Compare Stemmers.ipynb

{
 "worksheets": [
  {
   "cells": [
    {
     "metadata": {},
     "cell_type": "markdown",
     "source": "## Let's compare stemmers!\nFirst load in the libraries and set up the stemmers."
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "import nltk\nfrom nltk.corpus import stopwords\nenglish_stopwords = stopwords.words('english')\n\nfrom nltk.corpus import gutenberg\nimport re\npstemmer = nltk.PorterStemmer()\nlstemmer = nltk.LancasterStemmer()\nwnlemmatizer = nltk.WordNetLemmatizer()\n",
     "prompt_number": 1,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "markdown",
     "source": "We'll also need a bit of tokenization and normalization here.  Add some code here to remove punctuation and stopwords."
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "def tokenize_text(text):    \n    pattern = r'''(?x)\n    ([A-Z]\\.)+\n    |\\w+([-']\\w+)*\n    |\\$?\\d+(\\.\\d+)?%?\n    |\\.\\.\\.\n    |[.,?;]+\n    '''\n    tokens = nltk.regexp_tokenize(text,pattern)\n    # add code to remove punctuation and stopwords\n    return tokens",
     "prompt_number": 2,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "markdown",
     "source": "Let's tokenize good ol' Walt; make sure it worked."
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "tokens = tokenize_text(gutenberg.raw('whitman-leaves.txt'))\nprint len(tokens)\ntokens[0:10]",
     "prompt_number": 3,
     "outputs": [
      {
       "output_type": "stream",
       "text": "143541\n",
       "stream": "stdout"
      },
      {
       "text": "['Leaves', 'of', 'Grass', 'by', 'Walt', 'Whitman', '1855', 'Come', ',', 'said']",
       "output_type": "pyout",
       "metadata": {},
       "prompt_number": 3
      }
     ],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "markdown",
     "source": "Here is one example of running the stemmer; you can fill in the other two below."
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "pstemmed_tokens = [pstemmer.stem(word.lower()) for word in tokens]\n",
     "prompt_number": 4,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "lstemmer_tokens = [lstemmer.stem(word.lower()) for word in tokens]",
     "prompt_number": 5,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "wnlemmatizer_tokens = [wnlemmatizer.lemmatize(word.lower()) for word in tokens]",
     "prompt_number": 6,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "markdown",
     "source": "Now we want to make 3 FreqDists to count up how common each word is now that we've done the stemming."
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "pstem = nltk.FreqDist(pstemmed_tokens)\nlstem = nltk.FreqDist(lstemmer_tokens)\nwnlstem = nltk.FreqDist(wnlemmatizer_tokens)",
     "prompt_number": 7,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "markdown",
     "source": "Now we want to compare the three outputs.  What is a good function that quickly lets you do side-by-side comparisons of vertical lists?"
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "comp = zip(pstem.items(), lstem.items(), wnlstem.items())",
     "prompt_number": 8,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "import pandas as pd",
     "prompt_number": 9,
     "outputs": [
      {
       "output_type": "stream",
       "text": "/Users/colingerber/anaconda/lib/python2.7/site-packages/pytz-2013b-py2.7.egg/pytz/__init__.py:35: UserWarning: Module argparse was already imported from /Users/colingerber/anaconda/lib/python2.7/argparse.pyc, but /Users/colingerber/anaconda/lib/python2.7/site-packages is being added to sys.path\n  from pkg_resources import resource_stream\n",
       "stream": "stderr"
      }
     ],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "df = pd.DataFrame(pstem.values(), index=pstem.keys(), columns=['pstem'])",
     "prompt_number": 10,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "comp_dict = {}\nfor item in lstem.keys():\n    if item not in comp_dict:\n        comp_dict[item] = {'lstem':0, 'pstem':0, 'wnlstem':0}\n    comp_dict[item]['lstem'] += lstem[item]\n    if item in pstem.keys():\n        comp_dict[item]['pstem'] += pstem[item]\n    if item in pstem.keys():\n        comp_dict[item]['wnlstem'] += wnlstem[item]\n    \n    ",
     "prompt_number": 11,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "df = pd.DataFrame.from_dict(comp_dict)",
     "prompt_number": 12,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "df = df.T",
     "prompt_number": 13,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "import matplotlib as plt",
     "prompt_number": 15,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "df.sort(columns='lstem', ascending=False)",
     "prompt_number": 22,
     "outputs": [
      {
       "text": "               lstem  pstem  wnlstem\n,              17936  17936    17936\nthe            10387  10113    10113\nand             5333   5333     5332\nof              4263   4266     4263\ni               2906   2906     2906\nto              2172   2172     2172\nin              1888   1871     1871\n.               1881   1881     1881\nyou             1564   1533     1533\na               1285   1285     2101\nwith            1250   1250     1250\non              1200    670      670\nis              1110   1109     1109\nal              1083      0        0\nfor             1082    992      992\nit              1035   1029     1029\nor              1019   1003     1003\nmy              1014   1014     1014\nme              1009   1009     1009\nnot              915    876      876\nthat             854    854      854\nas               831    816        0\n?                742    742      742\nfrom             703    703      703\nar               672      0        0\no                593    593      593\nbe               487    509      487\nby               482    482      482\nwhat             480    480      480\nthey             478    478      478\n...              ...    ...      ...\nprivy              1      0        0\nfirm-fibred        1      0        0\npro                1      1        1\nfirework           1      1        1\nfireplac           1      1        0\nproc               1      0        0\nfireman's          1      0        0\nfirelock           1      1        1\nfire-trumpets      1      0        0\nfire-lock          1      1        1\nfire-flashing      1      0        0\nfire-engines       1      0        0\nfire-caps          1      0        0\nprofoundest        1      1        1\nfillest            1      1        1\nfir-trees          1      0        0\nprogeny            1      0        0\nfinger-nails       1      0        0\nfinger-joints      1      0        0\nprohibit           1      1        0\nfinger'd           1      1        1\nprojectil          1      1        0\nfinest             1      1        1\nprolog             1      0        0\nprolong            1      1        0\nfine-headed        1      0        0\nfilthy             1      0        0\nfilter'd           1      1        1\npromiscu           1      1        0\nzuyd               1      0        0\n\n[8951 rows x 3 columns]",
       "html": "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>lstem</th>\n      <th>pstem</th>\n      <th>wnlstem</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>,</th>\n      <td> 17936</td>\n      <td> 17936</td>\n      <td> 17936</td>\n    </tr>\n    <tr>\n      <th>the</th>\n      <td> 10387</td>\n      <td> 10113</td>\n      <td> 10113</td>\n    </tr>\n    <tr>\n      <th>and</th>\n      <td>  5333</td>\n      <td>  5333</td>\n      <td>  5332</td>\n    </tr>\n    <tr>\n      <th>of</th>\n      <td>  4263</td>\n      <td>  4266</td>\n      <td>  4263</td>\n    </tr>\n    <tr>\n      <th>i</th>\n      <td>  2906</td>\n      <td>  2906</td>\n      <td>  2906</td>\n    </tr>\n    <tr>\n      <th>to</th>\n      <td>  2172</td>\n      <td>  2172</td>\n      <td>  2172</td>\n    </tr>\n    <tr>\n      <th>in</th>\n      <td>  1888</td>\n      <td>  1871</td>\n      <td>  1871</td>\n    </tr>\n    <tr>\n      <th>.</th>\n      <td>  1881</td>\n      <td>  1881</td>\n      <td>  1881</td>\n    </tr>\n    <tr>\n      <th>you</th>\n      <td>  1564</td>\n      <td>  1533</td>\n      <td>  1533</td>\n    </tr>\n    <tr>\n      <th>a</th>\n      <td>  1285</td>\n      <td>  1285</td>\n      <td>  2101</td>\n    </tr>\n    <tr>\n      <th>with</th>\n      <td>  1250</td>\n      <td>  1250</td>\n      <td>  1250</td>\n    </tr>\n    <tr>\n      <th>on</th>\n      <td>  1200</td>\n      <td>   670</td>\n      <td>   670</td>\n    </tr>\n    <tr>\n      <th>is</th>\n      <td>  1110</td>\n      <td>  1109</td>\n      <td>  1109</td>\n    </tr>\n    <tr>\n      <th>al</th>\n      <td>  1083</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>for</th>\n      <td>  1082</td>\n      <td>   992</td>\n      <td>   992</td>\n    </tr>\n    <tr>\n      <th>it</th>\n      <td>  1035</td>\n      <td>  1029</td>\n      <td>  1029</td>\n    </tr>\n    <tr>\n      <th>or</th>\n      <td>  1019</td>\n      <td>  1003</td>\n      <td>  1003</td>\n    </tr>\n    <tr>\n      <th>my</th>\n      <td>  1014</td>\n      <td>  1014</td>\n      <td>  1014</td>\n    </tr>\n    <tr>\n      <th>me</th>\n      <td>  1009</td>\n      <td>  1009</td>\n      <td>  1009</td>\n    </tr>\n    <tr>\n      <th>not</th>\n      <td>   915</td>\n      <td>   876</td>\n      <td>   876</td>\n    </tr>\n    <tr>\n      <th>that</th>\n      <td>   854</td>\n      <td>   854</td>\n      <td>   854</td>\n    </tr>\n    <tr>\n      <th>as</th>\n      <td>   831</td>\n      <td>   816</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>?</th>\n      <td>   742</td>\n      <td>   742</td>\n      <td>   742</td>\n    </tr>\n    <tr>\n      <th>from</th>\n      <td>   703</td>\n      <td>   703</td>\n      <td>   703</td>\n    </tr>\n    <tr>\n      <th>ar</th>\n      <td>   672</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>o</th>\n      <td>   593</td>\n      <td>   593</td>\n      <td>   593</td>\n    </tr>\n    <tr>\n      <th>be</th>\n      <td>   487</td>\n      <td>   509</td>\n      <td>   487</td>\n    </tr>\n    <tr>\n      <th>by</th>\n      <td>   482</td>\n      <td>   482</td>\n      <td>   482</td>\n    </tr>\n    <tr>\n      <th>what</th>\n      <td>   480</td>\n      <td>   480</td>\n      <td>   480</td>\n    </tr>\n    <tr>\n      <th>they</th>\n      <td>   478</td>\n      <td>   478</td>\n      <td>   478</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>privy</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>firm-fibred</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>pro</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     1</td>\n    </tr>\n    <tr>\n      <th>firework</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     1</td>\n    </tr>\n    <tr>\n      <th>fireplac</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>proc</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>fireman's</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>firelock</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     1</td>\n    </tr>\n    <tr>\n      <th>fire-trumpets</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>fire-lock</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     1</td>\n    </tr>\n    <tr>\n      <th>fire-flashing</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>fire-engines</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>fire-caps</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>profoundest</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     1</td>\n    </tr>\n    <tr>\n      <th>fillest</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     1</td>\n    </tr>\n    <tr>\n      <th>fir-trees</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>progeny</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>finger-nails</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>finger-joints</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>prohibit</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>finger'd</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     1</td>\n    </tr>\n    <tr>\n      <th>projectil</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>finest</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     1</td>\n    </tr>\n    <tr>\n      <th>prolog</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>prolong</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>fine-headed</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>filthy</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>filter'd</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     1</td>\n    </tr>\n    <tr>\n      <th>promiscu</th>\n      <td>     1</td>\n      <td>     1</td>\n      <td>     0</td>\n    </tr>\n    <tr>\n      <th>zuyd</th>\n      <td>     1</td>\n      <td>     0</td>\n      <td>     0</td>\n    </tr>\n  </tbody>\n</table>\n<p>8951 rows × 3 columns</p>\n</div>",
       "output_type": "pyout",
       "metadata": {},
       "prompt_number": 22
      }
     ],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "%matplotlib inline",
     "prompt_number": 16,
     "outputs": [],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "df.sort(columns='lstem', ascending=False)[:50].plot(kind='bar', figsize=(16,10))",
     "prompt_number": 20,
     "outputs": [
      {
       "text": "<matplotlib.axes.AxesSubplot at 0x120475b50>",
       "output_type": "pyout",
       "metadata": {},
       "prompt_number": 20
      },
      {
       "png": "iVBORw0KGgoAAAANSUhEUgAAA60AAAJeCAYAAABf1OPcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nfQAAAABJRU5ErkJggg==\n",
       "text": "<matplotlib.figure.Figure at 0x11f44ccd0>",
       "output_type": "display_data",
       "metadata": {}
      }
     ],
     "language": "python",
     "trusted": true,
     "collapsed": false
    },
    {
     "metadata": {},
     "cell_type": "markdown",
     "source": "Now it's time to analyze your data.  How do the outputs differ?  How are they similar?"
    },
    {
     "metadata": {},
     "cell_type": "code",
     "input": "",
     "outputs": [],
     "language": "python",
     "trusted": false,
     "collapsed": false
    }
   ],
   "metadata": {}
  }
 ],
 "metadata": {
  "name": "",
  "signature": "sha256:54691865ececf7816779af96add502635bd4f355e1098a3e453f19f8daa11de3"
 },
 "nbformat": 3
}