{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import logging\n",
    "logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-05-23 18:15:06,938 : INFO : adding document #0 to Dictionary<0 unique tokens: []>\n",
      "2022-05-23 18:15:06,939 : INFO : built Dictionary<12 unique tokens: ['computer', 'human', 'interface', 'response', 'survey']...> from 9 documents (total 29 corpus positions)\n",
      "2022-05-23 18:15:06,939 : INFO : Dictionary lifecycle event {'msg': \"built Dictionary<12 unique tokens: ['computer', 'human', 'interface', 'response', 'survey']...> from 9 documents (total 29 corpus positions)\", 'datetime': '2022-05-23T18:15:06.939467', 'gensim': '4.2.0', 'python': '3.10.2 (tags/v3.10.2:a58ebcc, Jan 17 2022, 14:12:15) [MSC v.1929 64 bit (AMD64)]', 'platform': 'Windows-10-10.0.22000-SP0', 'event': 'created'}\n"
     ]
    }
   ],
   "source": [
    "from collections import defaultdict\n",
    "from gensim import corpora\n",
    "\n",
    "documents = [\n",
    "    \"Human machine interface for lab abc computer applications\",\n",
    "    \"A survey of user opinion of computer system response time\",\n",
    "    \"The EPS user interface management system\",\n",
    "    \"System and human system engineering testing of EPS\",\n",
    "    \"Relation of user perceived response time to error measurement\",\n",
    "    \"The generation of random binary unordered trees\",\n",
    "    \"The intersection graph of paths in trees\",\n",
    "    \"Graph minors IV Widths of trees and well quasi ordering\",\n",
    "    \"Graph minors A survey\",\n",
    "]\n",
    "\n",
    "# remove common words and tokenize\n",
    "stoplist = set('for a of the and to in'.split())\n",
    "texts = [\n",
    "    [word for word in document.lower().split() if word not in stoplist]\n",
    "    for document in documents\n",
    "]\n",
    "\n",
    "# remove words that appear only once\n",
    "frequency = defaultdict(int)\n",
    "for text in texts:\n",
    "    for token in text:\n",
    "        frequency[token] += 1\n",
    "\n",
    "texts = [\n",
    "    [token for token in text if frequency[token] > 1]\n",
    "    for text in texts\n",
    "]\n",
    "\n",
    "dictionary = corpora.Dictionary(texts)\n",
    "corpus = [dictionary.doc2bow(text) for text in texts]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-05-23 18:16:10,608 : INFO : collecting document frequencies\n",
      "2022-05-23 18:16:10,609 : INFO : PROGRESS: processing document #0\n",
      "2022-05-23 18:16:10,609 : INFO : TfidfModel lifecycle event {'msg': 'calculated IDF weights for 9 documents and 12 features (28 matrix non-zeros)', 'datetime': '2022-05-23T18:16:10.609938', 'gensim': '4.2.0', 'python': '3.10.2 (tags/v3.10.2:a58ebcc, Jan 17 2022, 14:12:15) [MSC v.1929 64 bit (AMD64)]', 'platform': 'Windows-10-10.0.22000-SP0', 'event': 'initialize'}\n"
     ]
    }
   ],
   "source": [
    "from gensim import models\n",
    "\n",
    "tfidf = models.TfidfModel(corpus) # 1. initialize the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[(0, 0.7071067811865476), (1, 0.7071067811865476)]\n"
     ]
    }
   ],
   "source": [
    "doc_bow = [(0,1), (1,1)]\n",
    "print(tfidf[doc_bow]) # 2. use the model to transform vectors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[(0, 0.5773502691896257), (1, 0.5773502691896257), (2, 0.5773502691896257)]\n",
      "[(0, 0.44424552527467476), (3, 0.44424552527467476), (4, 0.44424552527467476), (5, 0.3244870206138555), (6, 0.44424552527467476), (7, 0.3244870206138555)]\n",
      "[(2, 0.5710059809418182), (5, 0.4170757362022777), (7, 0.4170757362022777), (8, 0.5710059809418182)]\n",
      "[(1, 0.49182558987264147), (5, 0.7184811607083769), (8, 0.49182558987264147)]\n",
      "[(3, 0.6282580468670046), (6, 0.6282580468670046), (7, 0.45889394536615247)]\n",
      "[(9, 1.0)]\n",
      "[(9, 0.7071067811865475), (10, 0.7071067811865475)]\n",
      "[(9, 0.5080429008916749), (10, 0.5080429008916749), (11, 0.695546419520037)]\n",
      "[(4, 0.6282580468670046), (10, 0.45889394536615247), (11, 0.6282580468670046)]\n"
     ]
    }
   ],
   "source": [
    "corpus_tfidf = tfidf[corpus]\n",
    "for doc in corpus_tfidf:\n",
    "    print(doc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2022-05-23 18:40:30,354 : INFO : using serial LSI version on this node\n",
      "2022-05-23 18:40:30,354 : INFO : updating model with new documents\n",
      "2022-05-23 18:40:30,355 : INFO : preparing a new chunk of documents\n",
      "2022-05-23 18:40:30,358 : INFO : using 100 extra samples and 2 power iterations\n",
      "2022-05-23 18:40:30,359 : INFO : 1st phase: constructing (12, 102) action matrix\n",
      "2022-05-23 18:40:30,360 : INFO : orthonormalizing (12, 102) action matrix\n",
      "2022-05-23 18:40:30,362 : INFO : 2nd phase: running dense svd on (12, 9) matrix\n",
      "2022-05-23 18:40:30,363 : INFO : computing the final decomposition\n",
      "2022-05-23 18:40:30,364 : INFO : keeping 2 factors (discarding 47.565% of energy spectrum)\n",
      "2022-05-23 18:40:30,365 : INFO : processed documents up to #9\n",
      "2022-05-23 18:40:30,365 : INFO : topic #0(1.594): 0.703*\"trees\" + 0.538*\"graph\" + 0.402*\"minors\" + 0.187*\"survey\" + 0.061*\"system\" + 0.060*\"time\" + 0.060*\"response\" + 0.058*\"user\" + 0.049*\"computer\" + 0.035*\"interface\"\n",
      "2022-05-23 18:40:30,365 : INFO : topic #1(1.476): 0.460*\"system\" + 0.373*\"user\" + 0.332*\"eps\" + 0.328*\"interface\" + 0.320*\"response\" + 0.320*\"time\" + 0.293*\"computer\" + 0.280*\"human\" + 0.171*\"survey\" + -0.161*\"trees\"\n",
      "2022-05-23 18:40:30,365 : INFO : LsiModel lifecycle event {'msg': 'trained LsiModel<num_terms=12, num_topics=2, decay=1.0, chunksize=20000> in 0.01s', 'datetime': '2022-05-23T18:40:30.365269', 'gensim': '4.2.0', 'python': '3.10.2 (tags/v3.10.2:a58ebcc, Jan 17 2022, 14:12:15) [MSC v.1929 64 bit (AMD64)]', 'platform': 'Windows-10-10.0.22000-SP0', 'event': 'created'}\n"
     ]
    }
   ],
   "source": [
    "lsi_model = models.LsiModel(corpus_tfidf, id2word=dictionary, num_topics=2) # initialize an LSI transf\n",
    "corpus_lsi = lsi_model[corpus_tfidf] # create a double wrapper over the original"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "''"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lsi_model.print_topic(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "a991b7e5a58af45663279ce1606e861d35361e78ec04a120e3cc987f7e474d97"
  },
  "kernelspec": {
   "display_name": "Python 3.10.2 ('venv': venv)",
   "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": "3.10.2"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}