Testing coherence for LdaVowpalWabbit wrapper

coherence_testing.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from gensim.models.coherencemodel import CoherenceModel\n",
    "from gensim.models.ldamodel import LdaModel\n",
    "from gensim.corpora.dictionary import Dictionary\n",
    "from gensim.models.wrappers import LdaVowpalWabbit\n",
    "import numpy as np\n",
    "from pprint import pprint\n",
    "import test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "documents = [\"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\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "stoplist = set('for a of the and to in'.split())\n",
    "texts = [[word for word in document.lower().split() if word not in stoplist] for document in documents]\n",
    "dictionary = Dictionary(texts)\n",
    "corpus = [dictionary.doc2bow(text) for text in texts]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "np.random.seed(1)\n",
    "topics = []\n",
    "tm = LdaModel(corpus=corpus, id2word=dictionary, num_topics=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "model1 = LdaVowpalWabbit('/home/devashish/vw-8',corpus=corpus , num_topics=2, id2word=dictionary, passes=1)\n",
    "model2 = LdaVowpalWabbit('/home/devashish/vw-8',corpus=corpus , num_topics=2, id2word=dictionary, passes=50)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "cm1 = CoherenceModel(model=model1, corpus=corpus, coherence='u_mass')\n",
    "cm2 = CoherenceModel(model=model2, corpus=corpus, coherence='u_mass')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-20.5979947296\n",
      "-15.30250407\n"
     ]
    }
   ],
   "source": [
    "print cm1.get_coherence()\n",
    "print cm2.get_coherence()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}