# 把语料中的单词全部抽取出来, 转成小写, 并且去除单词中间的特殊符号
def words(text): return re.findall('[a-z]+', text.lower()) def train(features):
model = collections.defaultdict(lambda: 1)
for f in features:
model[f] += 1
return model NWORDS = train(words(open('big.txt').read()))
读入的数据是：福尔摩斯探案，6mb这样......
输出NWORDS:
defaultdict(<function __main__.train.<locals>.<lambda>>,
{'counterorders': 2,
'ureters': 3,
'displeasure': 9,
'omitted': 10,
'sparrow': 5,
'tubercle': 66,
'curse': 7,
'pauncefote': 2,
'updated': 5,
'gloomier': 4,
'foremost': 17,
'wabash': 2,
'anarchists': 4,
'intermediacy': 2,
'threadbare': 2,
'endeavouring': 9,
'freeholders': 11,
'irreproachably': 3,
'ignominious': 3,
'illuminated': 9,
'galitsyn': 2,
'struthers': 3,
'shuya': 2,
'futile': 16,
'each': 412,
'district': 38,
'acquiesced': 2,
'staircase': 14,
'shamelessly': 2,
'doubter': 2,
'plumage': 3,
'worming': 2,
'militiamen': 30,
'tombstones': 2,
'presupposable': 2,
'notable': 6,
'louise': 5,
'overtook': 17,
'abstraction': 8,
'displeased': 20,
'ranchmen': 2,
'instal': 2,
'kashmir': 3,
'nay': 4,
'wired': 5,
'pencil': 11,
'mustache': 46,
'breast': 87,
'dioxide': 9,
'disappointments': 4,
'impassive': 6,
'though': 651,
'floridas': 7,
'torban': 2,
'combine': 11,
'yawning': 7,
'homeless': 4,
'cinema': 2,
'subjects': 68,
'rib': 9,
'bin': 3,
'cylinders': 18,
'bijou': 2,
'acted': 38,
'accepted': 88,
'attainment': 11,
'mustered': 8,
'audacious': 2,
'respectable': 15,
'bilateral': 10,
'coraco': 2,
'stuffs': 2,
'reheat': 2,
'roberts': 3,
'trenton': 6,
'sharpening': 5,
'component': 6,
'pat': 4,
'animation': 32,
'coincidently': 5,
'cy': 2,
'smoker': 2,
'manes': 3,
'adelaide': 2,
'prayer': 43,
'industries': 65,
'advantageously': 5,
'dissolute': 3,
'tendon': 130,
'barton': 2,
'ablest': 2,
'episode': 12,
'barges': 3,
'sipping': 4,
'inoperative': 2,
'soap': 8,
'padlocks': 2,
'vagaries': 2,
'potemkins': 3,
'blackguard': 5,
'smashed': 11,
'bursitis': 17,
'goes': 61,
'prefix': 3,
'shops': 23,
'basketful': 2,
'stepfather': 22,
'veil': 17,
'adorers': 2,
'overhauled': 6,
'liquors': 3,
'bottoms': 3,
'plastun': 2,
'surest': 4,
'carlton': 5,
'friedland': 6,
'alice': 14,
'unhealthy': 15,
'cannula': 9,
'eleven': 22,
'persuasions': 3,
'cawolla': 2,
'elephants': 2,
'mechanicks': 2,
'kitten': 8,
'promotes': 2,
'venae': 2,
'matt': 2,
'private': 94,
'essential': 93,
'creating': 25,
'exclaiming': 5,
'extent': 100,
'oxidising': 2,
'dessicans': 3,
'uplands': 4,
'tops': 4,
'jerky': 6,
'irregularity': 6,
'recruitment': 3,
'fringes': 17,
'shopkeepers': 7,
'tendencies': 16,
'unconditionally': 3,
'brandy': 16,
'camberwell': 3,
'statue': 9,
'metatarsal': 9,
'measurement': 3,
'enclosures': 2,
'suspecting': 4,
'noses': 7,
'standard': 55,
'inspection': 19,
'enterprising': 6,
'freak': 4,
'liberating': 2,
'ordeal': 3,
'pancras': 2,
'luxury': 9,
'livery': 3,
'anconeus': 2,
'polypus': 4,
'leapt': 3,
'liberally': 2,
'finish': 50,
'previously': 56,
'mccarthy': 38,
'mallet': 6,
'bluestocking': 3,
'conveyance': 8,
'transformer': 2,
'compel': 10,
'blasphemies': 3,
'suggest': 25,
'shares': 4,
'dishonoured': 4,
'hen': 7,
'vols': 28,
'narcotisation': 2,
'speranski': 80,
'cherished': 15,
'overcoat': 27,
'mal*': 2,
'nephroma': 2,
'habeus': 2,
'coward': 9,
'widower': 5,
'extremely': 52,
'resembling': 53,
'understood': 223,
'impetus': 10,
'actinomyces': 10,
'eosinophile': 4,
'pronounce': 10,
'arrangements': 30,
'inevitably': 33,
'hochgeboren': 2,
'crusted': 3,
'weeks': 118,
'slightest': 26,
'fords': 2,
'stimulatingly': 2,
'economically': 3,
'thrice': 9,
'peg': 5,
'adventurous': 4,
'mountainous': 3,
'potch': 2,
'adults': 27,
'kindled': 11,
'have': 3494,
'sedate': 3,
'democrats': 94,
'vaginitis': 2,
'foo': 2,
'headgear': 2,
'gape': 8,
'reassigned': 2,
'incompletely': 2,
'pharmacopoeial': 2,
'feelings': 79,
'phone': 3,
'anger': 60,
'improvisations': 2,
'dethrone': 2,
'toothed': 2,
'sweetish': 2,
'tack': 4,
'unwinding': 3,
'pediculosis': 2,
'overfed': 2,
'rabble': 8,
'opsonins': 4,
'ver': 3,
'postures': 3,
'entertainment': 8,
'unkind': 5,
'lightest': 3,
'undergone': 10,
'persons': 120,
'mention': 47,
'iodism': 2,
'sterne': 2,
'kolocha': 17,
'wecollect': 2,
'asked': 778,
'augury': 2,
'uhlans': 29,
'fist': 9,
'winner': 3,
'praise': 17,
'legislative': 32,
'greediness': 3,
'resembled': 9,
'expense': 34,
'despotic': 2,
'storage': 4,
'league': 54,
'granular': 8,
'differed': 11,
'enlistment': 2,
'authorizing': 17,
'remembers': 7,
'outlays': 4,
'malignant': 89,
'allowed': 87,
'rang': 30,
'wing': 33,
'sped': 2,
'map': 39,
'might': 537,
'disrupting': 2,
'pyrexia': 7,
'besprinkled': 3,
'reddaway': 3,
'intrusions': 2,
'respectively': 11,
'ilagin': 26,
'portray': 2,
'shenkii': 2,
'drilled': 5,
'devilish': 4,
'abate': 6,
'trophic': 21,
'soil': 94,
'smelters': 3,
'people': 900,
'minerals': 9,
'site': 33,
'ceremony': 18,
'rostov': 777,
'occupation': 53,
'whale': 4,
'definitely': 36,
'steam': 31,
'turbinate': 2,
'recollection': 24,
'sports': 3,
'apportioned': 12,
'ripon': 2,
'representations': 4,
'calcanean': 3,
'demonetized': 2,
'cloaks': 10,
'river': 113,
'industrial': 99,
'foreman': 6,
'girt': 4,
'close': 220,
'warne': 2,
'blubberers': 2,
'disruption': 5,
'diligently': 4,
'blamelessly': 2,
'cornwall': 3,
'edinburgh': 26,
'denouncing': 5,
'sasha': 3,
'zeal': 26,
'shouted': 255,
'powerlessness': 2,
'helpless': 23,
'cheapest': 3,
'homely': 9,
'pyosalpynx': 2,
'poorhouse': 2,
'adhesive': 4,
'lumber': 15,
'cawing': 3,
'splashed': 7,
'interphalangeal': 3,
'maintenance': 11,
'pervade': 2,
'beads': 5,
'scarcity': 5,
'anticipate': 5,
'orthodox': 10,
'sponge': 8,
'infer': 4,
'inverted': 4,
'bleak': 5,
'main': 110,
'doddering': 2,
'ligation': 53,
'shiloh': 3,
'haitian': 2,
'hindrance': 12,
'amputate': 5,
'obstructed': 11,
'extensively': 9,
'raised': 213,
'visualized': 2,
'showed': 150,
'awaits': 8,
'specified': 10,
'gush': 2,
'partially': 11,
'calibres': 2,
'kettles': 2,
'easy': 123,
'confirming': 4,
'hordes': 4,
'saved': 52,
'sneered': 3,
'peevishly': 2,
'unexpectedly': 58,
'handedness': 2,
'gigantic': 24,
'bouts': 3,
'hoosier': 2,
'plural': 4,
'disuse': 6,
'flora': 10,
'wriggles': 2,
'reproving': 2,
'unrepaired': 2,
'repose': 8,
'baltic': 2,
'whistle': 29,
'barbarous': 3,
'warp': 3,
'vozdvizhenka': 8,
'intubation': 7,
'dreaminess': 2,
'creek': 4,
'suffrage': 116,
'gay': 36,
'bagovut': 3,
'dropping': 19,
'poultry': 3,
'sentiments': 15,
'bivouacs': 4,
'pobox': 5,
'fuller': 13,
'bombard': 2,
'vanishes': 4,
'independent': 74,
'card': 31,
'sheen': 2,
'descends': 3,
'cerebritis': 2,
'sparrows': 2,
'stab': 9,
'coverlet': 2,
'footmarks': 4,
'homicidal': 3,
'frustration': 2,
'sicca': 4,
'slowly': 134,
'stifling': 3,
'poetry': 11,
'inadvertent': 2,
'faints': 2,
'tudor': 2,
'hancocks': 2,
'postulated': 2,
'delegate': 10,
'ratify': 8,
'rag': 7,
'yankovo': 4,
'staked': 6,
'leprosy': 5,
'cheyenne': 2,
'verbally': 2,
're': 190,
'pedunculated': 14,
'splendidly': 12,
'troubled': 18,
'healed': 17,
'tuning': 2,
'farmer': 28,
'bourbon': 3,
'differently': 26,
'descry': 2,
'filter': 5,
'sob': 20,
'newfoundland': 2,
'flattered': 18,
'lotions': 9,
'refinements': 6,
'overtake': 13,
'offerings': 3,
'kent': 6,
'pimple': 2,
'carousals': 4,
'intrigue': 12,
'salut': 2,
'pliant': 2,
'zum': 2,
'saw': 600,
'load': 9,
'engineers': 5,
'imports': 12,
'indifference': 27,
'are': 3631,
'wringing': 3,
'kidney': 22,
'nun': 4,
'wool': 43,
'utero': 2,
'tag': 3,
'hamlet': 2,
'attain': 51,
'ingested': 2,
'longitudinal': 6,
'detestable': 4,
'inspector': 32,
'hernia': 14,
'circulates': 2,
'adieu': 7,
'annulment': 4,
'tumour': 224,
'elect': 13,
'sidorov': 5,
'eats': 9,
'bond': 27,
'messages': 7,
'surgeon': 44,
'dissecting': 6,
'clarifying': 2,
'stout': 63,
'wrung': 18,
'sincere': 23,
'reverie': 8,
'stampede': 3,
'vindicate': 2,
'cartload': 2,
'semiopen': 2,
'gainful': 2,
'noting': 11,
'marsh': 4,
'interfering': 20,
'sevres': 3,
'charmee': 2,
'cherish': 7,
'beseech': 4,
'transylvania': 4,
'new': 1212,
'weason': 2,
'frontiersmen': 6,
'feverish': 25,
'establish': 46,
'grassy': 2,
'assent': 10,
'muscularly': 4,
'rire': 2,
'mcmaster': 11,
'pineapples': 3,
'maritime': 6,
'debauchery': 6,
'disliked': 21,
'relationships': 3,
'swarmed': 5,
'surpassed': 4,
'discernible': 4,
'thyreoid': 22,
'paddle': 4,
'zoology': 4,
'tenn': 4,
'wood': 89,
'persuasiveness': 3,
'bashful': 3,
'uterine': 12,
'convention': 152,
'unshapely': 2,
'homes': 36,
'bicipital': 3,
'admirable': 15,
'nightshirt': 2,
'fibrin': 17,
'bartenstein': 3,
'guess': 18,
'circlet': 2,
'adventitious': 9,
'indemnify': 6,
'typewriting': 5,
'expunging': 2,
'quand': 6,
'exactions': 2,
'receiving': 55,
'incur': 3,
'giants': 3,
'tearing': 23,
'probing': 4,
'devise': 10,
'hearth': 2,
'placental': 2,
'hammering': 6,
'defeating': 3,
'womanly': 8,
'jewellery': 3,
'kuragins': 4,
'target': 6,
'stevedore': 2,
'safest': 3,
'sounder': 3,
'likes': 9,
'appointments': 12,
'speech': 83,
'quaker': 3,
'antonov': 2,
'proofs': 15,
'boasting': 6,
'wegiment': 3,
'disciplined': 4,
'occupancy': 2,
'flare': 2,
'copenhagen': 3,
'zenger': 4,
'battalions': 27,
'truth': 116,
'research': 37,
'recurvatum': 2,
'notion': 17,
'dishonour': 2,
'glittered': 17,
'kittenish': 2,
'handed': 81,
'acquiescence': 2,
'waggled': 2,
'forged': 5,
'unjust': 11,
'callous': 13,
'mantles': 2,
'election': 120,
'drummed': 2,
'salve': 2,
'agrees': 3,
'discharging': 5,
'cannons': 2,
'impure': 3,
'probable': 28,
'administration': 118,
'considerable': 174,
'forwards': 19,
'waterloo': 10,
'flail': 5,
'claiming': 7,
'phalanges': 12,
'bondage': 16,
'pelageya': 17,
'bigger': 8,
'southern': 197,
'perch': 5,
'enriched': 4,
'metaphysis': 3,
'protection': 64,
'factotum': 2,
'cavalryman': 6,
'radiated': 6,
'cheerfully': 14,
'solid': 42,
'vines': 2,
'scarves': 4,
'quick': 82,
'notabilities': 4,
'him': 5231,
'sixteenth': 12,
'ignoring': 2,
'deserters': 2,
'protege': 5,
'indulgence': 10,
'supreme': 75,
'closes': 7,
'shilling': 5,
'footing': 16,
'mission': 35,
'madame': 44,
'dissatisfied': 35,
'signatures': 4,
'helps': 6,
'garlic': 2,
'wart': 6,
'won': 202,
'overlooked': 14,
'lanfrey': 2,
'dulness': 2,
'unnatural': 38,
'supplier': 3,
'harassed': 4,
'hare': 37,
'slide': 5,
'necessitates': 6,
'conceived': 8,
'mode': 19,
'chant': 2,
'packing': 35,
'tentacles': 2,
'liberality': 2,
'phantasm': 2,
'gloat': 3,
'promptitude': 2,
'merchants': 55,
'whatnots': 2,
'spirited': 13,
'rupia': 5,
'succumbs': 2,
'fondest': 3,
'rusty': 5,
'strapped': 2,
'looking': 490,
'numerical': 6,
'jaws': 19,
'mann': 2,
'smelter': 2,
'becher': 4,
'comprehensive': 5,
'vessel': 138,
'code': 14,
'twopence': 3,
'semilunar': 9,
'elected': 45,
'tone': 167,
'epithelium': 56,
'steve': 2,
'pinckney': 4,
'knapsack': 8,
'kneeling': 9,
'strand': 6,
'solitude': 19,
'gentlemanly': 2,
'thoughts': 126,
'castanet': 2,
'bushy': 10,
'descried': 4,
'aponeurotic': 2,
'surrenders': 2,
'ordered': 149,
'emancipation': 24,
'alley': 6,
'blazers': 3,
'servants': 89,
'rests': 18,
'tooth': 28,
'risks': 15,
'yoke': 6,
'inflammation': 94,
'blonde': 10,
'album': 6,
'duc': 12,
'thorns': 5,
'planter': 19,
'log': 21,
'swarm': 8,
'trocar': 4,
'injured': 56,
'liquor': 14,
'perforations': 7,
'censuring': 2,
'contracture': 29,
'informer': 2,
'switzerland': 9,
'ponies': 2,
'glass': 117,
'burdensome': 5,
'security': 22,
'bitch': 13,
'bacillary': 5,
'transmuted': 2,
'atrocious': 3,
'elects': 2,
'but': 5654,
'muir': 3,
'nikita': 5,
'muddled': 4,
'lifts': 3,
'impresses': 2,
'slim': 14,
'maksim': 2,
'garrulously': 2,
'utterances': 2,
'stammered': 6,
'midsummer': 2,
'trousseau': 5,
'hogs': 3,
'metacarpals': 3,
'blindfold': 5,
'nonmoral': 2,
'moonlight': 19,
'waddling': 6,
'pointing': 89,
'differentiating': 4,
'silly': 14,
'ingest': 2,
'imply': 13,
'enlarges': 3,
'cart': 57,
'differ': 16,
'inflamed': 54,
'bolding': 2,
'shave': 4,
'adroitly': 4,
'served': 64,
'straining': 19,
'fall': 125,
'autocrats': 3,
'unreasonably': 2,
'salter': 2,
'ramshackle': 2,
'eminent': 13,
'molle': 2,
'pained': 8,
'loyal': 21,
'chalk': 14,
'willard': 3,
'idleness': 13,
'canceled': 4,
'inoculation': 23,
'sounding': 7,
'loopholes': 2,
'initial': 20,
'vicar': 3,
'oklahoma': 16,
'precautions': 15,
'commensurable': 2,
'batch': 2,
'push': 20,
'sublimed': 2,
'warned': 19,
'meuse': 4,
'snoring': 7,
'manner': 136,
'this': 4064,
'household': 56,
'millionaires': 6,
'duodenum': 3,
'dixon': 2,
'liberated': 11,
'arrangement': 36,
'soulless': 2,
'reserved': 16,
'essen': 2,
'whirlpool': 2,
'duport': 9,
'hellish': 4,
'engaged': 88,
'apropos': 2,
'retuned': 2,
'cancellation': 2,
'crack': 21,
'morrant': 2,
'pleasurable': 2,
'sunk': 28,
'indorsed': 7,
'wanted': 214,
'integration': 3,
'translations': 2,
'framework': 24,
'skill': 35,
'upper': 131,
'mufti': 2,
'softened': 29,
'callosity': 5,
'thrombosis': 40,
'septum': 4,
'sont': 3,
'sheaf': 2,
'redistribution': 6,
'clymer': 2,
'fatal': 64,
'laid': 187,
'nares': 2,
'archway': 2,
'deterred': 2,
'oscillates': 2,
'ineffective': 2,
'vacant': 11,
'confide': 7,
'nominal': 9,
'hiram': 2,
'resected': 12,
'unwanted': 2,
'pattern': 8,
'cicatricial': 42,
'bowl': 7,
'nor': 281,
'wobbly': 3,
'sarcomas': 9,
'solder': 2,
'laceration': 10,
'illustrating': 6,
'psammoma': 3,
'stuck': 21,
'perversion': 2,
'jewels': 6,
'country': 424,
'enforce': 30,
'battlefields': 2,
'speechless': 2,
'ruin': 49,
'grassland': 2,
'mistrusting': 2,
'bench': 27,
'scurrying': 2,
'rhetor': 25,
'morton': 2,
'suggestiveness': 2,
'remorseless': 2,
'divert': 7,
'melyukovs': 8,
'obviates': 2,
'cooperative': 10,
'started': 97,
'employe': 3,
'perfidiousness': 2,
'replied': 321,
'imagined': 49,
'marvel': 2,
'pitiable': 8,
'genteel': 2,
'unlocked': 9,
'independence': 152,
'appealed': 14,
'flexible': 6,
'xxiv': 9,
'authority': 101,
'frilled': 2,
'thoroughbred': 6,
'accuser': 2,
'hesitating': 17,
'pork': 4,
'voltaires': 2,
'bengal': 3,
'tends': 49,
'wastage': 2,
'shrill': 14,
'profunda': 4,
'thanksgiving': 7,
'enclose': 2,
'seedy': 3,
'furs': 11,
'splash': 5,
'supplementary': 4,
'sedately': 3,
'certainly': 120,
'puppet': 4,
'injustice': 14,
'lanolin': 4,
'thicknesses': 2,
'excuses': 7,
'faces': 163,
'fourteenth': 28,
'trimming': 2,
'prick': 6,
'economic': 121,
'stands': 20,
'programming': 2,
'princes': 12,
'lottery': 2,
'exsiccated': 2,
'parceled': 2,
'musculo': 9,
'standstill': 3,
'consolation': 19,
'uncle': 136,
'federalism': 2,
'intravenous': 4,
'assumption': 32,
'doors': 48,
'lisa': 2,
'disregard': 7,
'appendix': 12,
'myoma': 9,
'cost': 66,
'parrot': 6,
'manoeuvre': 2,
'achtung': 2,
'acorn': 3,
'aggrieved': 4,
'cutlery': 2,
'glorious': 12,
'rotten': 9,
'denoted': 2,
'muster': 4,
'hug': 2,
'eccentricity': 3,
'susquehanna': 4,
'partake': 4,
'nicely': 10,
'thing': 304,
'wages': 51,
'dislike': 10,
'beams': 10,
'spree': 3,
'antagonizing': 2,
'advises': 4,
'snuffling': 2,
'rods': 6,
'borisov': 2,
'mayor': 16,
'mathematics': 12,
'invent': 11,
'teaching': 19,
'girdle': 4,
'averting': 4,
'elijah': 2,
'platelets': 2,
'uvula': 2,
'mumbling': 5,
'retreat': 95,
'fwashing': 2,
'bar': 26,
'scudding': 2,
'nowadays': 19,
'loftiness': 3,
'ceded': 9,
'delirium': 35,
'wiring': 3,
'centre': 51,
'frightfully': 2,
'wag': 6,
'sockets': 2,
'fluctuates': 2,
'concealment': 4,
'intima': 11,
'burnt': 9,
'tiding': 3,
'osteomas': 4,
'tug': 5,
'vis': 2,
'fabrication': 2,
'powers': 150,
'sweeps': 2,
'supervene': 7,
'meal': 16,
'briskly': 20,
'reinforce': 3,
'devriez': 2,
'youngster': 5,
'coast': 41,
'sameness': 2,
'about': 1498,
'whither': 9,
'tolstoy': 14,
'certain': 362,
'paunch': 2,
'laurel': 4,
'stamping': 4,
'incorporate': 4,
...})