Merge pull request joanby#3 from johnnync13/master

All repository to colab
gergutisan · Sep 10, 2020 · 0d7be2a · 0d7be2a
2 parents 60bf05f + ce8b4f7
commit 0d7be2a
Show file tree

Hide file tree

Showing 34 changed files with 13,166 additions and 0 deletions.
diff --git a/...----------------- Part 1 - Data Preprocessing --------------------/categorical_data.ipynb b/...----------------- Part 1 - Data Preprocessing --------------------/categorical_data.ipynb
@@ -0,0 +1,329 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "KdUFcDsdzRyw"
+   },
+   "source": [
+    "# Clonamos el repositorio para obtener los dataSet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 54
+    },
+    "colab_type": "code",
+    "id": "mHReFf3_y9ms",
+    "outputId": "c17545fd-c7dd-42c2-e3ad-4f55db21611f"
+   },
+   "outputs": [],
+   "source": [
+    "!git clone https://github.com/joanby/machinelearning-az.git"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "vNKZXgtKzU2x"
+   },
+   "source": [
+    "# Damos acceso a nuestro Drive"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 54
+    },
+    "colab_type": "code",
+    "id": "5gu7KWnzzUQ0",
+    "outputId": "abe602b4-3a59-470e-d508-037c6966002b"
+   },
+   "outputs": [],
+   "source": [
+    "from google.colab import drive\n",
+    "drive.mount('/content/drive')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "1gUxIkHWzfHV"
+   },
+   "source": [
+    "# Test it"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 119
+    },
+    "colab_type": "code",
+    "id": "mIQt3jBMzYRE",
+    "outputId": "d050bd10-4da5-4ff3-db48-cead7fdee3d1"
+   },
+   "outputs": [],
+   "source": [
+    "!ls '/content/drive/My Drive' "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "mHsK36uN0XB-"
+   },
+   "source": [
+    "# Google colab tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "kTzwfUPWzrm4"
+   },
+   "outputs": [],
+   "source": [
+    "from google.colab import files # Para manejar los archivos y, por ejemplo, exportar a su navegador\n",
+    "import glob # Para manejar los archivos y, por ejemplo, exportar a su navegador\n",
+    "from google.colab import drive # Montar tu Google drive"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "3yFpBwmNz70v"
+   },
+   "source": [
+    "# Plantilla de Pre Procesado - Datos Categóricos\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "v8OxSXXSz-OP"
+   },
+   "source": [
+    "# Cómo importar las librerías\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "edZX51YLzs59"
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "8XfXlqtF0B58"
+   },
+   "source": [
+    "# Importar el data set\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "-nnozsHsz_-N"
+   },
+   "outputs": [],
+   "source": [
+    "dataset = pd.read_csv('/content/machinelearning-az/datasets/Part 1 - Data Preprocessing/Section 2 -------------------- Part 1 - Data Preprocessing --------------------/Data.csv')\n",
+    "X = dataset.iloc[:, :-1].values\n",
+    "y = dataset.iloc[:, 3].values\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "x8PABYut0i7y"
+   },
+   "source": [
+    "# Codificar datos categóricos"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "oPVZUP870DoR"
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.preprocessing import LabelEncoder, OneHotEncoder\n",
+    "from sklearn.compose import ColumnTransformer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "3lajo7ye0lEs"
+   },
+   "outputs": [],
+   "source": [
+    "labelencoder_X = LabelEncoder()\n",
+    "X[:, 0] = labelencoder_X.fit_transform(X[:, 0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "BQ-MnRSO0md2"
+   },
+   "outputs": [],
+   "source": [
+    "ct = ColumnTransformer(\n",
+    "    [('one_hot_encoder', OneHotEncoder(categories='auto'), [0])],    # The column numbers to be transformed (here is [0] but can be [0, 1, 3])\n",
+    "    remainder='passthrough'                         # Leave the rest of the columns untouched\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "colab_type": "text",
+    "id": "HSvLo8r30psf"
+   },
+   "source": [
+    "#onehotencoder = OneHotEncoder(categorical_features=[0])\n",
+    "#X = onehotencoder.fit_transform(X).toarray()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "kt9uD3hE0nxd"
+   },
+   "outputs": [],
+   "source": [
+    "X = np.array(ct.fit_transform(X), dtype=np.float)\n",
+    "labelencoder_y = LabelEncoder()\n",
+    "y = labelencoder_y.fit_transform(y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 34
+    },
+    "colab_type": "code",
+    "id": "S-Eb4Y9M0uS1",
+    "outputId": "5925ae23-11d9-4bd4-ad11-c6ca7f704a0c"
+   },
+   "outputs": [],
+   "source": [
+    "print(X.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 34
+    },
+    "colab_type": "code",
+    "id": "vwx3Dzmz0wRg",
+    "outputId": "79b2f6dd-cf00-4adc-c382-5c9a3659648d"
+   },
+   "outputs": [],
+   "source": [
+    "print(y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 359
+    },
+    "colab_type": "code",
+    "id": "lILzSQnW0x8V",
+    "outputId": "140411a2-33f7-4dda-cab4-6ca94dd0fbf6"
+   },
+   "outputs": [],
+   "source": [
+    "result = pd.DataFrame({'Column1': X[:, 0], 'Column2': X[:, 1],'Column3': X[:, 2], 'Age': X[:, 3],'Salary': X[:, 4],'Purchased': y[:]})\n",
+    "display(result)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "name": "categorical_data.ipynb",
+   "provenance": [],
+   "toc_visible": true
+  },
+  "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": "3.8.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}