medium/NameClassifier/dataload

NameClassifier_data_load.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>code</th>\n",
       "      <th>name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>24944</th>\n",
       "      <td>Spanish (Spain)</td>\n",
       "      <td>Luís Escobar Abascal</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>83738</th>\n",
       "      <td>Japanese</td>\n",
       "      <td>中島 英樹</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87719</th>\n",
       "      <td>Japanese</td>\n",
       "      <td>吉本 知実</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2567</th>\n",
       "      <td>Arabic (Egypt)</td>\n",
       "      <td>Maria Green</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23727</th>\n",
       "      <td>Spanish (Spain)</td>\n",
       "      <td>Emilia Valbuena Fuente</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24189</th>\n",
       "      <td>Spanish (Spain)</td>\n",
       "      <td>Carlos Estrada Teruel</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>83525</th>\n",
       "      <td>Japanese</td>\n",
       "      <td>田中 晃</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>74719</th>\n",
       "      <td>Russian</td>\n",
       "      <td>Сорокина Евпраксия Афанасьевна</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7575</th>\n",
       "      <td>Arabic (Egypt)</td>\n",
       "      <td>Darren Gonzalez</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69719</th>\n",
       "      <td>Portuguese (Brazil)</td>\n",
       "      <td>Isaac Almeida</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      code                            name\n",
       "24944      Spanish (Spain)            Luís Escobar Abascal\n",
       "83738             Japanese                           中島 英樹\n",
       "87719             Japanese                           吉本 知実\n",
       "2567        Arabic (Egypt)                     Maria Green\n",
       "23727      Spanish (Spain)          Emilia Valbuena Fuente\n",
       "24189      Spanish (Spain)           Carlos Estrada Teruel\n",
       "83525             Japanese                            田中 晃\n",
       "74719              Russian  Сорокина Евпраксия Афанасьевна\n",
       "7575        Arabic (Egypt)                 Darren Gonzalez\n",
       "69719  Portuguese (Brazil)                   Isaac Almeida"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd \n",
    "import os \n",
    "import numpy as np\n",
    "from sklearn.feature_extraction.text import CountVectorizer\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# setting up path to the data file\n",
    "PATH = os.path.abspath('')\n",
    "PATH = os.path.join(PATH, 'data')\n",
    "names = 'multi_class_names.csv'\n",
    "\n",
    "# read in the data as panda dataframe\n",
    "df = pd.read_csv(os.path.join(PATH, names))\n",
    "df.sample(10)"
   ]
  }
 ],
 "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": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}