{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from biased_stop_words import get_stop_words\n",
    "from sklearn.feature_extraction.text import CountVectorizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "biased_stop_words = get_stop_words('gendered')\n",
    "corpus = [\n",
    "    'He is an astronaut, he is on Venus',\n",
    "    'He is an accountant, he is on Earth',\n",
    "    'She is an astronaut, she is on Mars'\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['accountant', 'an', 'astronaut', 'earth', 'is', 'mars', 'on', 'venus']\n",
      "[[0 1 1 0 2 0 1 1]\n",
      " [1 1 0 1 2 0 1 0]\n",
      " [0 1 1 0 2 1 1 0]]\n"
     ]
    }
   ],
   "source": [
    "vectorizer = CountVectorizer(stop_words=biased_stop_words)\n",
    "X = vectorizer.fit_transform(corpus)\n",
    "print(vectorizer.get_feature_names())\n",
    "\n",
    "print(X.toarray()) "
   ]
  }
 ],
 "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
}