diff code/Gensim LDA tutorial.ipynb @ 1:995546d09284

add gensim notebook and matlab scripts

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/code/Gensim LDA tutorial.ipynb	Tue Jan 24 17:44:45 2017 +0000
@@ -0,0 +1,111 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1.10.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "import six\n",
+    "print six.__version__\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "import gensim\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "import gensim\n",
+    "import bz2\n",
+    "logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "ename": "IOError",
+     "evalue": "[Errno 2] No such file or directory: 'wiki_en_wordids.txt'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mIOError\u001b[0m                                   Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-4-54645b7b2c38>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m# load id->word mapping (the dictionary), one of the results of step 2 above\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mid2word\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgensim\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpora\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDictionary\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload_from_text\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'wiki_en_wordids.txt'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0;31m# load corpus iterator\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mmm\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgensim\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcorpora\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mMmCorpus\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'wiki_en_tfidf.mm'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;31m# mm = gensim.corpora.MmCorpus(bz2.BZ2File('wiki_en_tfidf.mm.bz2')) # use this if you compressed the TFIDF output\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Library/Python/2.7/site-packages/gensim/corpora/dictionary.pyc\u001b[0m in \u001b[0;36mload_from_text\u001b[0;34m(fname)\u001b[0m\n\u001b[1;32m    342\u001b[0m         \"\"\"\n\u001b[1;32m    343\u001b[0m         \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mDictionary\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 344\u001b[0;31m         \u001b[0;32mwith\u001b[0m \u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msmart_open\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfname\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    345\u001b[0m             \u001b[0;32mfor\u001b[0m \u001b[0mlineno\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mline\u001b[0m \u001b[0;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    346\u001b[0m                 \u001b[0mline\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mutils\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_unicode\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mline\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Library/Python/2.7/site-packages/smart_open/smart_open_lib.pyc\u001b[0m in \u001b[0;36msmart_open\u001b[0;34m(uri, mode, **kw)\u001b[0m\n\u001b[1;32m    125\u001b[0m             \u001b[0;31m# local files -- both read & write supported\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    126\u001b[0m             \u001b[0;31m# compression, if any, is determined by the filename extension (.gz, .bz2)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 127\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mfile_smart_open\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mparsed_uri\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muri_path\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    128\u001b[0m         \u001b[0;32melif\u001b[0m \u001b[0mparsed_uri\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscheme\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;34m\"s3\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"s3n\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    129\u001b[0m             \u001b[0;31m# Get an S3 host. It is required for sigv4 operations.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/Library/Python/2.7/site-packages/smart_open/smart_open_lib.pyc\u001b[0m in \u001b[0;36mfile_smart_open\u001b[0;34m(fname, mode)\u001b[0m\n\u001b[1;32m    556\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mmake_closing\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mGzipFile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    557\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 558\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmode\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    559\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    560\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mIOError\u001b[0m: [Errno 2] No such file or directory: 'wiki_en_wordids.txt'"
+     ]
+    }
+   ],
+   "source": [
+    "# load id->word mapping (the dictionary), one of the results of step 2 above\n",
+    "id2word = gensim.corpora.Dictionary.load_from_text('wiki_en_wordids.txt')\n",
+    "# load corpus iterator\n",
+    "mm = gensim.corpora.MmCorpus('wiki_en_tfidf.mm')\n",
+    "# mm = gensim.corpora.MmCorpus(bz2.BZ2File('wiki_en_tfidf.mm.bz2')) # use this if you compressed the TFIDF output\n",
+    "\n",
+    "print(mm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "2.7.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}