Tweet Analysis-Copy5 (1).ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 351,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(3100, 468)\n"
     ]
    }
   ],
   "source": [
    "#Implementing LDA \n",
    "\n",
    "from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer\n",
    "from sklearn.decomposition import LatentDirichletAllocation\n",
    "stop_words.update([\"shri\",\"also\", \"towards\"])\n",
    "\n",
    "tf_vectorizer = CountVectorizer(strip_accents = 'unicode',\n",
    "                                stop_words = 'english',\n",
    "                                lowercase = True,\n",
    "                                token_pattern = r'\\b[a-zA-Z]{3,}\\b',\n",
    "                                max_df = 0.5, \n",
    "                                min_df = 10)\n",
    "dtm_tf = tf_vectorizer.fit_transform(data['Tweets_Cln'])\n",
    "print(dtm_tf.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 352,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(3100, 468)\n"
     ]
    }
   ],
   "source": [
    "tfidf_vectorizer = TfidfVectorizer(**tf_vectorizer.get_params())\n",
    "dtm_tfidf = tfidf_vectorizer.fit_transform(data['Tweets_Cln'])\n",
    "print(dtm_tfidf.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 353,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LatentDirichletAllocation(batch_size=128, doc_topic_prior=None,\n",
       "             evaluate_every=-1, learning_decay=0.7, learning_method=None,\n",
       "             learning_offset=10.0, max_doc_update_iter=100, max_iter=10,\n",
       "             mean_change_tol=0.001, n_components=10, n_jobs=1, n_topics=5,\n",
       "             perp_tol=0.1, random_state=0, topic_word_prior=None,\n",
       "             total_samples=1000000.0, verbose=0)"
      ]
     },
     "execution_count": 353,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# for TF DTM\n",
    "lda_tf = LatentDirichletAllocation(n_topics=5, random_state=0)\n",
    "lda_tf.fit(dtm_tf)\n",
    "# for TFIDF DTM\n",
    "lda_tfidf = LatentDirichletAllocation(n_topics=5, random_state=0)\n",
    "lda_tfidf.fit(dtm_tfidf)"
   ]
  }
 ],
 "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
}