simple linear regression without sklearn.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "class LR:\n",
    "\n",
    "    def __init__(self):\n",
    "        self.m = None\n",
    "        self.b = None\n",
    "\n",
    "    def fit(self,X_train,y_train):\n",
    "        num = 0\n",
    "        den = 0\n",
    "        for i in range(X_train.shape[0]):\n",
    "            num = num + ((X_train[i] - X_train.mean())*(y_train[i] - y_train.mean()))\n",
    "            den = den + ((X_train[i] - X_train.mean())*(X_train[i] - X_train.mean()))\n",
    "        self.m = num/den\n",
    "        self.b = y_train.mean() - (self.m * X_train.mean())\n",
    "        print(self.m)\n",
    "        print(self.b)\n",
    "\n",
    "    def predict(self,X_test):\n",
    "        print(X_test)\n",
    "        return self.m * X_test + self.b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "outputs": [],
   "source": [
    "df=pd.read_csv('placement.csv')"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "outputs": [
    {
     "data": {
      "text/plain": "   cgpa  package\n0  6.89     3.26\n1  5.12     1.98\n2  7.82     3.25\n3  7.42     3.67\n4  6.94     3.57",
      "text/html": "<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>cgpa</th>\n      <th>package</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>6.89</td>\n      <td>3.26</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>5.12</td>\n      <td>1.98</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>7.82</td>\n      <td>3.25</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>7.42</td>\n      <td>3.67</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>6.94</td>\n      <td>3.57</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "outputs": [],
   "source": [
    "X = df.iloc[:,0].values\n",
    "y = df.iloc[:,1].values"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from sklearn.model_selection import train_test_split"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "outputs": [],
   "source": [
    "X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=2)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "outputs": [],
   "source": [
    "lr=LR()"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5579519734250721\n",
      "-0.8961119222429152\n"
     ]
    }
   ],
   "source": [
    "lr.fit(X_train,y_train)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "8.58\n",
      "3.891116009744203\n"
     ]
    }
   ],
   "source": [
    "print(lr.predict(X_test[0]))"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [],
   "metadata": {
    "collapsed": false
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}