add sklearn linear regression

SoroushGhaderi · Sep 7, 2020 · b7d5f48 · b7d5f48
1 parent 44fe535
commit b7d5f48
Showing 1 changed file with 115 additions and 28 deletions.
diff --git a/Concrete_Data_Analysis.ipynb b/Concrete_Data_Analysis.ipynb
@@ -2,9 +2,18 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\ProgramData\\Anaconda3\\lib\\importlib\\_bootstrap.py:219: RuntimeWarning: numpy.ufunc size changed, may indicate binary incompatibility. Expected 192 from C header, got 216 from PyObject\n",
+      "  return f(*args, **kwds)\n"
+     ]
+    }
+   ],
    "source": [
     "import numpy as np\n",
     "import pandas as pd \n",
@@ -13,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -24,7 +33,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -133,7 +142,7 @@
        "4   198.6  132.4  0.0  192.0     0.0   978.4  825.5  360     44.30"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -144,7 +153,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -176,7 +185,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -185,7 +194,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -199,7 +208,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -233,7 +242,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -242,7 +251,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -252,7 +261,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -291,7 +300,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -346,7 +355,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -359,7 +368,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -386,7 +395,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -420,7 +429,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -438,7 +447,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -473,7 +482,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -491,7 +500,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -523,7 +532,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -534,7 +543,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -548,7 +557,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -558,7 +567,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -587,7 +596,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -596,7 +605,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -605,7 +614,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [
     {
@@ -623,7 +632,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [
     {
@@ -639,6 +648,84 @@
     "print(\"Adjusted R Squared for Linear Regression is: {}\".format(adjusted_r_squared_predicted_with_normal_equation))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Implementation with SKlearn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.metrics import r2_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "concrete = pd.read_csv(\"data/Concrete_Data.csv\")\n",
+    "# Rename the columns\n",
+    "concrete.columns = [\"cement\", \"slag\", \"ash\", \"water\", \"splast\", \"coarse\", \"fine\", \"age\", \"strength\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Initializing X and Y according to shape and converting to numpy arrays\n",
+    "X = concrete.iloc[:,0:number_of_features-1].values\n",
+    "y = concrete.iloc[:,number_of_features-1:number_of_features].values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "linear_regreesion= LinearRegression()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "linear_regreesion.fit(X,y)\n",
+    "model_accuracy= linear_regreesion.predict(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.6155198704142721"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "r2_score(y, model_accuracy)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,