \n",
              "12                1.0                1.0                1.0   \n",
              "13                1.0                1.0                1.0   \n",
              "14                1.0                1.0                1.0   \n",
              "15                1.0                1.0                1.0   \n",
              "16                1.0                1.0                1.0   \n",
              "17                1.0                1.0                1.0   \n",
              "18                1.0                1.0                1.0   \n",
              "19                1.0                1.0                1.0   \n",
              "20                1.0                1.0                1.0   \n",
              "21                1.0                1.0                1.0   \n",
              "22                1.0                1.0                1.0   \n",
              "23                1.0                1.0                1.0   \n",
              "24                1.0                1.0                1.0   \n",
              "25                1.0                1.0                1.0   \n",
              "26                1.0                1.0                1.0   \n",
              "27                1.0                1.0                1.0   \n",
              "28                1.0                1.0                1.0   \n",
              "29                1.0                1.0                1.0   \n",
              "30                1.0                1.0                1.0   \n",
              "31                1.0                1.0                1.0   \n",
              "32                1.0                1.0                1.0   \n",
              "33                1.0                1.0                1.0   \n",
              "34                1.0                1.0                1.0   \n",
              "35                1.0                1.0                1.0   \n",
              "36                1.0                1.0                1.0   \n",
              "37                1.0                1.0                1.0   \n",
              "38                1.0                1.0                1.0   \n",
              "39                1.0                1.0                1.0   \n",
              "40                1.0                1.0                1.0   \n",
              "41                1.0                1.0                1.0   \n",
              "42                1.0                1.0                1.0   \n",
              "43                1.0                1.0                1.0   \n",
              "44                1.0                1.0                1.0   \n",
              "45                1.0                1.0                1.0   \n",
              "46                1.0                1.0                1.0   \n",
              "47                1.0                1.0                1.0   \n",
              "48                1.0                1.0                1.0   \n",
              "49                1.0                1.0                1.0   \n",
              "50                1.0                1.0                1.0   \n",
              "51                1.0                1.0                1.0   \n",
              "52                1.0                1.0                1.0   \n",
              "53                1.0                1.0                1.0   \n",
              "54                1.0                1.0                1.0   \n",
              "55                1.0                1.0                1.0   \n",
              "56                1.0                1.0                1.0   \n",
              "57                1.0                1.0                1.0   \n",
              "58                1.0                1.0                1.0   \n",
              "59                1.0                1.0                1.0   \n",
              "\n",
              "    split3_test_score  split4_test_score  mean_test_score  std_test_score  \\\n",
              "0                 1.0                1.0              1.0             0.0   \n",
              "1                 1.0                1.0              1.0             0.0   \n",
              "2                 1.0                1.0              1.0             0.0   \n",
              "3                 1.0                1.0              1.0             0.0   \n",
              "4                 1.0                1.0              1.0             0.0   \n",
              "5                 1.0                1.0              1.0             0.0   \n",
              "6                 1.0                1.0              1.0             0.0   \n",
              "7                 1.0                1.0              1.0             0.0   \n",
              "8                 1.0                1.0              1.0             0.0   \n",
              "9                 1.0                1.0              1.0             0.0   \n",
              "10                1.0                1.0              1.0             0.0   \n",
              "11                1.0                1.0              1.0             0.0   \n",
              "12                1.0                1.0              1.0             0.0   \n",
              "13                1.0                1.0              1.0             0.0   \n",
              "14                1.0                1.0              1.0             0.0   \n",
              "15                1.0                1.0              1.0             0.0   \n",
              "16                1.0                1.0              1.0             0.0   \n",
              "17                1.0                1.0              1.0             0.0   \n",
              "18                1.0                1.0              1.0             0.0   \n",
              "19                1.0                1.0              1.0             0.0   \n",
              "20                1.0                1.0              1.0             0.0   \n",
              "21                1.0                1.0              1.0             0.0   \n",
              "22                1.0                1.0              1.0             0.0   \n",
              "23                1.0                1.0              1.0             0.0   \n",
              "24                1.0                1.0              1.0             0.0   \n",
              "25                1.0                1.0              1.0             0.0   \n",
              "26                1.0                1.0              1.0             0.0   \n",
              "27                1.0                1.0              1.0             0.0   \n",
              "28                1.0                1.0              1.0             0.0   \n",
              "29                1.0                1.0              1.0             0.0   \n",
              "30                1.0                1.0              1.0             0.0   \n",
              "31                1.0                1.0              1.0             0.0   \n",
              "32                1.0                1.0              1.0             0.0   \n",
              "33                1.0                1.0              1.0             0.0   \n",
              "34                1.0                1.0              1.0             0.0   \n",
              "35                1.0                1.0              1.0             0.0   \n",
              "36                1.0                1.0              1.0             0.0   \n",
              "37                1.0                1.0              1.0             0.0   \n",
              "38                1.0                1.0              1.0             0.0   \n",
              "39                1.0                1.0              1.0             0.0   \n",
              "40                1.0                1.0              1.0             0.0   \n",
              "41                1.0                1.0              1.0             0.0   \n",
              "42                1.0                1.0              1.0             0.0   \n",
              "43                1.0                1.0              1.0             0.0   \n",
              "44                1.0                1.0              1.0             0.0   \n",
              "45                1.0                1.0              1.0             0.0   \n",
              "46                1.0                1.0              1.0             0.0   \n",
              "47                1.0                1.0              1.0             0.0   \n",
              "48                1.0                1.0              1.0             0.0   \n",
              "49                1.0                1.0              1.0             0.0   \n",
              "50                1.0                1.0              1.0             0.0   \n",
              "51                1.0                1.0              1.0             0.0   \n",
              "52                1.0                1.0              1.0             0.0   \n",
              "53                1.0                1.0              1.0             0.0   \n",
              "54                1.0                1.0              1.0             0.0   \n",
              "55                1.0                1.0              1.0             0.0   \n",
              "56                1.0                1.0              1.0             0.0   \n",
              "57                1.0                1.0              1.0             0.0   \n",
              "58                1.0                1.0              1.0             0.0   \n",
              "59                1.0                1.0              1.0             0.0   \n",
              "\n",
              "    rank_test_score  \n",
              "0                 1  \n",
              "1                 1  \n",
              "2                 1  \n",
              "3                 1  \n",
              "4                 1  \n",
              "5                 1  \n",
              "6                 1  \n",
              "7                 1  \n",
              "8                 1  \n",
              "9                 1  \n",
              "10                1  \n",
              "11                1  \n",
              "12                1  \n",
              "13                1  \n",
              "14                1  \n",
              "15                1  \n",
              "16                1  \n",
              "17                1  \n",
              "18                1  \n",
              "19                1  \n",
              "20                1  \n",
              "21                1  \n",
              "22                1  \n",
              "23                1  \n",
              "24                1  \n",
              "25                1  \n",
              "26                1  \n",
              "27                1  \n",
              "28                1  \n",
              "29                1  \n",
              "30                1  \n",
              "31                1  \n",
              "32                1  \n",
              "33                1  \n",
              "34                1  \n",
              "35                1  \n",
              "36                1  \n",
              "37                1  \n",
              "38                1  \n",
              "39                1  \n",
              "40                1  \n",
              "41                1  \n",
              "42                1  \n",
              "43                1  \n",
              "44                1  \n",
              "45                1  \n",
              "46                1  \n",
              "47                1  \n",
              "48                1  \n",
              "49                1  \n",
              "50                1  \n",
              "51                1  \n",
              "52                1  \n",
              "53                1  \n",
              "54                1  \n",
              "55                1  \n",
              "56                1  \n",
              "57                1  \n",
              "58                1  \n",
              "59                1  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-cfeb4246-80a3-4dae-8a61-621c5efcdc22\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>mean_fit_time</th>\n",
              "      <th>std_fit_time</th>\n",
              "      <th>mean_score_time</th>\n",
              "      <th>std_score_time</th>\n",
              "      <th>param_rfc__criterion</th>\n",
              "      <th>param_rfc__max_depth</th>\n",
              "      <th>param_rfc__max_features</th>\n",
              "      <th>param_rfc__n_estimators</th>\n",
              "      <th>params</th>\n",
              "      <th>split0_test_score</th>\n",
              "      <th>split1_test_score</th>\n",
              "      <th>split2_test_score</th>\n",
              "      <th>split3_test_score</th>\n",
              "      <th>split4_test_score</th>\n",
              "      <th>mean_test_score</th>\n",
              "      <th>std_test_score</th>\n",
              "      <th>rank_test_score</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.111023</td>\n",
              "      <td>0.011433</td>\n",
              "      <td>0.012563</td>\n",
              "      <td>0.001503</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 4...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.183906</td>\n",
              "      <td>0.002403</td>\n",
              "      <td>0.020397</td>\n",
              "      <td>0.002105</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 4...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.094998</td>\n",
              "      <td>0.002342</td>\n",
              "      <td>0.012999</td>\n",
              "      <td>0.001786</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 4...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.254508</td>\n",
              "      <td>0.138868</td>\n",
              "      <td>0.026519</td>\n",
              "      <td>0.014778</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 4...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.168174</td>\n",
              "      <td>0.124877</td>\n",
              "      <td>0.021047</td>\n",
              "      <td>0.012063</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 4...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>0.257884</td>\n",
              "      <td>0.149015</td>\n",
              "      <td>0.024631</td>\n",
              "      <td>0.007732</td>\n",
              "      <td>gini</td>\n",
              "      <td>4</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 4...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>0.095281</td>\n",
              "      <td>0.001626</td>\n",
              "      <td>0.011678</td>\n",
              "      <td>0.000376</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 5...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>0.185602</td>\n",
              "      <td>0.004091</td>\n",
              "      <td>0.022044</td>\n",
              "      <td>0.002133</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 5...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>0.097428</td>\n",
              "      <td>0.002938</td>\n",
              "      <td>0.012592</td>\n",
              "      <td>0.001029</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 5...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>0.185458</td>\n",
              "      <td>0.002650</td>\n",
              "      <td>0.019903</td>\n",
              "      <td>0.000311</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 5...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>10</th>\n",
              "      <td>0.098786</td>\n",
              "      <td>0.009012</td>\n",
              "      <td>0.012090</td>\n",
              "      <td>0.000686</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 5...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>11</th>\n",
              "      <td>0.185033</td>\n",
              "      <td>0.004874</td>\n",
              "      <td>0.022337</td>\n",
              "      <td>0.002588</td>\n",
              "      <td>gini</td>\n",
              "      <td>5</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 5...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>12</th>\n",
              "      <td>0.095849</td>\n",
              "      <td>0.002064</td>\n",
              "      <td>0.011578</td>\n",
              "      <td>0.000098</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 6...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>13</th>\n",
              "      <td>0.186085</td>\n",
              "      <td>0.003390</td>\n",
              "      <td>0.019865</td>\n",
              "      <td>0.000199</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 6...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>14</th>\n",
              "      <td>0.095479</td>\n",
              "      <td>0.003102</td>\n",
              "      <td>0.011547</td>\n",
              "      <td>0.000162</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 6...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15</th>\n",
              "      <td>0.184624</td>\n",
              "      <td>0.004396</td>\n",
              "      <td>0.021759</td>\n",
              "      <td>0.001806</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 6...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>16</th>\n",
              "      <td>0.095781</td>\n",
              "      <td>0.003191</td>\n",
              "      <td>0.011549</td>\n",
              "      <td>0.000239</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 6...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17</th>\n",
              "      <td>0.188229</td>\n",
              "      <td>0.002127</td>\n",
              "      <td>0.021187</td>\n",
              "      <td>0.002142</td>\n",
              "      <td>gini</td>\n",
              "      <td>6</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 6...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>18</th>\n",
              "      <td>0.096282</td>\n",
              "      <td>0.003817</td>\n",
              "      <td>0.012591</td>\n",
              "      <td>0.001928</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 7...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>19</th>\n",
              "      <td>0.184800</td>\n",
              "      <td>0.002830</td>\n",
              "      <td>0.020975</td>\n",
              "      <td>0.001519</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 7...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>20</th>\n",
              "      <td>0.095722</td>\n",
              "      <td>0.001888</td>\n",
              "      <td>0.012681</td>\n",
              "      <td>0.001614</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 7...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>21</th>\n",
              "      <td>0.184990</td>\n",
              "      <td>0.004245</td>\n",
              "      <td>0.020375</td>\n",
              "      <td>0.001161</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 7...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>22</th>\n",
              "      <td>0.097488</td>\n",
              "      <td>0.006296</td>\n",
              "      <td>0.011720</td>\n",
              "      <td>0.000201</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 7...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>23</th>\n",
              "      <td>0.187842</td>\n",
              "      <td>0.005468</td>\n",
              "      <td>0.021441</td>\n",
              "      <td>0.002259</td>\n",
              "      <td>gini</td>\n",
              "      <td>7</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 7...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>24</th>\n",
              "      <td>0.093332</td>\n",
              "      <td>0.000974</td>\n",
              "      <td>0.011548</td>\n",
              "      <td>0.000186</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 8...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25</th>\n",
              "      <td>0.183427</td>\n",
              "      <td>0.004882</td>\n",
              "      <td>0.023013</td>\n",
              "      <td>0.003690</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 8...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26</th>\n",
              "      <td>0.094893</td>\n",
              "      <td>0.002178</td>\n",
              "      <td>0.013211</td>\n",
              "      <td>0.002181</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 8...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>27</th>\n",
              "      <td>0.182575</td>\n",
              "      <td>0.003168</td>\n",
              "      <td>0.024601</td>\n",
              "      <td>0.004880</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 8...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>28</th>\n",
              "      <td>0.094627</td>\n",
              "      <td>0.000937</td>\n",
              "      <td>0.012775</td>\n",
              "      <td>0.001017</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 8...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>29</th>\n",
              "      <td>0.184692</td>\n",
              "      <td>0.003012</td>\n",
              "      <td>0.021543</td>\n",
              "      <td>0.003715</td>\n",
              "      <td>gini</td>\n",
              "      <td>8</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'gini', 'rfc__max_depth': 8...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>30</th>\n",
              "      <td>0.105584</td>\n",
              "      <td>0.009489</td>\n",
              "      <td>0.014673</td>\n",
              "      <td>0.002832</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>31</th>\n",
              "      <td>0.275020</td>\n",
              "      <td>0.011384</td>\n",
              "      <td>0.025412</td>\n",
              "      <td>0.000663</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>32</th>\n",
              "      <td>0.096465</td>\n",
              "      <td>0.002041</td>\n",
              "      <td>0.012641</td>\n",
              "      <td>0.001959</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>33</th>\n",
              "      <td>0.188252</td>\n",
              "      <td>0.005504</td>\n",
              "      <td>0.020808</td>\n",
              "      <td>0.001840</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>34</th>\n",
              "      <td>0.102124</td>\n",
              "      <td>0.006069</td>\n",
              "      <td>0.012724</td>\n",
              "      <td>0.001448</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>35</th>\n",
              "      <td>0.190200</td>\n",
              "      <td>0.004527</td>\n",
              "      <td>0.019312</td>\n",
              "      <td>0.000737</td>\n",
              "      <td>entropy</td>\n",
              "      <td>4</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>36</th>\n",
              "      <td>0.094715</td>\n",
              "      <td>0.000886</td>\n",
              "      <td>0.011673</td>\n",
              "      <td>0.000190</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>37</th>\n",
              "      <td>0.185882</td>\n",
              "      <td>0.003682</td>\n",
              "      <td>0.020216</td>\n",
              "      <td>0.001987</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>38</th>\n",
              "      <td>0.097725</td>\n",
              "      <td>0.001652</td>\n",
              "      <td>0.011071</td>\n",
              "      <td>0.000129</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>39</th>\n",
              "      <td>0.186276</td>\n",
              "      <td>0.001131</td>\n",
              "      <td>0.020351</td>\n",
              "      <td>0.002086</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>40</th>\n",
              "      <td>0.093506</td>\n",
              "      <td>0.003323</td>\n",
              "      <td>0.012343</td>\n",
              "      <td>0.001831</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>41</th>\n",
              "      <td>0.182880</td>\n",
              "      <td>0.001534</td>\n",
              "      <td>0.019117</td>\n",
              "      <td>0.000648</td>\n",
              "      <td>entropy</td>\n",
              "      <td>5</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>42</th>\n",
              "      <td>0.097344</td>\n",
              "      <td>0.005491</td>\n",
              "      <td>0.014179</td>\n",
              "      <td>0.001873</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>43</th>\n",
              "      <td>0.184524</td>\n",
              "      <td>0.003262</td>\n",
              "      <td>0.020037</td>\n",
              "      <td>0.001794</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>44</th>\n",
              "      <td>0.094403</td>\n",
              "      <td>0.002175</td>\n",
              "      <td>0.011156</td>\n",
              "      <td>0.000389</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>45</th>\n",
              "      <td>0.185083</td>\n",
              "      <td>0.003988</td>\n",
              "      <td>0.022371</td>\n",
              "      <td>0.003091</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>46</th>\n",
              "      <td>0.096014</td>\n",
              "      <td>0.003153</td>\n",
              "      <td>0.011179</td>\n",
              "      <td>0.000345</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>47</th>\n",
              "      <td>0.186285</td>\n",
              "      <td>0.002189</td>\n",
              "      <td>0.020154</td>\n",
              "      <td>0.001718</td>\n",
              "      <td>entropy</td>\n",
              "      <td>6</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>48</th>\n",
              "      <td>0.099635</td>\n",
              "      <td>0.003457</td>\n",
              "      <td>0.011257</td>\n",
              "      <td>0.000502</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49</th>\n",
              "      <td>0.184550</td>\n",
              "      <td>0.001906</td>\n",
              "      <td>0.020074</td>\n",
              "      <td>0.002434</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50</th>\n",
              "      <td>0.093693</td>\n",
              "      <td>0.000567</td>\n",
              "      <td>0.011006</td>\n",
              "      <td>0.000260</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>51</th>\n",
              "      <td>0.185253</td>\n",
              "      <td>0.005284</td>\n",
              "      <td>0.020315</td>\n",
              "      <td>0.002665</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>52</th>\n",
              "      <td>0.097362</td>\n",
              "      <td>0.003008</td>\n",
              "      <td>0.011231</td>\n",
              "      <td>0.000246</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>53</th>\n",
              "      <td>0.185700</td>\n",
              "      <td>0.005131</td>\n",
              "      <td>0.020181</td>\n",
              "      <td>0.002238</td>\n",
              "      <td>entropy</td>\n",
              "      <td>7</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>54</th>\n",
              "      <td>0.092985</td>\n",
              "      <td>0.001066</td>\n",
              "      <td>0.011812</td>\n",
              "      <td>0.001788</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>auto</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>55</th>\n",
              "      <td>0.186557</td>\n",
              "      <td>0.004201</td>\n",
              "      <td>0.021094</td>\n",
              "      <td>0.003369</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>auto</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>56</th>\n",
              "      <td>0.097084</td>\n",
              "      <td>0.003346</td>\n",
              "      <td>0.011214</td>\n",
              "      <td>0.000163</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>57</th>\n",
              "      <td>0.183019</td>\n",
              "      <td>0.002741</td>\n",
              "      <td>0.018897</td>\n",
              "      <td>0.000668</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>sqrt</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>58</th>\n",
              "      <td>0.094486</td>\n",
              "      <td>0.002788</td>\n",
              "      <td>0.011581</td>\n",
              "      <td>0.000817</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>log2</td>\n",
              "      <td>100</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>59</th>\n",
              "      <td>0.184231</td>\n",
              "      <td>0.005874</td>\n",
              "      <td>0.020041</td>\n",
              "      <td>0.001369</td>\n",
              "      <td>entropy</td>\n",
              "      <td>8</td>\n",
              "      <td>log2</td>\n",
              "      <td>200</td>\n",
              "      <td>{'rfc__criterion': 'entropy', 'rfc__max_depth'...</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-cfeb4246-80a3-4dae-8a61-621c5efcdc22')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-cfeb4246-80a3-4dae-8a61-621c5efcdc22 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-cfeb4246-80a3-4dae-8a61-621c5efcdc22');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 46
        }
      ],
      "source": [
        "pd.DataFrame(gs_pipe.cv_results_)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 47,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:17.390365Z",
          "start_time": "2021-10-28T03:34:17.386703Z"
        },
        "hidden": true,
        "scrolled": true,
        "id": "Hr3RKI49H1bT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "154818ab-9a0e-4f4c-f154-39e39e42b3eb"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'rfc__criterion': 'gini',\n",
              " 'rfc__max_depth': 4,\n",
              " 'rfc__max_features': 'auto',\n",
              " 'rfc__n_estimators': 100}"
            ]
          },
          "metadata": {},
          "execution_count": 47
        }
      ],
      "source": [
        "gs_pipe.best_params_"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "QUYjrodbH1bT"
      },
      "source": [
        "## A Note on Data Leakage"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "eUxpaMsiH1bT"
      },
      "source": [
        "Note we still have to be careful in performing a grid search!\n",
        "\n",
        "We can accidentally \"leak\" information by doing transformations with the **whole data set**, instead of just the **training set**!"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "Udoh_ExdH1bT"
      },
      "source": [
        "### Example of leaking information"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 48,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:20.651129Z",
          "start_time": "2021-10-28T03:34:20.342682Z"
        },
        "hidden": true,
        "id": "XgDNxEUhH1bT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "18159dff-4efb-4a0a-cebb-58c3c401ec9c"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "RandomForestClassifier()"
            ]
          },
          "metadata": {},
          "execution_count": 48
        }
      ],
      "source": [
        "scaler = StandardScaler()\n",
        "# Scales over all of the X-train data! (validation set will be considered in scaling)\n",
        "scaled_data = scaler.fit_transform(X_train.select_dtypes('float64'))\n",
        "\n",
        "parameters = {'rfc__n_estimators': [100, 200],\n",
        " 'rfc__max_features': ['auto', 'sqrt', 'log2'],\n",
        " 'rfc__max_depth': [4, 5, 6, 7, 8],\n",
        " 'rfc__criterion': ['gini', 'entropy']}\n",
        "\n",
        "rfc = RandomForestClassifier()\n",
        "rfc_cv = GridSearchCV(rfc, parameters)\n",
        "rfc.fit(X_train.select_dtypes('float64'), y_train)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "W2lemRinH1bT"
      },
      "source": [
        "### Example of Grid Search with no leakage"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 49,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:23.982285Z",
          "start_time": "2021-10-28T03:34:23.221271Z"
        },
        "hidden": true,
        "id": "gpUndDW7H1bT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "fb0b722f-caec-4e65-e013-bb5d6e4d8170"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['Adelie' 'Gentoo' 'Adelie' 'Chinstrap' 'Adelie' 'Gentoo' 'Gentoo'\n",
            " 'Chinstrap' 'Chinstrap' 'Chinstrap' 'Adelie' 'Adelie' 'Gentoo' 'Adelie'\n",
            " 'Gentoo' 'Adelie' 'Adelie' 'Chinstrap' 'Adelie' 'Gentoo' 'Chinstrap'\n",
            " 'Adelie' 'Gentoo' 'Chinstrap' 'Adelie' 'Adelie' 'Gentoo' 'Gentoo'\n",
            " 'Chinstrap' 'Gentoo' 'Chinstrap' 'Gentoo' 'Adelie' 'Adelie' 'Gentoo'\n",
            " 'Gentoo' 'Chinstrap' 'Gentoo' 'Adelie' 'Adelie' 'Adelie' 'Adelie'\n",
            " 'Chinstrap' 'Chinstrap' 'Adelie' 'Adelie' 'Gentoo' 'Adelie' 'Adelie'\n",
            " 'Gentoo' 'Adelie' 'Gentoo' 'Gentoo' 'Adelie' 'Adelie' 'Gentoo' 'Adelie'\n",
            " 'Adelie' 'Chinstrap' 'Chinstrap' 'Gentoo' 'Gentoo' 'Gentoo' 'Adelie'\n",
            " 'Adelie' 'Gentoo' 'Adelie' 'Gentoo' 'Adelie' 'Gentoo' 'Adelie' 'Adelie'\n",
            " 'Gentoo' 'Gentoo' 'Gentoo' 'Chinstrap' 'Adelie' 'Adelie' 'Adelie'\n",
            " 'Gentoo' 'Adelie' 'Adelie' 'Adelie' 'Adelie' 'Gentoo' 'Gentoo' 'Adelie'\n",
            " 'Gentoo' 'Chinstrap' 'Chinstrap' 'Gentoo' 'Gentoo' 'Adelie' 'Adelie'\n",
            " 'Adelie' 'Adelie' 'Adelie' 'Chinstrap' 'Chinstrap' 'Adelie' 'Adelie'\n",
            " 'Gentoo' 'Gentoo' 'Adelie' 'Chinstrap' 'Adelie' 'Gentoo' 'Gentoo'\n",
            " 'Adelie' 'Chinstrap' 'Adelie' 'Gentoo' 'Adelie' 'Chinstrap' 'Chinstrap'\n",
            " 'Chinstrap' 'Adelie' 'Gentoo' 'Adelie' 'Chinstrap' 'Adelie' 'Gentoo'\n",
            " 'Gentoo' 'Adelie' 'Adelie' 'Gentoo' 'Adelie' 'Adelie' 'Adelie'\n",
            " 'Chinstrap' 'Adelie' 'Adelie' 'Chinstrap' 'Adelie' 'Adelie' 'Adelie'\n",
            " 'Gentoo' 'Chinstrap' 'Gentoo' 'Adelie' 'Chinstrap' 'Gentoo' 'Adelie'\n",
            " 'Gentoo' 'Chinstrap' 'Gentoo' 'Chinstrap' 'Gentoo' 'Gentoo' 'Gentoo'\n",
            " 'Chinstrap' 'Gentoo' 'Adelie' 'Adelie' 'Gentoo' 'Chinstrap' 'Chinstrap'\n",
            " 'Adelie' 'Chinstrap' 'Chinstrap' 'Adelie' 'Gentoo' 'Gentoo' 'Gentoo'\n",
            " 'Chinstrap' 'Gentoo' 'Gentoo']\n"
          ]
        }
      ],
      "source": [
        "pipeline = Pipeline([\n",
        "    ('scaler', StandardScaler()),\n",
        "    ('rfc', RandomForestClassifier())\n",
        "])\n",
        "\n",
        "# Note you use the part of the pipeline's name `NAME__{parameter}`\n",
        "parameters = {'rfc__n_estimators': [100, 200],\n",
        " 'rfc__max_features': ['auto', 'sqrt', 'log2'],\n",
        " 'rfc__max_depth': [4, 5, 6, 7, 8],\n",
        " 'rfc__criterion': ['gini', 'entropy']}\n",
        "\n",
        "cv = GridSearchCV(pipeline, param_grid=parameters)\n",
        "\n",
        "cv.fit(X_train.select_dtypes('float64'), y_train)\n",
        "y_pred = cv.predict(X_test.select_dtypes('float64'))\n",
        "print(y_pred)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "id": "SolzyK_aH1bU"
      },
      "source": [
        "# Grid Search Exercise"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "tcGJN5aNH1bU"
      },
      "source": [
        "Use a classifier of your choice to predict the category of price range for the phones in this dataset. Try tuning some hyperparameters using a grid search, and then write up a short paragraph about your findings."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 50,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:38.974212Z",
          "start_time": "2021-10-28T03:34:38.957557Z"
        },
        "hidden": true,
        "id": "nFBtKGGrH1bU"
      },
      "outputs": [],
      "source": [
        "#phones_train = pd.read_csv('data/train.csv')\n",
        "#phones_test = pd.read_csv('data/test.csv')"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "id": "nxRoLugpH1bU"
      },
      "source": [
        "# Level Up: Random Searching"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "hidden": true,
        "id": "E-N5Rn0TH1bU"
      },
      "source": [
        "It is also possible to search for good hyperparameter values randomly. This is a nice choice if computation time is an issue or if you are tuning over continuous hyperparameters."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "heading_collapsed": true,
        "hidden": true,
        "id": "r9hzFEr1H1bU"
      },
      "source": [
        "### `RandomizedSearchCV` with `LogisticRegression`"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 51,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:46.731177Z",
          "start_time": "2021-10-28T03:34:46.727225Z"
        },
        "hidden": true,
        "id": "2idaPvOWH1bU"
      },
      "outputs": [],
      "source": [
        "log_reg_grid = {'C': stats.uniform(loc=0, scale=10),\n",
        "               'l1_ratio': stats.expon(scale=0.2)}"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 52,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:34:49.166819Z",
          "start_time": "2021-10-28T03:34:48.678224Z"
        },
        "hidden": true,
        "id": "GM_K4Zc6H1bU",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ef38705e-98df-42c9-babf-306742185616"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'C': 3.745401188473625, 'l1_ratio': 0.6020242861835042}"
            ]
          },
          "metadata": {},
          "execution_count": 52
        }
      ],
      "source": [
        "rs = RandomizedSearchCV(estimator=LogisticRegression(penalty='elasticnet',\n",
        "                                                    solver='saga',\n",
        "                                                    max_iter=1000,\n",
        "                                                    random_state=42),\n",
        "                        param_distributions=log_reg_grid,\n",
        "                       random_state=42)\n",
        "\n",
        "rs.fit(X_train_clean, y_train)\n",
        "\n",
        "rs.best_params_"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-27T21:03:32.018295Z",
          "start_time": "2021-10-27T21:03:32.015972Z"
        },
        "id": "8JPm7CIZH1bU"
      },
      "source": [
        "# Level Up: SMOTE"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Kqc53V__H1bU"
      },
      "source": [
        "Often we encounter a problem of imbalance classification that there are too few observations of the minority class for a model to effectively learn the decision boundary. \n",
        "\n",
        "One way to solve this problem is to **oversample** the observations in the minority class (or alternatively **undersample** the observations in the majority class) by synthesizing new observation from the minority class.\n",
        "\n",
        "The most widely used approach to synthesizing new observations is called the **Synthetic Minority Oversampling Technique**, or **SMOTE** for short. \n",
        "\n",
        "Resource: https://arxiv.org/abs/1106.1813\n",
        "\n",
        "Before getting into the example, please note the following,\n",
        "\n",
        "1. Oversampling process is based on **k-nearest neighbors** of the minority class.\n",
        "2. Oversampling only works with **numerical predictors** since the synthetic observations are created based on the k-nearest neighbors algorithm, which is a distance based algorithm.  \n",
        "\n",
        "We use the Scikit-Learn's breast cancer dataset to demonstrate the use of SMOTE from imblearn package."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 53,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:40:52.976867Z",
          "start_time": "2021-10-28T03:40:52.960326Z"
        },
        "id": "HV7HfWPiH1bU"
      },
      "outputs": [],
      "source": [
        "from sklearn.datasets import load_breast_cancer\n",
        "\n",
        "# Load the data\n",
        "preds, target = load_breast_cancer(return_X_y=True)\n",
        "\n",
        "# Split into train and test\n",
        "X_train, X_test, y_train, y_test = train_test_split(preds, target,\n",
        "                                                   random_state=42)\n",
        "\n",
        "# Scale the data\n",
        "bc_scaler = StandardScaler()\n",
        "bc_scaler.fit(X_train)\n",
        "X_train_sc = bc_scaler.transform(X_train)\n",
        "X_test_sc = bc_scaler.transform(X_test)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 54,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T04:05:58.031838Z",
          "start_time": "2021-10-28T04:05:58.029009Z"
        },
        "id": "Yx_PLGpXH1bU"
      },
      "outputs": [],
      "source": [
        "# Import imblearn dependencies\n",
        "from imblearn.over_sampling import SMOTE\n",
        "from imblearn.under_sampling import RandomUnderSampler\n",
        "from imblearn.pipeline import Pipeline as imbPipeline\n",
        "from collections import Counter\n",
        "from matplotlib import pyplot\n",
        "from numpy import where"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4LRC8I8aH1bU"
      },
      "source": [
        "Note that we have an imbalance class for the target variable in this dataset."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 55,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:52:29.498843Z",
          "start_time": "2021-10-28T03:52:29.235296Z"
        },
        "id": "lyL2PKQBH1bV",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 284
        },
        "outputId": "f2e32d48-bf57-4a06-d5c6-bd9fddc5eded"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Counter({1: 268, 0: 158})\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ],
      "source": [
        "# Check the class distribution of the target\n",
        "counter = Counter(y_train)\n",
        "print(counter)\n",
        "\n",
        "# scatter plot of examples by class label\n",
        "for label, _ in counter.items():\n",
        "    row_ix = where(y_train == label)[0]\n",
        "    pyplot.scatter(X_train_sc[row_ix, 0], X_train_sc[row_ix, 1], label=str(label))\n",
        "pyplot.legend()\n",
        "pyplot.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 56,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:48:44.180793Z",
          "start_time": "2021-10-28T03:48:44.174593Z"
        },
        "id": "YwgU7zrWH1bV"
      },
      "outputs": [],
      "source": [
        "# Create the oversampler and undersampler objects\n",
        "over = SMOTE(sampling_strategy=0.7)\n",
        "under = RandomUnderSampler(sampling_strategy=0.8)\n",
        "\n",
        "# transform the dataset\n",
        "X, y = under.fit_resample(X_train_sc, y_train)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "f2CTXB6TH1bV"
      },
      "source": [
        "After the oversampling and undersampling process, we observe a more balance class distribution in the target variable."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 57,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T03:53:00.623842Z",
          "start_time": "2021-10-28T03:53:00.365844Z"
        },
        "id": "_307n89_H1bV",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 285
        },
        "outputId": "93633ab4-0aa3-42b6-8b57-026984ddbc4d"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Counter({1: 197, 0: 158})\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ],
      "source": [
        "# Check the class distribution of the target\n",
        "counter = Counter(y)\n",
        "print(counter)\n",
        "\n",
        "# scatter plot of examples by class label\n",
        "for label, _ in counter.items():\n",
        "    row_ix = where(y == label)[0]\n",
        "    pyplot.scatter(X_train_sc[row_ix, 0], X_train_sc[row_ix, 1], label=str(label))\n",
        "pyplot.legend()\n",
        "pyplot.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 58,
      "metadata": {
        "ExecuteTime": {
          "end_time": "2021-10-28T04:06:22.089385Z",
          "start_time": "2021-10-28T04:06:21.429799Z"
        },
        "id": "HQmAhO_xH1bV",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "58ea5d97-ecd6-4fc5-9437-78ed4a32ae5d"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[1 0 0 1 1 0 0 0 0 1 1 0 1 1 1 0 1 1 1 0 1 1 0 1 1 1 1 1 1 0 1 1 1 1 1 1 0\n",
            " 1 0 1 1 0 1 1 1 1 1 1 1 1 0 0 0 1 1 1 1 0 0 1 1 0 0 1 1 1 0 0 1 1 0 0 1 0\n",
            " 1 1 1 1 1 1 0 1 1 0 0 0 0 0 1 1 1 1 1 1 1 1 0 0 1 0 0 1 0 0 1 1 1 0 1 1 0\n",
            " 1 1 0 1 0 1 1 1 0 1 1 1 0 1 0 0 1 1 0 0 0 1 1 1 0 0 1 1 0 1 0 1]\n"
          ]
        }
      ],
      "source": [
        "# Create imblearn pipeline for the oversampler and undersampler\n",
        "steps = [('o', over), ('u', under), ('model', DecisionTreeClassifier())]\n",
        "pipeline = imbPipeline(steps=steps)\n",
        "\n",
        "\n",
        "# Create the GridSearchCV object with different hyperparameters\n",
        "parameters = {\n",
        "    'model__max_depth': [2, 4, 6, 8],\n",
        "    'model__min_samples_split': [5, 10, 15],\n",
        "    'model__criterion': ['gini', 'entropy']\n",
        "}\n",
        "\n",
        "cv = GridSearchCV(pipeline, param_grid=parameters)\n",
        "\n",
        "cv.fit(X_train_sc, y_train)\n",
        "\n",
        "# Predict the label with the best model\n",
        "y_pred = cv.predict(X_test_sc)\n",
        "print(y_pred)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 58,
      "metadata": {
        "id": "EnQrhPzMH1bV"
      },
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "hide_input": false,
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.7.2"
    },
    "latex_envs": {
      "LaTeX_envs_menu_present": true,
      "autoclose": false,
      "autocomplete": true,
      "bibliofile": "biblio.bib",
      "cite_by": "apalike",
      "current_citInitial": 1,
      "eqLabelWithNumbers": true,
      "eqNumInitial": 1,
      "hotkeys": {
        "equation": "Ctrl-E",
        "itemize": "Ctrl-I"
      },
      "labels_anchors": false,
      "latex_user_defs": false,
      "report_style_numbering": false,
      "user_envs_cfg": false
    },
    "nbTranslate": {
      "displayLangs": [
        "*"
      ],
      "hotkey": "alt-t",
      "langInMainMenu": true,
      "sourceLang": "en",
      "targetLang": "fr",
      "useGoogleTranslate": true
    },
    "toc": {
      "base_numbering": 1,
      "nav_menu": {},
      "number_sections": true,
      "sideBar": true,
      "skip_h1_title": false,
      "title_cell": "Table of Contents",
      "title_sidebar": "TOC",
      "toc_cell": true,
      "toc_position": {
        "height": "calc(100% - 180px)",
        "left": "10px",
        "top": "150px",
        "width": "232px"
      },
      "toc_section_display": true,
      "toc_window_display": false
    },
    "colab": {
      "provenance": [],
      "name": "hyperparameters_&_pipeline.ipynb",
      "collapsed_sections": [
        "_1Iv8Oz7H1bH",
        "2WlZxi05H1bI",
        "05KiRJKcH1bL",
        "b1g2jSp_H1bM",
        "HNIuFwx3H1bO",
        "M6dGBlb4H1bO",
        "DiUclnHWH1bP",
        "Gizvn0T5H1bP",
        "FyQ0xJyxH1bO"
      ]
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}