from nltk.book import *
*** Introductory Examples for the NLTK Book ***
Loading text1, ..., text9 and sent1, ..., sent9
Type the name of the text or sentence to view it.
Type: 'texts()' or 'sents()' to list the materials.
text1: Moby Dick by Herman Melville 1851
text2: Sense and Sensibility by Jane Austen 1811
text3: The Book of Genesis
text4: Inaugural Address Corpus
text5: Chat Corpus
text6: Monty Python and the Holy Grail
text7: Wall Street Journal
text8: Personals Corpus
text9: The Man Who Was Thursday by G . K . Chesterton 1908
查看词汇出现的上下文
text1.concordance("Dick" )
Displaying 25 of 84 matches:
Dick by Herman Melville 1851 ] ETYMOLOGY
must be the same that some call Moby Dick ." " Moby Dick ?" shouted Ahab . " D
e that some call Moby Dick ." " Moby Dick ?" shouted Ahab . " Do ye know the w
Death and devils ! men , it is Moby Dick ye have seen -- Moby Dick -- Moby Di
it is Moby Dick ye have seen -- Moby Dick -- Moby Dick !" " Captain Ahab ," sa
ck ye have seen -- Moby Dick -- Moby Dick !" " Captain Ahab ," said Starbuck ,
Captain Ahab , I have heard of Moby Dick -- but it was not Moby Dick that too
of Moby Dick -- but it was not Moby Dick that took off thy leg ?" " Who told
my hearties all round ; it was Moby Dick that dismasted me ; Moby Dick that b
s Moby Dick that dismasted me ; Moby Dick that brought me to this dead stump I
white whale ; a sharp lance for Moby Dick !" " God bless ye ," he seemed to ha
white whale ? art not game for Moby Dick ?" " I am game for his crooked jaw ,
l whaleboat ' s bow -- Death to Moby Dick ! God hunt us all , if we do not hun
hunt us all , if we do not hunt Moby Dick to his death !" The long , barbed st
owels to feel fear ! CHAPTER 41 Moby Dick . I , Ishmael , was one of that crew
ividualizing tidings concerning Moby Dick . It was hardly to be doubted , that
on must have been no other than Moby Dick . Yet as of late the Sperm Whale fis
ident ignorantly gave battle to Moby Dick ; such hunters , perhaps , for the m
g and piling their terrors upon Moby Dick ; those things had gone far to shake
ies , which eventually invested Moby Dick with new terrors unborrowed from any
rmen recalled , in reference to Moby Dick , the earlier days of the Sperm Whal
ngs were ready to give chase to Moby Dick ; and a still greater number who , c
was the unearthly conceit that Moby Dick was ubiquitous ; that he had actuall
their superstitions ; declaring Moby Dick not only ubiquitous , but immortal (
shaped lower jaw beneath him , Moby Dick had reaped away Ahab ' s leg , as a
查看和目标词出现在相似上下文中的词汇
text2.similar("father" )
mother sister brother heart wife own name family face house sex
feelings cousin son engagement mind head being attachment choice
查看两个词出现处相似的上下文
text2.common_contexts(["monstrous" ,"very" ])
a_pretty is_pretty a_lucky am_glad be_glad
绘制词汇在文中的分布表
text1.dispersion_plot(["big" , "very" , "whale" , "pretty" ])
text4.dispersion_plot(["man" ,"woman" ])
展示词汇绝对丰富程度 构建有序的词汇表
number = sorted(set(text3))
len(number)
2789
展示词汇相对丰富程度 平均出现次数
from __future__ import division
len(text3)/len(set(text3))
16.050197203298673
特定词在文中出现的百分比
100 * text5.count("lol" )/len(text5)
1.5640968673628082
def lexical_diversity (text) :
return len(text)/len(set(text))
def percentage (count, total) :
return 100 * count / total
print lexical_diversity(text2)
print percentage(text2.count("sense" ),len(text2))
20.7194497293
0.0218963666158
ex1= ['Monty' , 'Python' , 'and' , 'the' , 'Holy' , 'Grail' ,'.' ]
print sorted(ex1)
print len(ex1)
print lexical_diversity(ex1)
print percentage(ex1.count("." ),len(ex1))
['.', 'Grail', 'Holy', 'Monty', 'Python', 'and', 'the']
7
1.0
14.2857142857
频率分布 FreqDist
fdist1 = FreqDist(text2)
fdist1.keys()[:50 ]
[u'succour',
u'four',
u'woods',
u'hanging',
u'woody',
u'conjure',
u'looking',
u'eligible',
u'scold',
u'unsuitableness',
u'meadows',
u'stipulate',
u'leisurely',
u'bringing',
u'disturb',
u'internally',
u'hostess',
u'mohrs',
u'persisted',
u'Does',
u'succession',
u'tired',
u'cordially',
u'pulse',
u'elegant',
u'second',
u'sooth',
u'shrugging',
u'abundantly',
u'errors',
u'forgetting',
u'contributed',
u'fingers',
u'increasing',
u'exclamations',
u'hero',
u'leaning',
u'Truth',
u'here',
u'china',
u'hers',
u'natured',
u'substance',
u'unwillingness',
u'pretensions',
u'reports',
u'NOT',
u'NOW',
u'divide',
u'sweetest']
fdist1['sweetest' ]
2
fdist1.plot(50 , cumulative=True )
len(text2)
141576
fdist1.hapaxes()
[u'succour',
u'woody',
u'conjure',
u'unsuitableness',
u'meadows',
u'stipulate',
u'leisurely',
u'hostess',
u'mohrs',
u'sooth',
u'shrugging',
u'abundantly',
u'errors',
u'forgetting',
u'exclamations',
u'hero',
u'Truth',
u'substance',
u'reports',
u'Three',
u'summons',
u'forbore',
u'cherishing',
u'impartiality',
u'females',
u'successful',
u'irksome',
u'pursue',
u'complaining',
u'significancy',
u'feature',
u'embellishments',
u'hop',
u'abstraction',
u'OWN',
u'entrusted',
u'keeps',
u'nonsensical',
u'restriction',
u'unexhilarating',
u'unworthiness',
u'concurrence',
u'wrought',
u'fir',
u'unforeseen',
u'recognised',
u'auditors',
u'endeavoring',
u'admirable',
u'enrich',
u'wooded',
u'rumour',
u'blushes',
u'ankle',
u'uninfluenced',
u'interfering',
u'preceded',
u'whip',
u'toleration',
u'literature',
u'diction',
u'excepting',
u'mend',
u'Vanity',
u'sheet',
u'estimate',
u'unstudied',
u'tempting',
u'breed',
u'Please',
u'clamorous',
u'blossoms',
u'ranging',
u'project',
u'uncouth',
u'amusing',
u'Mansion',
u'loitered',
u'tempted',
u'Extend',
u'shuffling',
u'theme',
u'bliss',
u'touched',
u'stammered',
u'relish',
u'esteeming',
u'expediency',
u'unexpectedly',
u'playfulness',
u'rings',
u'score',
u'scorn',
u'unobtrusiveness',
u'sacrificing',
u'refinement',
u'demanded',
u'argue',
u'adapted',
u'Willing',
u'Comparisons',
u'tallest',
u'exactness',
u'incommode',
u'worked',
u'foreplanned',
u'conditioned',
u'anticipating',
u'Valley',
u'dryness',
u'fairly',
u'boiled',
u'qualifications',
u'confusedly',
u'redeem',
u'echoed',
u'misconstruction',
u'beset',
u'exclaiming',
u'rushing',
u'ham',
u'obedient',
u'disagreement',
u'birth',
u'replace',
u'remind',
u'misled',
u'beneficial',
u'honeysuckles',
u'fox',
u'witty',
u'losing',
u'memorable',
u'bowing',
u'Think',
u'shaken',
u'nought',
u'Scotland',
u'respectably',
u'administer',
u'beings',
u'despised',
u']',
u'denoting',
u'safeguard',
u'humbled',
u'mighty',
u'juvenile',
u'Sit',
u'restorative',
u'acacia',
u'unlover',
u'protested',
u'solicitation',
u'dotted',
u'circumstanced',
u'intend',
u'intent',
u'rolling',
u'beamed',
u'whoever',
u'indolent',
u'vex',
u'recurrence',
u'fullest',
u'speculation',
u'occurrence',
u'celebrated',
u'funeral',
u'commonly',
u'Born',
u'Frosts',
u'reclaim',
u'ESTEEM',
u'prefer',
u'obstinacy',
u'humouring',
u'undergone',
u'wicket',
u'sisterly',
u'resuscitation',
u'Those',
u'loving',
u'refrain',
u'odious',
u'militated',
u'Pope',
u'Midsummer',
u'believes',
u'indolence',
u'stole',
u'deserves',
u'poking',
u'cavil',
u'dove',
u'stress',
u'canvassing',
u'inhabiting',
u'swollen',
u'Encouraged',
u'unsolicited',
u'LESS',
u'quarrelled',
u'tore',
u'derive',
u'haughty',
u'Folly',
u'bashful',
u'overpowering',
u'establishing',
u'bowling',
u'prudently',
u'retailed',
u'giddy',
u'astray',
u'investigation',
u'Offended',
u'complicated',
u'remainder',
u'patronage',
u'crossness',
u'undesirable',
u'jumbled',
u'conscientiously',
u'habitation',
u'partook',
u'city',
u'2',
u'stuffed',
u'JOHN',
u'representing',
u'Seven',
u'Exert',
u'depressed',
u'coats',
u'KNEW',
u'tasted',
u'jewels',
u'tastes',
u'lurking',
u'BOTH',
u'Half',
u'coincide',
u'opposite',
u'discerning',
u'horridly',
u'impoverishing',
u'blockhead',
u'bright',
u'transact',
u'uppermost',
u'dispute',
u'dissimilar',
u'condemning',
u'Having',
u'Unaccountable',
u'borrow',
u'landlord',
u'noisier',
u'CATCHING',
u'mutton',
u'refreshed',
u'apiece',
u'rapacious',
u'thickly',
u'cramps',
u'plantation',
u'stretch',
u'west',
u'braving',
u'practised',
u'hilarity',
u'possessor',
u'endured',
u'.)--',
u'regularity',
u'fame',
u'parliament',
u'reanimate',
u'unemployed',
u'sterling',
u'defy',
u'entanglement',
u'devolved',
u'veal',
u'judiciously',
u'scrape',
u'vague',
u'doubtingly',
u'stranger',
u'discarded',
u'militate',
u'divine',
u'restoring',
u'destroys',
u'biased',
u";'",
u'edtions',
u'meal',
u'practicable',
u'image',
u'widower',
u'dawned',
u'lounging',
u'sealed',
u'DRAW',
u'imbibed',
u'survived',
u'buying',
u'abused',
u'pull',
u'rage',
u'abuses',
u'darker',
u'Hon',
u'accents',
u'stealing',
u'associating',
u'ay',
u'blinded',
u'Gracious',
u'accosted',
u'mass',
u'original',
u'curate',
u'caused',
u'reasoning',
u'improperly',
u'Biddy',
u'Precious',
u'Conversation',
u'LOOK',
u'desertion',
u'honourably',
u'Drury',
u'outdone',
u'mound',
u'cessation',
u'regiment',
u'crowned',
u'6',
u'inquisitiveness',
u'spoilt',
u'Relate',
u'foundations',
u'keeping',
u'gallop',
u'unbiased',
u'salts',
u'reproachfully',
u'respective',
u'imminent',
u'enlarge',
u'relinquished',
u'disgraced',
u'sympathize',
u'imagery',
u'passages',
u'incessantly',
u'installed',
u'signs',
u'shuddering',
u'propose',
u'likeness',
u'assemblies',
u'Newton',
u'truths',
u'upstairs',
u'disclaiming',
u'grandmothers',
u'exorbitant',
u'embellishment',
u'candlelight',
u'silks',
u'denoted',
u'impudence',
u'risen',
u'rises',
u'II',
u'owners',
u'decently',
u'afflictions',
u'instigation',
u'rooted',
u'transgressed',
u'disordered',
u'heads',
u'threatening',
u'Twill',
u'demonstrations',
u'reprobate',
u'extorted',
u'reliance',
u'interrupting',
u'unequal',
u'accommodations',
u'defended',
u'surpassed',
u'degraded',
u'occupation',
u'wrapt',
u'detaining',
u'waistcoats',
u'blameable',
u'remedy',
u'closely',
u'compass',
u'cruelly',
u'enemy',
u'proclaim',
u'potent',
u'outwardly',
u'seconded',
u'hauteur',
u'premises',
u'Against',
u'untouched',
u'retarded',
u'bely',
u'archness',
u'publishing',
u'proprietor',
u'39',
u'hardness',
u'slyly',
u'Cold',
u'Concern',
u'indelicacy',
u'beautifully',
u'vanish',
u'renounced',
u'shorten',
u'failure',
u'doat',
u'infamous',
u'oddest',
u'comprise',
u'Ungracious',
u'detract',
u'THREE',
u'conclusions',
u'servilely',
u'admission',
u'parents',
u'depravity',
u'reverted',
u'emergency',
u'emergence',
u'projects',
u'stylish',
u'disorder',
u'palm',
u'curious',
u'eclat',
u'novelty',
u'religion',
u'seclusion',
u'discontented',
u'unintentional',
u'awaited',
u'appropriate',
u'repaid',
u'spending',
u'occupy',
u'unknowingly',
u'considerably',
u'undeserving',
u'patronised',
u'nieces',
u'unpremeditated',
u'genial',
u'reconcile',
u'defined',
u'presided',
u'surveying',
u'stiffly',
u'invalid',
u'condolence',
u'livings',
u'prosecution',
u'anticipations',
u'rescued',
u'indecorous',
u'scratch',
u'broader',
u'amiss',
u'carelessly',
u'resources',
u'panting',
u'detested',
u'Dennison',
u'inelegant',
u'incoherently',
u'imply',
u'henceforth',
u'flowing',
u'scenery',
u'rascally',
u'gathered',
u'Gibson',
u'scornfully',
u'desiring',
u'cheered',
u'encroachments',
u'pencil',
u'laboured',
u'MADAM',
u'bodily',
u'foolishly',
u'retreated',
u'streamed',
u'purposes',
u'await',
u'preferring',
u'huswifes',
u'counter',
u'alloy',
u'recreating',
u'chosen',
u'imperfection',
u'spoiling',
u'unbounded',
u'forfeiting',
u'billiard',
u'conformity',
u'undertaking',
u'traced',
u'scanty',
u'slightingly',
u'thirteen',
u'irritation',
u'wander',
u'alighted',
u'blown',
u'alleged',
u'Farm',
u'malady',
u'enforcement',
u'stomach',
u'HERS',
u'tortured',
u'torrent',
u'ingenious',
u'separations',
u'gently',
u'fourteenth',
u'viewed',
u'patroness',
u'manor',
u'courtesy',
u'wounded',
u'bedroom',
u'unconnected',
u'trivial',
u'Grandeur',
u'conciliate',
u'quickened',
u'riding',
u'handle',
u'undivided',
u'Whether',
u'familiar',
u'listener',
u'Once',
u'contemptible',
u'taxed',
u'guessing',
u'allusion',
u'incurable',
u'packed',
u'illaudable',
u'destiny',
u'insulting',
u'quickest',
u'barbarously',
u'observable',
u'whispering',
u'meantime',
u'powered',
u'poured',
u'feather',
u'>',
u'hateful',
u'banish',
u'LUCY',
u'westerly',
u'Supported',
u've',
u':--"',
u'immoderately',
u'pangs',
u'romance',
u'feminine',
u'covenant',
u'ball',
u'monopolize',
u'expand',
u'philippic',
u'patterns',
u'afflicted',
u'clergyman',
u'fluctuating',
u'goings',
u'incessant',
u'descendant',
u'chairs',
u'inconstant',
u'recognition',
u'disbelief',
u'apprehended',
u'hoarded',
u'undoubtingly',
u'drift',
u'repaired',
u'merited',
u'concession',
u'diabolical',
u'cultivated',
u'roads',
u'quarrelling',
u'Early',
u'prepossessing',
u'stocks',
u'justifying',
u'encouragements',
u'-?"',
u'MIND',
u'delivery',
u'grate',
u'chained',
u'detestably',
u'cordial',
u'rightly',
u'nurses',
u'contribute',
u'faintness',
u'denote',
u'disengagement',
u'effected',
u'expensiveness',
u'efficacy',
u'excellencies',
u'trials',
u'compares',
u'behold',
u'illusion',
u'dismiss',
u'surplice',
u'abhor',
u'unspeakable',
u'saves',
u'oldest',
u'effectually',
u'sellers',
u'disobedient',
u'immoveable',
u'FAITH',
u'Strange',
u'incompatible',
u'Sally',
u'Brown',
u'admirers',
u'equals',
u'Queen',
u'Hush',
u'angrily',
u'uncivil',
u'negative',
u'knoll',
u'administering',
u'striving',
u'ere',
u'transparency',
u'blooming',
u'fanciful',
u'unwarily',
u'indubitable',
u'taverns',
u'nipped',
u'frequency',
u'befallen',
u'production',
u'uncordial',
u'break',
u'band',
u'bank',
u'rocks',
u'lifted',
u'Confess',
u'Parrys',
u'remorse',
u'medicine',
u'disagreements',
u'mourning',
u'disputes',
u'forcibly',
u'detecting',
u'unfulfilled',
u'caprice',
u'festival',
u'footsteps',
u'Going',
u'thick',
u'pardonable',
u'seduction',
u'compromise',
u'dogs',
u'Preparation',
u'splendidly',
u'contrasted',
u'interests',
u'encumbered',
u'maxims',
u'completed',
u'circles',
u'exercised',
u'extending',
u'accounted',
u'respectfully',
u'wrung',
u'painfully',
u'guidance',
u'deepest',
u'adequate',
u'warmest',
u'yielded',
u'covering',
u'exchanged',
u'rung',
u'observer',
u'discussions',
u'draws',
u'revealment',
u'PARTIES',
u'confessedly',
u'blights',
u'packages',
u'climate',
u'cod',
u'negotiation',
u'collecting',
u'widen',
u'seizure',
u'dawdled',
u'petty',
u'attacked',
u'inconsolable',
u'deterred',
u'Westminster',
u'east',
u'aim',
u'Esteem',
u'sting',
u'slighting',
u'1811',
u'bedchamber',
u'acquitting',
u'fuss',
u'inheritor',
u'swell',
u'hang',
u'confiding',
u'blamed',
u'Mind',
u'Mine',
u'mingle',
u'slighter',
u'adding',
u'belongs',
u'tricking',
u'retreat',
u'invaluable',
u'critique',
u'Epicurism',
u'comments',
u'illustration',
u'impenetrable',
u'newspapers',
u'banker',
u'horizon',
u'Priory',
u'rendering',
u'amidst',
u'unchanging',
u'editions',
u'unusually',
u'TWO',
u'evidence',
u'subsist',
u'stake',
u'holding',
u'test',
u'brothers',
u'assiduous',
u'paces',
u'Bishop',
u'beds',
u'songs',
u'contributing',
u'mounted',
u'disapproves',
u'gigs',
u'disapproved',
u'puppyism',
u'feebly',
u'blast',
u'feeble',
u'Just',
u'altering',
u'agitate',
u'niggardly',
u'helpless',
u'foregoing',
u'uniform',
u'Imagine',
u'During',
u'appeal',
u'muslin',
u'merriment',
u'pillow',
u'retired',
u'captivate',
u'Pity',
u'club',
u'ninny',
u'clue',
u'commissioned',
u'Down',
u'hears',
u'gales',
u'Dullness',
u'malevolence',
u'economy',
u'superintend',
u'?)',
u'flourish',
u'lifting',
u'candles',
u'crept',
u'playful',
u'vicinity',
u'inflicted',
u'Concealing',
u'Norfolk',
u'hall',
u'wont',
u'concerto',
u'Misses',
u'bursts',
u'furnishing',
u'em',
u'directing',
u'naming',
u'shown',
u'perfections',
u'oftenest',
u'disapprobation',
u'temporizing',
u'Impatient',
u'intruding',
u'counteracted',
u'promotion',
u'occupations',
u'omitted',
u'comprised',
u'Till',
u'forwarding',
u'lightened',
u'artless',
u'rugged',
u'respectability',
u'renewing',
u'spraining',
u'twould',
u'unconquerable',
u'pattern',
u'dispersed',
u'ELINOR',
u'whiled',
u'honours',
u'Pardon',
u'protestations',
u'suspects',
u'3',
u'despatching',
u'prettiest',
u'emigrant',
u"'--",
u'reasonableness',
u'reluctantly',
u'comer',
u'shamefully',
u'madness',
u'dispatch',
u'Eager',
u'thistles',
u'muttered',
u'olives',
u'external',
u'countless',
u'winks',
u'trick',
u'bias',
u'hens',
u'worry',
u'northward',
u'indefatigable',
u'Supposing',
u'thunderbolt',
u'constitutional',
u'charged',
u'speed',
u'politely',
u'execution',
u'miracle',
u'verbal',
u'zealously',
u'duration',
u'capability',
u'passions',
u'unlocked',
u'garret',
u'carefulness',
u'tuition',
u'fondness',
u'Get',
u'boldly',
u'sedulously',
u'persecution',
u'Add',
u".'--",
u'stare',
u'forwarded',
u'start',
u'cats',
u'drains',
u'pitched',
u'copied',
u'toned',
u'intents',
u'remembrances',
u'humiliations',
u'sheath',
u'Law',
u'THERE',
u'endeavors',
u'bulk',
u'moonlight',
u'Dearest',
u'alleviation',
u'expatiate',
u'pique',
u'bequeath',
u'referring',
u'confidential',
u'souls',
u'abatement',
u'-?',
u'streets',
u'chuckle',
u'induce',
u'witnesses',
u'Thunderbolts',
u'apologized',
u'witticisms',
u'loose',
u'answers',
u'praises',
u'inspired',
u'soldier',
u'Clarke',
u'attendant',
u'ash',
u'injure',
u'mysterious',
u'Abundance',
u'St',
u'producing',
u'nine',
u'spontaneous',
u'history',
u'claimed',
u'weakening',
u'resettled',
u'tries',
u'imaginations',
u'Cassino',
u'daggers',
u'contrives',
u'dispersing',
u'dream',
u'systems',
u'differed',
u'friendliest',
u'forbear',
u'food',
u'ye',
u'atoning',
u'OCCASION',
u'Gentleman',
...]