hashing_vectorizer_benchmark.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4827372, 22)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = join_df('tweets/')\n",
    "tweets = Series(df['text'])\n",
    "df.shape "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 2.84 s, sys: 736 ms, total: 3.58 s\n",
      "Wall time: 3.81 s\n"
     ]
    }
   ],
   "source": [
    "vec = cumlHashingVectorizer(stop_words='english')\n",
    "%time X = vec.fit_transform(tweets)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 1min 17s, sys: 902 ms, total: 1min 18s\n",
      "Wall time: 1min 18s\n"
     ]
    }
   ],
   "source": [
    "tweets_pd = tweets.to_pandas()\n",
    "vec = skHashingVectorizer(stop_words='english')\n",
    "%time X = vec.fit_transform(tweets_pd)"
   ]
  }
 ],
 "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}