{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[u'austen-emma.txt',\n", " u'austen-persuasion.txt',\n", " u'austen-sense.txt',\n", " u'bible-kjv.txt',\n", " u'blake-poems.txt',\n", " u'bryant-stories.txt',\n", " u'burgess-busterbrown.txt',\n", " u'carroll-alice.txt',\n", " u'chesterton-ball.txt',\n", " u'chesterton-brown.txt',\n", " u'chesterton-thursday.txt',\n", " u'edgeworth-parents.txt',\n", " u'melville-moby_dick.txt',\n", " u'milton-paradise.txt',\n", " u'shakespeare-caesar.txt',\n", " u'shakespeare-hamlet.txt',\n", " u'shakespeare-macbeth.txt',\n", " u'whitman-leaves.txt']" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import nltk\n", "nltk.corpus.gutenberg.fileids()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### .isalpha()\n", "This method returns true if all characters in the string are alphabetic and there is at least one character, false otherwise." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[u'Leaves', u'of', u'Grass', u'by', u'Walt', u'Whitman', u'Come', u'said', u'my', u'soul']\n" ] } ], "source": [ "# note the use of words() to load tokens\n", "whitmanTokens = list(nltk.corpus.gutenberg.words('whitman-leaves.txt'))\n", "# filter out non-words\n", "whitmanWords = [word for word in whitmanTokens if word[0].isalpha()]\n", "print whitmanWords[:10]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "#### .collocations()\n", "There's actually a very easy and convenient way to look for the top bigrams in an NLTK text using the collocations() function and specifying the number of top frequency phrases to return." ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "young men; open air; Walt Whitman; young man; New World; every one;\n", "every thing; live oak; Good bye; whole earth; Thou knowest; thousand\n", "years; Old Age; mocking bird; shapes arise; old man; little child;\n", "steam whistle; centuries hence; old age\n" ] } ], "source": [ "whitmanText = nltk.Text (whitmanWords)\n", "# 20 top bigrams separated by semi-colon\n", "whitmanText.collocations(20)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### NLTK N-Grams" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(u'Leaves', u'of', u'Grass', u'by')\n", "(14, u'it shall be you')\n", "(11, u'of the earth and')\n", "(11, u'I do not know')\n", "(11, u'as much as the')\n", "(10, u'The shape of the')\n", "(10, u'in the open air')\n", "(10, u'of men and women')\n", "(10, u'I do not doubt')\n", "(10, u'just as much as')\n", "(8, u'in the midst of')\n", "(8, u'of the earth I')\n", "(8, u'you whoever you are')\n", "(7, u'do not know what')\n", "(7, u'the sound of the')\n", "(7, u'know what it is')\n" ] } ], "source": [ "# create four-grams\n", "whitman4grams = list(nltk.ngrams(whitmanWords,4))\n", "print whitman4grams[0] # a list of 4 grams words\n", "# determine frequency of four-grams\n", "whitman4gramsFreq = nltk.FreqDist(whitman4grams)\n", "for words, count in whitman4gramsFreq.most_common(15):\n", " print (count, ' '.join(list(words)))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Distribution of Phrase" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaoAAAEWCAYAAAA3h9P4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "whitmanText.dispersion_plot([\"I do not know\"])\n", "# won't work since phrases aren't in the emmaText tokens" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "However, we can create a new text from our ngrams and then ask for a dispersion plot. " ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAdYAAAEWCAYAAADb8rbuAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "whitman4gramsText = nltk.Text(whitman4grams)\n", "whitman4gramsText.dispersion_plot([(\"I\",\"do\",\"not\",\"know\")])" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Longest Repeating Phrases" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "('ngram of', 33, ' words occuring ', 2, ' times:', u'from top to toe I sing Not physiognomy alone nor brain alone is worthy for the Muse I say the Form complete is worthier far The Female equally with the Male I sing')\n" ] } ], "source": [ "ngramsFreqs = [] # keep track of last set of repeating phrases\n", "# create a range from 2 to the length of the text (even if we don't get that high)\n", "for length in range (2,len(whitmanWords)):\n", " ngrams = list(nltk.ngrams(whitmanWords, length))\n", " freqs = nltk.FreqDist(ngrams)\n", " \n", " # filter out frequencies that don't repeat\n", " freqs = [(ngram, count) for ngram, count in freqs.items() if count > 1]\n", " if len(freqs) > 0: # we have at least one repeating phrase\n", " ngramsFreqs = freqs # new set of frequencies\n", " else: # if we've filtered out all frequencies then break out of the loop\n", " break\n", "\n", "for ngram, count in ngramsFreqs:\n", " print('ngram of', len(ngram), ' words occuring ', count, ' times:', ' '.join(list(ngram)))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Segmenting Texts\n", "We can segment our tokens or n-grams in various ways, but one convenient way is to use a library called NumPy that is helpful for working with arrays (and graphing array-backed data). Let's see it in action with a simplified example where we're going to create a list of numbers from 0 to 9 (10 elements) and then create 5 equal bins in which to place the items." ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[0, 1, 2, 3, 4, 5, 6, 7, 8]" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "numbers = list(range(0,9)) # create a range from 0 to 9 and convert the range to a list\n", "numbers" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "('number of bins:', 5)\n" ] }, { "data": { "text/plain": [ "[array([0, 1]), array([2, 3]), array([4, 5]), array([6, 7]), array([8])]" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import numpy as np\n", "numberBins = np.array_split(numbers, 5) # divide our numbers into 5 equal bins\n", "print(\"number of bins:\", len(numberBins))\n", "numberBins" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We can do something similar with our whitman4gramsTokens, dividing the list into 10 each parts." ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Leaves of Grass by\n" ] }, { "data": { "text/plain": [ "[12628, 12628, 12628, 12627, 12627, 12627, 12627, 12627, 12627, 12627]" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "\n", "whitman4gramsTokens = [\" \".join(gram) for gram in whitman4grams]\n", "print whitman4gramsTokens[0]\n", "whitman4gramsSegments = np.array_split(whitman4gramsTokens, 10)\n", "[len(segment) for segment in whitman4gramsSegments] # how many ngrams in each bin?" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now, instead of counting the number of tokens, we'll count the number of occurrences of our search term \"it shall be you\"." ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[2, 3, 2, 0, 2, 0, 2, 0, 0, 0]" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "iDoNotKnowCounts = []\n", "for seg in whitman4gramsSegments:\n", " iDoNotKnowCounts.append(list(seg).count('I do not know'))\n", "\n", "itShallBeYouCounts # counts per segment" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "And now a simple plot of these counts (we're adding a legend to make it easier to understand)." ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD8CAYAAACMwORRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAdYAAAEWCAYAAADb8rbuAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import matplotlib.pyplot as plt\n", "line = plt.plot(iDoNotKnowCounts, label=\"I do not know\")\n", "plt.ylim(0) # make sure to set y axis to start at zero\n", "plt.legend(handles=line) # we're going to add a legend\n", "plt.show() # make sure to flush out the line chart\n", "whitman4gramsText.dispersion_plot([(\"I\",\"do\",\"not\",\"know\")]) # for comparison sake" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Line graphs can be a bit easier to read for multiple values though. Let's construct a graph that compares \"I do not know\" and \"of the earth and\"." ] }, { "cell_type": "code", "execution_count": 31, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[, ]\n" ] }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAW4AAAD8CAYAAABXe05zAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxfw/kxjWX8ZG1NsAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "searches = [\"I do not know\", \"of the earth and\"]\n", "lines = []\n", "for search in searches:\n", " line, = plt.plot([list(segment).count(search) for segment in whitman4gramsSegments], label=search)\n", " lines.append(line)\n", "print lines\n", "plt.legend(handles=lines)\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Correlations\n", "\n", "A question we might have about the graph above is to what extent values in the two lines correlate. In other words, if one line rises, does the other have a tendency to rise, or is it the opposite, or is there no real correlation (synchronized variation) between the two.\n", "\n", "Once again we can use NumPy to help us measure correlation using corrcoef(). Let's first see it in action with a couple of simple example datasets." ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[2, 3, 2, 0, 2, 0, 2, 0, 0, 0]\n", "[1, 0, 1, 2, 1, 0, 0, 5, 0, 1]\n" ] } ], "source": [ "iDoNotKnowCounts = [list(segment).count(\"I do not know\") for segment in whitman4gramsSegments]\n", "ofTheEarthAndCounts = [list(segment).count(\"of the earth and\") for segment in whitman4gramsSegments]\n", "print(iDoNotKnowCounts)\n", "print(ofTheEarthAndCounts)" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "-0.37150258224395127" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.corrcoef(iDoNotKnowCounts, ofTheEarthAndCounts)[0,1]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "A weak inverse correlation.\n", "\n", "Let's see if we can find one of our top frequency four-grams with a stronger correlation." ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[u'it shall be you', u'of the earth and', u'I do not know', u'as much as the', u'The shape of the', u'in the open air', u'of men and women', u'I do not doubt', u'just as much as', u'in the midst of', u'of the earth I', u'you whoever you are', u'do not know what', u'the sound of the', u'know what it is']\n" ] } ], "source": [ "whitman4gramsMostFreq = [\" \".join(words) for words, count in whitman4gramsFreq.most_common(15)]\n", "print (whitman4gramsMostFreq)" ] }, { "cell_type": "code", "execution_count": 37, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# build a dictionary of counts for each search item\n", "whitman4gramsSegmentsCounts = {}\n", "for search in whitman4gramsMostFreq:\n", " whitman4gramsSegmentsCounts[search] = [list(segment).count(search) for segment in whitman4gramsSegments]" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [], "source": [ "# build a dictionary of correlaiton values for \"I do not know\"\n", "iDoNotKnowCorrelations = {}\n", "for ngram, counts in whitman4gramsSegmentsCounts.items():\n", " iDoNotKnowCorrelations[ngram] = np.corrcoef(whitman4gramsSegmentsCounts[\"I do not know\"], counts)[0,1]" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "[(u'I do not know', 0.99999999999999978), (u'do not know what', 0.93566055193419362), (u'you whoever you are', 0.67033207807355677), (u'in the midst of', 0.64699663922063044), (u'in the open air', 0.5906244232186183), (u'as much as the', 0.49769250596919062), (u'just as much as', 0.48224282217041209), (u'it shall be you', 0.2641352718976871), (u'know what it is', 0.24976918100516846), (u'of the earth I', 0.1917027079172238), (u'the sound of the', 0.17875432925883694), (u'of men and women', 0.16074760739013735), (u'I do not doubt', -0.29531221160930909), (u'The shape of the', -0.32283199898606196), (u'of the earth and', -0.37150258224395127)]\n" ] }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY4AAAFpCAYAAACLRc9GAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "iDoNotKnowCorrelationFreqs = nltk.FreqDist(iDoNotKnowCorrelations)\n", "print iDoNotKnowCorrelationFreqs.most_common()\n", "iDoNotKnowCorrelationFreqs.plot()" ] }, { "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": "2.7.13" } }, "nbformat": 4, "nbformat_minor": 2 }