{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=pd.read_excel(\"https://github.com/masterfloss/data/blob/main/socialmedia.xlsx?raw=true\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import statsmodels.api as sm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X=df[['Linux','Chrome','Twitter']]\n",
    "y=df[['Facebook']]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = sm.add_constant(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "result = sm.OLS(y,X).fit()\n",
    "result.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.plot.scatter('Linux','Facebook')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.plot.scatter('Chrome','Facebook')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X=df[['Linux']]\n",
    "y=df[['Facebook']]\n",
    "result = sm.OLS(y,X).fit()\n",
    "result.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X=df[['Linux','Chrome','Twitter']]\n",
    "y=df[['Facebook']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from statsmodels.stats.outliers_influence import variance_inflation_factor\n",
    "# VIF dataframe \n",
    "vif_data = pd.DataFrame() \n",
    "vif_data[\"feature\"] = X.columns \n",
    "\n",
    "# calculating VIF for each feature \n",
    "vif_data[\"VIF\"] = [variance_inflation_factor(X.values, i) for i in range(len(X.columns))] \n",
    "  \n",
    "print(vif_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "len(X.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "XX=df[['Twitter']]**(1/2)\n",
    "XX['Linux']=df[['Linux']]**(1/2)\n",
    "XX['Chrome']=df[['Chrome']]**(1/2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from statsmodels.stats.outliers_influence import variance_inflation_factor\n",
    "# VIF dataframe \n",
    "vif_data = pd.DataFrame() \n",
    "vif_data[\"feature\"] = XX.columns \n",
    "\n",
    "# calculating VIF for each feature \n",
    "vif_data[\"VIF\"] = [variance_inflation_factor(XX.values, i) for i in range(len(XX.columns))] \n",
    "  \n",
    "print(vif_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "XX = sm.add_constant(XX)\n",
    "result = sm.OLS(y,XX).fit()\n",
    "result.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}