Gini index

Gini.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "data = pd.DataFrame({'Working': [7979, 260], 'On pension': [1334, 39], 'Unknown': [3806, 30]}).T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>On pension</th>\n",
       "      <td>1334</td>\n",
       "      <td>39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Unknown</th>\n",
       "      <td>3806</td>\n",
       "      <td>30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Working</th>\n",
       "      <td>7979</td>\n",
       "      <td>260</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               0    1\n",
       "On pension  1334   39\n",
       "Unknown     3806   30\n",
       "Working     7979  260"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Suppose we have a variable about people occupation and frequencies for some target.\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#Calculate target rate and sort.\n",
    "data['s'] = data[1] / np.sum(data.values, axis=1)\n",
    "data = data.sort_values('s', axis=0, ascending=False)\n",
    "#Renaming columns for easier reference.\n",
    "data.columns = ['n', 'y', 's']\n",
    "#Calculate cummulative percent.\n",
    "data['cum_perc_n'] = data.n.cumsum()/data.n.sum()\n",
    "data['cum_perc_y'] = data.y.cumsum()/data.y.sum()\n",
    "#Rolling mean for X is calculated. First value should be simply half of itself, it is calculated separately, as this is easier.\n",
    "data['x'] = data.cum_perc_y.rolling(2, min_periods=1).mean()\n",
    "data.iloc[0, 5] = data.iloc[0, 5] / 2\n",
    "#Y is calculated as difference between the value in the current and the previous row.\n",
    "data['Y'] = data.cum_perc_n - data.cum_perc_n.shift(1).fillna(0)\n",
    "#Simple element-wise multiplication.\n",
    "data['g'] = data.x * data.Y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>n</th>\n",
       "      <th>y</th>\n",
       "      <th>s</th>\n",
       "      <th>cum_perc_n</th>\n",
       "      <th>cum_perc_y</th>\n",
       "      <th>x</th>\n",
       "      <th>Y</th>\n",
       "      <th>g</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Working</th>\n",
       "      <td>7979</td>\n",
       "      <td>260</td>\n",
       "      <td>0.031557</td>\n",
       "      <td>0.608202</td>\n",
       "      <td>0.790274</td>\n",
       "      <td>0.395137</td>\n",
       "      <td>0.608202</td>\n",
       "      <td>0.240323</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>On pension</th>\n",
       "      <td>1334</td>\n",
       "      <td>39</td>\n",
       "      <td>0.028405</td>\n",
       "      <td>0.709886</td>\n",
       "      <td>0.908815</td>\n",
       "      <td>0.849544</td>\n",
       "      <td>0.101685</td>\n",
       "      <td>0.086386</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Unknown</th>\n",
       "      <td>3806</td>\n",
       "      <td>30</td>\n",
       "      <td>0.007821</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.954407</td>\n",
       "      <td>0.290114</td>\n",
       "      <td>0.276887</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               n    y         s  cum_perc_n  cum_perc_y         x         Y  \\\n",
       "Working     7979  260  0.031557    0.608202    0.790274  0.395137  0.608202   \n",
       "On pension  1334   39  0.028405    0.709886    0.908815  0.849544  0.101685   \n",
       "Unknown     3806   30  0.007821    1.000000    1.000000  0.954407  0.290114   \n",
       "\n",
       "                   g  \n",
       "Working     0.240323  \n",
       "On pension  0.086386  \n",
       "Unknown     0.276887  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "20.718992454156492\n"
     ]
    }
   ],
   "source": [
    "#This is Gini. Sum g, multiply by 2 and subtract 1.\n",
    "print((np.sum(data['g']) * 2 - 1) * 100)"
   ]
  }
 ],
 "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": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}