{ "cells": [ { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": false }, "outputs": [], "source": [ "from __future__ import division" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Load text data" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": false }, "outputs": [], "source": [ "text = open(\"text.txt\").read()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "'Clinton La'" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# SLICING\n", "text[0:10]" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "'clinton lays into trump for his praise of russia\\xe2\\x80\\x99s leader\\nby amy chozick and jonathan martin 12:28 pm et\\nhillary clinton seized on donald j. trump\\xe2\\x80\\x99s assertion at a forum on wednesday night that vladimir v. putin was a better leader than president obama.\\nshe said that mr. trump\\xe2\\x80\\x99s comments showed that, if elected, he would be little more than a tool of mr. putin.\\naccused of insufficient smiling, clinton says she will stay serious on issues 11:38 am et\\n'" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "text.lower()" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "['Clinton',\n", " 'Lays',\n", " 'Into',\n", " 'Trump',\n", " 'for',\n", " 'His',\n", " 'Praise',\n", " 'of',\n", " 'Russia\\xe2\\x80\\x99s',\n", " 'Leader',\n", " 'By',\n", " 'AMY',\n", " 'CHOZICK',\n", " 'and',\n", " 'JONATHAN',\n", " 'MARTIN',\n", " '12:28',\n", " 'PM',\n", " 'ET',\n", " 'Hillary',\n", " 'Clinton',\n", " 'seized',\n", " 'on',\n", " 'Donald',\n", " 'J.',\n", " 'Trump\\xe2\\x80\\x99s',\n", " 'assertion',\n", " 'at',\n", " 'a',\n", " 'forum',\n", " 'on',\n", " 'Wednesday',\n", " 'night',\n", " 'that',\n", " 'Vladimir',\n", " 'V.',\n", " 'Putin',\n", " 'was',\n", " 'a',\n", " 'better',\n", " 'leader',\n", " 'than',\n", " 'President',\n", " 'Obama.',\n", " 'She',\n", " 'said',\n", " 'that',\n", " 'Mr.',\n", " 'Trump\\xe2\\x80\\x99s',\n", " 'comments',\n", " 'showed',\n", " 'that,',\n", " 'if',\n", " 'elected,',\n", " 'he',\n", " 'would',\n", " 'be',\n", " 'little',\n", " 'more',\n", " 'than',\n", " 'a',\n", " 'tool',\n", " 'of',\n", " 'Mr.',\n", " 'Putin.',\n", " 'Accused',\n", " 'of',\n", " 'Insufficient',\n", " 'Smiling,',\n", " 'Clinton',\n", " 'Says',\n", " 'She',\n", " 'Will',\n", " 'Stay',\n", " 'Serious',\n", " 'on',\n", " 'Issues',\n", " '11:38',\n", " 'AM',\n", " 'ET']" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "text.split()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Basic processing: lists" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": true }, "outputs": [], "source": [ "tokens = text.split()" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "['Clinton', 'Lays', 'Into', 'Trump', 'for']" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tokens[0:5]" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "'ET'" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tokens[-1]" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Basic counting: dictionaries" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "collapsed": true }, "outputs": [], "source": [ "d = {}\n", "d['asdf'] = 5" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "{'asdf': 5}" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "d" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "collapsed": true }, "outputs": [], "source": [ "d['qwerqwereqw'] = 10.45" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "{'asdf': 5, 'qwerqwereqw': 10.45}" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "d" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "('asdf', 'qwer', 'zxcv')" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "('asdf','qwer','zxcv')" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": true }, "outputs": [], "source": [ "d[ ('a','b') ] = 1000" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "{'asdf': 5, 'qwerqwereqw': 10.45, ('a', 'b'): 1000}" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "d" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "collapsed": true }, "outputs": [], "source": [ "d[('a','b')] = 1200" ] }, { "cell_type": "code", "execution_count": 28, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "{'asdf': 5, 'qwerqwereqw': 10.45, ('a', 'b'): 1200}" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "d" ] }, { "cell_type": "code", "execution_count": 29, "metadata": { "collapsed": true }, "outputs": [], "source": [ "None" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Counting with dictionaries" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "565" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "text = open(\"new.txt\").read()\n", "tokens = text.split()\n", "len(tokens)" ] }, { "cell_type": "code", "execution_count": 32, "metadata": { "collapsed": true }, "outputs": [], "source": [ "#from collections import Counter" ] }, { "cell_type": "code", "execution_count": 36, "metadata": { "collapsed": false }, "outputs": [], "source": [ "# Counting with a simple dict\n", "counts = {}\n", "for w in tokens:\n", " if w not in counts:\n", " counts[w] = 0\n", " counts[w] = counts[w] + 1" ] }, { "cell_type": "code", "execution_count": 38, "metadata": { "collapsed": false }, "outputs": [], "source": [ "counts = {}\n", "for w in tokens:\n", " if w not in counts:\n", " counts[w] = 0\n", " counts[w] += 1" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Plotting" ] }, { "cell_type": "code", "execution_count": 39, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import matplotlib.pyplot as plt\n", "%matplotlib inline" ] }, { "cell_type": "code", "execution_count": 41, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "[]" ] }, "execution_count": 41, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEACAYAAAC9Gb03AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nm5kVnIPezKzgHPRmZgXnoDczK7j/B5ip/wYeqfD6AAAAAElFTkSuQmCC\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.plot( [1,2,4], [100, 150, 800] )" ] }, { "cell_type": "code", "execution_count": 42, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEACAYAAAC9Gb03AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n5Qx6SWo5g16SWs6gl6SW+/92Y7FhVbcWvAAAAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter( [1,2,4], [100,150,800] )" ] }, { "cell_type": "code", "execution_count": 44, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "['CHARLOTTE',\n", " '',\n", " 'N.C.',\n", " '\\xe2\\x80\\x94',\n", " 'Hillary',\n", " 'Clinton',\n", " 'excoriated',\n", " 'Donald',\n", " 'J.',\n", " 'Trump',\n", " 'on',\n", " 'Thursday',\n", " 'for',\n", " 'asserting',\n", " 'that',\n", " 'the',\n", " 'Russian',\n", " 'president',\n", " '',\n", " 'Vladimir',\n", " 'V.',\n", " 'Putin',\n", " '',\n", " 'was',\n", " 'a',\n", " 'better',\n", " 'leader',\n", " 'than',\n", " 'President',\n", " 'Obama',\n", " '',\n", " 'saying',\n", " 'Mr.',\n", " 'Trump\\xe2\\x80\\x99s',\n", " 'praise',\n", " 'for',\n", " 'the',\n", " 'authoritarian',\n", " 'leader',\n", " 'of',\n", " 'an',\n", " 'adversarial',\n", " 'power',\n", " '\\xe2\\x80\\x9cis',\n", " 'not',\n", " 'just',\n", " 'unpatriotic',\n", " 'and',\n", " 'insulting',\n", " 'to',\n", " 'the',\n", " 'people',\n", " 'of',\n", " 'our',\n", " 'country',\n", " '',\n", " 'as',\n", " 'well',\n", " 'as',\n", " 'to',\n", " 'our',\n", " 'commander',\n", " 'in',\n", " 'chief',\n", " '',\n", " 'it',\n", " 'is',\n", " 'scary.\\xe2\\x80\\x9d\\n\\nMrs.',\n", " 'Clinton',\n", " '',\n", " 'the',\n", " 'Democratic',\n", " 'presidential',\n", " 'candidate',\n", " '',\n", " 'seized',\n", " 'on',\n", " 'Mr.',\n", " 'Trump\\xe2\\x80\\x99s',\n", " 'assertion',\n", " 'in',\n", " 'a',\n", " 'televised',\n", " 'forum',\n", " 'Wednesday',\n", " 'that',\n", " 'Mr.',\n", " 'Putin\\xe2\\x80\\x99s',\n", " 'incursions',\n", " 'into',\n", " 'neighboring',\n", " 'countries',\n", " '',\n", " 'crackdown',\n", " 'on',\n", " 'Russia\\xe2\\x80\\x99s',\n", " 'independent',\n", " 'press',\n", " 'and',\n", " 'support',\n", " 'for',\n", " 'America\\xe2\\x80\\x99s',\n", " 'enemies',\n", " 'were',\n", " 'no',\n", " 'less',\n", " 'troublesome',\n", " 'than',\n", " 'Mr.',\n", " 'Obama\\xe2\\x80\\x99s',\n", " 'transgressions.',\n", " 'She',\n", " 'said',\n", " 'it',\n", " 'showed',\n", " 'that',\n", " 'if',\n", " 'elected',\n", " '',\n", " 'her',\n", " 'Republican',\n", " 'rival',\n", " 'would',\n", " 'be',\n", " 'little',\n", " 'more',\n", " 'than',\n", " 'a',\n", " 'tool',\n", " 'of',\n", " 'Mr.',\n", " 'Putin.\\n\\n\\xe2\\x80\\x9cIt',\n", " 'suggests',\n", " 'he',\n", " 'will',\n", " 'let',\n", " 'Putin',\n", " 'do',\n", " 'whatever',\n", " 'Putin',\n", " 'wants',\n", " 'to',\n", " 'do',\n", " '',\n", " 'and',\n", " 'then',\n", " 'make',\n", " 'excuses',\n", " 'for',\n", " 'him',\n", " '\\xe2\\x80\\x9d',\n", " 'Mrs.',\n", " 'Clinton',\n", " 'told',\n", " 'reporters',\n", " 'in',\n", " 'New',\n", " 'York',\n", " 'on',\n", " 'Thursday',\n", " 'morning',\n", " 'at',\n", " 'the',\n", " 'White',\n", " 'Plains',\n", " 'airport',\n", " '',\n", " 'ratcheting',\n", " 'up',\n", " 'her',\n", " 'oratory',\n", " 'as',\n", " 'polls',\n", " 'indicate',\n", " 'the',\n", " 'race',\n", " 'has',\n", " 'tightened',\n", " '\\xe2\\x80\\x94',\n", " 'and',\n", " 'as',\n", " 'Mr.',\n", " 'Trump',\n", " 'continues',\n", " 'to',\n", " 'say',\n", " 'things',\n", " 'rarely',\n", " 'heard',\n", " 'before',\n", " 'from',\n", " 'a',\n", " 'major',\n", " 'party',\n", " 'presidential',\n", " 'nominee.\\n\\nIn',\n", " 'the',\n", " 'Wednesday',\n", " 'night',\n", " 'forum',\n", " 'on',\n", " 'NBC',\n", " 'and',\n", " 'MSNBC',\n", " '',\n", " 'which',\n", " 'was',\n", " 'devoted',\n", " 'to',\n", " 'national',\n", " 'security',\n", " 'issues',\n", " '',\n", " 'Mr.',\n", " 'Trump',\n", " 'twice',\n", " 'denigrated',\n", " 'America\\xe2\\x80\\x99s',\n", " 'generals',\n", " '',\n", " 'suggested',\n", " 'he',\n", " 'would',\n", " 'fire',\n", " 'the',\n", " 'country\\xe2\\x80\\x99s',\n", " 'current',\n", " 'military',\n", " 'leadership',\n", " 'and',\n", " 'claimed',\n", " '',\n", " 'without',\n", " 'offering',\n", " 'evidence',\n", " '',\n", " 'that',\n", " 'the',\n", " 'intelligence',\n", " 'officials',\n", " 'who',\n", " 'recently',\n", " 'gave',\n", " 'him',\n", " 'a',\n", " 'classified',\n", " 'briefing',\n", " 'about',\n", " 'threats',\n", " 'to',\n", " 'the',\n", " 'United',\n", " 'States',\n", " 'were',\n", " 'not',\n", " 'pleased',\n", " 'with',\n", " 'Mr.',\n", " 'Obama.\\n\\nIn',\n", " 'a',\n", " 'news',\n", " 'conference',\n", " 'before',\n", " 'boarding',\n", " 'her',\n", " 'campaign',\n", " 'plane',\n", " '',\n", " 'Mrs.',\n", " 'Clinton',\n", " 'appeared',\n", " 'incredulous',\n", " 'at',\n", " 'times',\n", " 'as',\n", " 'she',\n", " 'remarked',\n", " 'upon',\n", " 'Mr.',\n", " 'Trump\\xe2\\x80\\x99s',\n", " 'statements',\n", " 'the',\n", " 'night',\n", " 'before',\n", " '',\n", " 'particularly',\n", " 'about',\n", " 'Mr.',\n", " 'Putin.\\n\\nIn',\n", " 'the',\n", " 'forum',\n", " '',\n", " 'Mr.',\n", " 'Trump',\n", " 'said',\n", " 'of',\n", " 'Mr.',\n", " 'Putin',\n", " 'that',\n", " 'he',\n", " 'had',\n", " 'been',\n", " 'a',\n", " 'leader',\n", " '\\xe2\\x80\\x9cfar',\n", " 'more',\n", " 'than',\n", " 'our',\n", " 'president.\\xe2\\x80\\x9d\\n\\nAnd',\n", " 'after',\n", " 'Matt',\n", " 'Lauer',\n", " '',\n", " 'the',\n", " 'NBC',\n", " 'anchor',\n", " 'who',\n", " 'moderated',\n", " 'the',\n", " 'event',\n", " '',\n", " 'highlighted',\n", " 'Mr.',\n", " 'Putin\\xe2\\x80\\x99s',\n", " 'record',\n", " '',\n", " 'Mr.',\n", " 'Trump',\n", " 'shot',\n", " 'back',\n", " '',\n", " '\\xe2\\x80\\x9cBut',\n", " 'do',\n", " 'you',\n", " 'want',\n", " 'me',\n", " 'to',\n", " 'start',\n", " 'naming',\n", " 'some',\n", " 'of',\n", " 'the',\n", " 'things',\n", " 'that',\n", " 'President',\n", " 'Obama',\n", " 'does',\n", " 'at',\n", " 'the',\n", " 'same',\n", " 'time?\\xe2\\x80\\x9d\\n\\nContinue',\n", " 'reading',\n", " 'the',\n", " 'main',\n", " 'story\\n\\nPresidential',\n", " 'Election',\n", " '2016\\nThe',\n", " 'latest',\n", " 'news',\n", " 'and',\n", " 'analysis',\n", " 'of',\n", " 'the',\n", " 'candidates',\n", " 'and',\n", " 'issues',\n", " 'shaping',\n", " 'the',\n", " 'presidential',\n", " 'race.\\nWho',\n", " 'Is',\n", " 'Winning',\n", " 'in',\n", " 'West',\n", " 'Virginia?\\nSEP',\n", " '8\\nDonald',\n", " 'Trump',\n", " 'vs.',\n", " 'Hillary',\n", " 'Clinton:',\n", " 'Where',\n", " 'They',\n", " 'Stand',\n", " 'on',\n", " 'Education\\nSEP',\n", " '8\\nNot',\n", " 'Smiling',\n", " 'Enough?',\n", " 'Hillary',\n", " 'Clinton',\n", " 'Says',\n", " 'She',\n", " 'Will',\n", " 'Stay',\n", " 'Serious',\n", " 'on',\n", " 'Vital',\n", " 'Issues\\nSEP',\n", " '8\\nWho',\n", " 'Is',\n", " 'Winning',\n", " 'in',\n", " 'Alabama?\\nSEP',\n", " '8\\nMatt',\n", " 'Lauer',\n", " 'Loses',\n", " 'the',\n", " 'War',\n", " 'in',\n", " 'a',\n", " 'Battle',\n", " 'Between',\n", " 'the',\n", " 'Candidates\\nSEP',\n", " '8\\nSee',\n", " 'More',\n", " '\\xc2\\xbb\\n\\nAdvertisement\\n\\nContinue',\n", " 'reading',\n", " 'the',\n", " 'main',\n", " 'story\\nIn',\n", " 'her',\n", " 'news',\n", " 'conference',\n", " 'Thursday',\n", " '',\n", " 'Mrs.',\n", " 'Clinton',\n", " 'asked',\n", " '',\n", " '\\xe2\\x80\\x9cWhat',\n", " 'would',\n", " 'Ronald',\n", " 'Reagan',\n", " 'say',\n", " 'about',\n", " 'a',\n", " 'Republican',\n", " 'nominee',\n", " 'who',\n", " 'attacks',\n", " 'American',\n", " 'generals',\n", " 'and',\n", " 'heaps',\n", " 'praise',\n", " 'on',\n", " 'Russia\\xe2\\x80\\x99s',\n", " 'president?\\xe2\\x80\\x9d\\n\\nMrs.',\n", " 'Clinton',\n", " 'was',\n", " 'also',\n", " 'withering',\n", " 'in',\n", " 'referring',\n", " 'to',\n", " 'Mr.',\n", " 'Trump\\xe2\\x80\\x99s',\n", " 'assertion',\n", " 'that',\n", " 'the',\n", " 'United',\n", " 'States',\n", " 'made',\n", " 'a',\n", " 'mistake',\n", " 'by',\n", " 'not',\n", " 'seizing',\n", " 'oil',\n", " 'fields',\n", " 'in',\n", " 'Iraq',\n", " 'and',\n", " 'Libya',\n", " 'after',\n", " 'invading',\n", " 'the',\n", " 'countries.\\n\\n\\xe2\\x80\\x9cThe',\n", " 'United',\n", " 'States',\n", " 'of',\n", " 'America',\n", " 'does',\n", " 'not',\n", " 'invade',\n", " 'other',\n", " 'countries',\n", " 'to',\n", " 'plunder',\n", " 'and',\n", " 'pillage',\n", " '\\xe2\\x80\\x9d',\n", " 'she',\n", " 'said.',\n", " '\\xe2\\x80\\x9cWe',\n", " 'don\\xe2\\x80\\x99t',\n", " 'send',\n", " 'our',\n", " 'brave',\n", " 'men',\n", " 'and',\n", " 'women',\n", " 'around',\n", " 'the',\n", " 'world',\n", " 'to',\n", " 'steal',\n", " 'oil.',\n", " 'And',\n", " 'that\\xe2\\x80\\x99s',\n", " 'not',\n", " 'even',\n", " 'getting',\n", " 'into',\n", " 'the',\n", " 'absurdity',\n", " 'of',\n", " 'what',\n", " 'is',\n", " 'involved.\\xe2\\x80\\x9d\\n\\nMrs.',\n", " 'Clinton',\n", " '',\n", " 'who',\n", " 'had',\n", " 'faced',\n", " 'a',\n", " 'barrage',\n", " 'of',\n", " 'questions',\n", " 'in',\n", " 'her',\n", " 'half',\n", " 'of',\n", " 'the',\n", " 'forum',\n", " 'about',\n", " 'her',\n", " 'use',\n", " 'of',\n", " 'a',\n", " 'private',\n", " 'email',\n", " 'server',\n", " 'as',\n", " 'secretary',\n", " 'of',\n", " 'state',\n", " '',\n", " 'also',\n", " 'used',\n", " 'the',\n", " 'news',\n", " 'conference',\n", " 'to',\n", " 'try',\n", " 'to',\n", " 'drive',\n", " 'a',\n", " 'wedge',\n", " 'between',\n", " 'Mr.',\n", " 'Trump',\n", " 'and',\n", " 'the',\n", " 'leadership',\n", " 'of',\n", " 'his',\n", " 'party.\\n\\n\\n']" ] }, "execution_count": 44, "metadata": {}, "output_type": "execute_result" } ], "source": [ "re.split('[ ,]', text)" ] } ], "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 }