Python中文自然语言处理-NLTK 学习笔记1 chapter1

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  #确保使用浮点除法
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',
 ...]