How to deal with outliers in Python

38.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "**How we can deal with outliers in Python** \n",
      "\n",
      "     Price  Rooms  Square_Feet\n",
      "0   632541      2         1600\n",
      "1   425618      5         2850\n",
      "2   356471      3         1780\n",
      "3  7412512    100        90000\n",
      "\n",
      "    Price  Rooms  Square_Feet\n",
      "0  632541      2         1600\n",
      "1  425618      5         2850\n",
      "2  356471      3         1780\n",
      "\n",
      "     Price  Rooms  Square_Feet  Outlier\n",
      "0   632541      2         1600        0\n",
      "1   425618      5         2850        0\n",
      "2   356471      3         1780        0\n",
      "3  7412512    100        90000        1\n",
      "\n",
      "     Price  Rooms  Square_Feet  Outlier  Log_Of_Square_Feet\n",
      "0   632541      2         1600        0            7.377759\n",
      "1   425618      5         2850        0            7.955074\n",
      "2   356471      3         1780        0            7.484369\n",
      "3  7412512    100        90000        1           11.407565\n"
     ]
    }
   ],
   "source": [
    "## How we can deal with outliers in Python \n",
    "def ProjectPro_Ex_38():\n",
    "    \n",
    "    print('**How we can deal with outliers in Python** ')\n",
    "\n",
    "    # Loading library\n",
    "    import numpy as np\n",
    "    import pandas as pd\n",
    "\n",
    "    # Creating DataFrame\n",
    "    farm = pd.DataFrame()\n",
    "    farm['Price'] = [632541, 425618, 356471, 7412512]\n",
    "    farm['Rooms'] = [2, 5, 3, 100]\n",
    "    farm['Square_Feet'] = [1600, 2850, 1780, 90000]\n",
    "    print(); print(farm)\n",
    "\n",
    "    # Outlier Handling Option 1: Drop\n",
    "    # Droping observations greater than some value\n",
    "    h = farm[farm['Rooms'] < 20]\n",
    "    print(); print(h)\n",
    "\n",
    "    # Outlier Handling Option 2: Mark\n",
    "    # Creating feature based on boolean condition\n",
    "    farm['Outlier'] = np.where(farm['Rooms'] < 20, 0, 1)\n",
    "\n",
    "    # Show data\n",
    "    print(); print(farm)\n",
    "\n",
    "    # Outlier Handling Option 3: Rescale\n",
    "    # Log feature\n",
    "    farm['Log_Of_Square_Feet'] = [np.log(x) for x in farm['Square_Feet']]\n",
    "\n",
    "    # Show data\n",
    "    print(); print(farm)\n",
    "\n",
    "ProjectPro_Ex_38()"
   ]
  }
 ],
 "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}