le.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import helpers\n",
    "from sklearn import preprocessing\n",
    "X_test, y_test = helpers.get_data(subset=\"test\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Cambodia', 'Canada', 'China', 'Columbia', 'Cuba',\n",
       "       'Dominican-Republic', 'Ecuador', 'El-Salvador', 'England',\n",
       "       'France', 'Germany', 'Greece', 'Guatemala', 'Haiti', 'Honduras',\n",
       "       'Hong', 'Hungary', 'India', 'Iran', 'Ireland', 'Italy', 'Jamaica',\n",
       "       'Japan', 'Laos', 'Mexico', 'Nicaragua',\n",
       "       'Outlying-US(Guam-USVI-etc)', 'Peru', 'Philippines', 'Poland',\n",
       "       'Portugal', 'Puerto-Rico', 'Scotland', 'South', 'Taiwan',\n",
       "       'Thailand', 'Trinadad&Tobago', 'United-States', 'Vietnam',\n",
       "       'Yugoslavia', 'nan'], dtype=object)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "le = preprocessing.LabelEncoder()\n",
    "le.fit(X_test['native-country'].astype(str))\n",
    "countries = le.classes_\n",
    "countries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14, 15, 16,\n",
       "       17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33,\n",
       "       34, 35, 36, 37, 38, 39, 40])"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "le.transform(countries)"
   ]
  }
 ],
 "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": "3.6.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}