《Python 自然语言处理》学习笔记--第二章：获得文本语料和词汇资源

获取文本语料库

古腾堡语料库

>>> import nltk
>>> nltk.corpus.gutenberg.fileids()
['austen-emma.txt', 'austen-persuasion.txt', 'austen-sense.txt', 'bible-kjv.txt', 'blake-poems.txt', 'bryant-stories.txt', 'burgess-busterbrown.txt', 'carroll-alice.txt', 'chesterton-ball.txt', 'chesterton-brown.txt', 'chesterton-thursday.txt', 'edgeworth-parents.txt', 'melville-moby_dick.txt', 'milton-paradise.txt', 'shakespeare-caesar.txt', 'shakespeare-hamlet.txt', 'shakespeare-macbeth.txt', 'whitman-leaves.txt']
>>> emma = nltk.corpus.gutenberg.words('austen-emma.txt')
#另一种版本的import，简洁
>>>from nltk.corpus import gutenberg
>>> gutenberg.fileids()
['austen-emma.txt', 'austen-persuasion.txt', 'austen-sense.txt', 'bible-kjv.txt', 'blake-poems.txt', 'bryant-stories.txt', 'burgess-busterbrown.txt', 'carroll-alice.txt', 'chesterton-ball.txt', 'chesterton-brown.txt', 'chesterton-thursday.txt', 'edgeworth-parents.txt', 'melville-moby_dick.txt', 'milton-paradise.txt', 'shakespeare-caesar.txt', 'shakespeare-hamlet.txt', 'shakespeare-macbeth.txt', 'whitman-leaves.txt']
>>> emma = gutenberg.words('austen-emma.txt')

统计平均词长，平均句子长度和每个词出现的平均次数（词汇多样性得分）
>>> for fileid in gutenberg.fileids():
#raw()提供了没有进行过语言学处理的文件内容，因此len是包含了空格的词汇个数
...     num_chars = len(gutenberg.raw(fileid))
...     num_words = len(gutenberg.words(fileid))
#sent()把文本划成句子
...     num_sents = len(gutenberg.sents(fileid))
...     num_vocab = len(set([w.lower() for w in gutenberg.words(fileid)]))
...     print (int(num_chars/num_words),int(num_words/num_sents),int(num_words/num_vocab),fileid)
...
4 24 26 austen-emma.txt
4 26 16 austen-persuasion.txt
4 28 22 austen-sense.txt
4 33 79 bible-kjv.txt
4 19 5 blake-poems.txt
4 19 14 bryant-stories.txt
4 17 12 burgess-busterbrown.txt
4 20 12 carroll-alice.txt
4 20 11 chesterton-ball.txt
4 22 11 chesterton-brown.txt
4 18 10 chesterton-thursday.txt
4 20 24 edgeworth-parents.txt
4 25 15 melville-moby_dick.txt
4 52 10 milton-paradise.txt
4 11 8 shakespeare-caesar.txt
4 12 7 shakespeare-hamlet.txt
4 12 6 shakespeare-macbeth.txt
4 36 12 whitman-leaves.txt
>>> macbeth_sentences = gutenberg.sents('shakespeare-macbeth.txt')
>>> macbeth_sentences[1037]
['Good', 'night', ',', 'and', 'better', 'health', 'Attend', 'his', 'Maiesty']
>>> longest_len = max([len(s) for s in macbeth_sentences])
>>> [s for s in macbeth_sentences if len(s)==longest_len]
[['Doubtfull', 'it', 'stood', ',', 'As', 'two', 'spent', 'Swimmers', ',', 'that', 'doe', 'cling', 'together', ',', 'And', 'choake', 'their', 'Art', ':', 'The', 'mercilesse', 'Macdonwald', '(',...]]

网络和聊天文本

>>> from nltk.corpus import webtext
>>> for fileid in webtext.fileids():
...     print(fileid, webtext.raw(fileid)[:65],'...')
...
firefox.txt Cookie Manager: "Don't allow sites that set removed cookies to se ...
grail.txt SCENE 1: [wind] [clop clop clop]
KING ARTHUR: Whoa there!  [clop ...
overheard.txt White guy: So, do you have any plans for this evening?
Asian girl ...
pirates.txt PIRATES OF THE CARRIBEAN: DEAD MAN'S CHEST, by Ted Elliott & Terr ...
singles.txt 25 SEXY MALE, seeks attrac older single lady, for discreet encoun ...
wine.txt Lovely delicate, fragrant Rhone wine. Polished leather and strawb ...

>>> from nltk.corpus import nps_chat
>>> chatroom = nps_chat.posts('10-19-20s_706posts.xml')
>>> chatroom[123]
['i', 'do', "n't", 'want', 'hot', 'pics', 'of', 'a', 'female', ',', 'I', 'can', 'look', 'in', 'a', 'mirror', '.']

布朗语料库

>>> from nltk.corpus import brown
#文体
>>> brown.categories()
['adventure', 'belles_lettres', 'editorial', 'fiction', 'government', 'hobbies', 'humor', 'learned', 'lore', 'mystery', 'news', 'religion', 'reviews', 'romance', 'science_fiction']
>>> brown.words(categories='news')
['The', 'Fulton', 'County', 'Grand', 'Jury', 'said', ...]
#文件名
>>> brown.words(fileids=['cg22'])
['Does', 'our', 'society', 'have', 'a', 'runaway', ',', ...]
>>> brown.sents(categories=['news','editorial',])
[['The', 'Fulton', 'County', 'Grand', 'Jury', 'said', 'Friday', 'an', 'investigation', 'of', "Atlanta's", 'recent', 'primary', 'election', 'produced', '``', 'no', 'evidence', "''", 'that', 'any', 'irregularities', 'took', 'place', '.'], ['The', 'jury', 'further', 'said', 'in', 'term-end', 'presentments', 'that', 'the', 'City', 'Executive', 'Committee', ',', 'which', 'had', 'over-all', 'charge', 'of', 'the', 'election', ',', '``', 'deserves', 'the', 'praise', 'and', 'thanks', 'of', 'the', 'City', 'of', 'Atlanta', "''", 'for', 'the', 'manner', 'in', 'which', 'the', 'election', 'was', 'conducted', '.'], ...]
>>> brown.sents(categories=['news','editorial','reviews'])
[['The', 'Fulton', 'County', 'Grand', 'Jury', 'said', 'Friday', 'an', 'investigation', 'of', "Atlanta's", 'recent', 'primary', 'election', 'produced', '``', 'no', 'evidence', "''", 'that', 'any', 'irregularities', 'took', 'place', '.'], ['The', 'jury', 'further', 'said', 'in', 'term-end', 'presentments', 'that', 'the', 'City', 'Executive', 'Committee', ',', 'which', 'had', 'over-all', 'charge', 'of', 'the', 'election', ',', '``', 'deserves', 'the', 'praise', 'and', 'thanks', 'of', 'the', 'City', 'of', 'Atlanta', "''", 'for', 'the', 'manner', 'in', 'which', 'the', 'election', 'was', 'conducted', '.'], ...]

#研究情态动词
>>> news_text = brown.words(categories='news')
>>> fdist = nltk.FreqDist([w.lower() for w in news_text])
>>> modals = ['can','could','may','might','must','will']
>>> for m in modals:
...     print(m+':',fdist[m])
...
can: 94
could: 87
may: 93
might: 38
must: 53
will: 389

路透社语料库

>>> from nltk.corpus import reuters
>>> reuters.fileids()
['test/14826', 'test/14828', 'test/14829', 'test/14832', 'test/14833', 'test/14839', 'test/14840', 'test/14841', 'test/14842', 'test/14843', 'test/14844',...]
#和布朗语料库不同，是有重叠的
>>> reuters.categories()
['acq', 'alum', 'barley', 'bop', 'carcass', 'castor-oil', 'cocoa', 'coconut', 'coconut-oil', ...]
>>> reuters.categories('training/9865')
['barley', 'corn', 'grain', 'wheat']
>>> reuters.categories(['training/9865','training/9880'])
['barley', 'corn', 'grain', 'money-fx', 'wheat']
>>> reuters.fileids('barley')
['test/15618', 'test/15649', 'test/15676', 'test/15728', 'test/15871', 'test/15875', 'test/15952', ...]
>>> reuters.fileids(['barley','corn'])
['test/14832', 'test/14858', 'test/15033', 'test/15043', 'test/15106', 'test/15287', 'test/15341', 'test/15618', 'test/15648', 'test/15649', 'test/15676', 'test/15686', ...]

#开始几个词是标题，以大写字母存储
>>> reuters.words(['training/9865','training/9880'])[:14]
['FRENCH', 'FREE', 'MARKET', 'CEREAL', 'EXPORT', 'BIDS', 'DETAILED', 'French', 'operators', 'have', 'requested', 'licences', 'to', 'export']
>>> reuters.words(categories=['barley','corn'])
['THAI', 'TRADE', 'DEFICIT', 'WIDENS', 'IN', 'FIRST', ...]

就职演说语料库

>>> from nltk.corpus import inaugural
>>> inaugural.fileids()
['1789-Washington.txt', '1793-Washington.txt', '1797-Adams.txt', '1801-Jefferson.txt', '1805-Jefferson.txt', ...]
>>> [fileid[:4] for fileid in inaugural.fileids()]
['1789', '1793', '1797', '1801', '1805', '1809', '1813', '1817', '1821', '1825', '1829',...]

#研究america和citizen随时间推移的使用情况
>>> cfd=nltk.ConditionalFreqDist(
...          (target,fileid[:4])
...          for fileid in inaugural.fileids()
...          for w in inaugural.words(fileid)
...          for target in ['america','citizen']
...          if w.lower().startswith(target))
>>> cfd.plot()

其他语言语料库

#人权宣言中不同语言版本字长差异
>>> from nltk.corpus import udhr
>>> languages = ['Chickasaw','English','German_Deutsch','Greenlandic_Inuktikut','Hungarian_Magyar','Ibibio_Efik']
>>> cfd = nltk.ConditionalFreqDist(
...       (lang, len(word))
...       for lang in languages
...       for word in udhr.words(lang + '-Latin1'))
>>> cfd.plot(cumulative=True)

文本语料库的结构

>>> raw = gutenberg.raw("burgess-busterbrown.txt")
>>> raw[1:20]
'The Adventures of B'
>>> words=gutenberg.words("burgess-busterbrown.txt")
>>> words[1:20]
['The', 'Adventures', 'of', 'Buster', 'Bear', 'by', 'Thornton', 'W', '.', 'Burgess', '1920', ']', 'I', 'BUSTER', 'BEAR', 'GOES', 'FISHING', 'Buster', 'Bear']
>>> sents = gutenberg.sents("burgess-busterbrown.txt")
>>> sents[1:5]
[['I'], ['BUSTER', 'BEAR', 'GOES', 'FISHING'], ['Buster', 'Bear', 'yawned', 'as', 'he', 'lay', 'on', 'his', 'comfortable', 'bed', 'of', 'leaves', 'and', 'watched', 'the', 'first', 'early', 'morning', 'sunbeams', 'creeping', 'through', 'the', 'Green', 'Forest', 'to', 'chase', 'out', 'the', 'Black', 'Shadows', '.'], ['Once', 'more', 'he', 'yawned', ',', 'and', 'slowly', 'got', 'to', 'his', 'feet', 'and', 'shook', 'himself', '.']]

按文体计数词汇

>>> from nltk.corpus import brown
>>> cfd = nltk.ConditionalFreqDist(
...       (genre, word)
...       for genre in brown.categories()
...       for word in brown.words(categories = genre))
#只看新闻和言情两种文体，对每种文体遍历每个词产生文体与词的配对
>>> genre_word = [(genre,word)
...              for genre in ['news','romance']
...              for word in brown.words(categories=genre)]
>>> len(genre_word)
170576
>>> genre_word[:4]
[('news', 'The'), ('news', 'Fulton'), ('news', 'County'), ('news', 'Grand')]
>>> genre_word[-4:]
[('romance', 'afraid'), ('romance', 'not'), ('romance', "''"), ('romance', '.')]
>>> cfd = nltk.ConditionalFreqDist(genre_word)
>>> cfd
<ConditionalFreqDist with 2 conditions>
>>> cfd.conditions()
['news', 'romance']
>>> cfd['news']
FreqDist({'the': 5580, ',': 5188, '.': 4030, 'of': 2849, 'and': 2146, 'to': 2116, 'a': 1993, 'in': 1893, 'for': 943, 'The': 806, ...})
>>> cfd['romance']
FreqDist({',': 3899, '.': 3736, 'the': 2758, 'and': 1776, 'to': 1502, 'a': 1335, 'of': 1186, '``': 1045, "''": 1044, 'was': 993, ...})
>>> list(cfd['romance'])
['They', 'neither', 'liked', 'nor', 'disliked', 'the', 'Old', 'Man', '.', 'To', 'them', 'he', 'could', 'have', 'been', 'broken', 'bell', 'in', 'church', 'tower',...]
>>> cfd['romance']['could']
193

使用双连词生成随机文本

#构造一个条件频率分布来记录哪些词汇最有可能跟在给定词后面
>>> def generate_model(cfdist, word, num=15):
...     for i in range(num):
...         print (word),
...         word = cfdist[word].max()
...
>>>
>>> text = nltk.corpus.genesis.words('english-kjv.txt')
>>> bigrams = nltk.bigrams(text)
>>> cfd = nltk.ConditionalFreqDist(bigrams)
>>> print(cfd['living'])
<FreqDist with 6 samples and 16 outcomes>
>>> print(list(cfd['living']))
['creature', 'thing', 'soul', '.', 'substance', ',']
>>> generate_model(cfd,'living')
living
creature
that
he
said
,
and
the
land
of
the
land
of
the
land

词汇列表语料库

#意在删除所有在现有的词汇列表中出现的元素，留下罕见或者拼写错误
>>> def unusual_words(text):
...     text_vocab = set(w.lower() for w in text if w.isalpha())
...     english_vocab = set(w.lower() for w in nltk.corpus.words.words())
...     unusual = text_vocab.difference(english_vocab)
...     return sorted(unusual)
...
#没什么用，连普通词汇的复数形式也被选了出来。
>>> unusual_words(nltk.corpus.gutenberg.words('austen-sense.txt'))
['abbeyland', 'abhorred', 'abilities', 'abounded', 'abridgement', 'abused', 'abuses', 'accents', 'accepting', 'accommodations', 'accompanied',...]
>>> unusual_words(nltk.corpus.nps_chat.words())
['aaaaaaaaaaaaaaaaa', 'aaahhhh', 'abortions', 'abou', 'abourted', 'abs', 'ack', 'acros', 'actualy', 'adams', 'adds', 'adduser', 'adjusts', ...]

停用词语料库

>>> from nltk.corpus import stopwords
>>> stopwords.words('english')
['i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've", "you'll", "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', ...]
#计算文本中没有在停用词列表中的词的比例
>>> def content_fraction(text):
...     stopwords = nltk.corpus.stopwords.words('english')
...     content = [w for w in text if w.lower() not in stopwords]
...     return len(content)/len(text)
...
>>> content_fraction(nltk.corpus.reuters.words())
0.735240435097661

字母拼词游戏

>>> puzzle_letters = nltk.FreqDist('egivrvonl')
>>> obligatory = 'r'
>>> wordlist = nltk.corpus.words.words()
>>> [w for w in wordlist if len(w)>=6
...                         and obligatory in w
...                         and nltk.FreqDist(w) <= puzzle_letters]
['glover', 'gorlin', 'govern', 'grovel', 'ignore', 'involver', 'lienor', 'linger', 'longer', 'lovering', 'noiler', 'overling', 'region', 'renvoi', 'revolving', 'ringle', 'roving', 'violer', 'virole']

姓名语料库

>>> names = nltk.corpus.names
>>> names.fileids()
['female.txt', 'male.txt']
>>> male_names=names.words('male.txt')
>>> female_names=names.words('female.txt')
>>> [w for w in male_names if w in female_names]
['Abbey', 'Abbie', 'Abby', 'Addie', 'Adrian', 'Adrien', 'Ajay', 'Alex', 'Alexis', 'Alfie', 'Ali', 'Alix', 'Allie', 'Allyn', 'Andie', 'Andrea',...]

#绘制男性和女性名字的结尾字母
>>> cfd = nltk.ConditionalFreqDist(
...       (fileid, name[-1])
...       for fileid in names.fileids()
...       for name in names.words(fileid)
...       )
>>> cfd.plot()

发音词典

#对每个词提供了语音代码--音素，每个条目由两部分组成
>>> entries = nltk.corpus.cmudict.entries()
>>> len(entries)
133737
>>> for entry in entries[39943:39951]:
...     print (entry)
...
('explorer', ['IH0', 'K', 'S', 'P', 'L', 'AO1', 'R', 'ER0'])
('explorers', ['IH0', 'K', 'S', 'P', 'L', 'AO1', 'R', 'ER0', 'Z'])
('explores', ['IH0', 'K', 'S', 'P', 'L', 'AO1', 'R', 'Z'])
('exploring', ['IH0', 'K', 'S', 'P', 'L', 'AO1', 'R', 'IH0', 'NG'])
('explosion', ['IH0', 'K', 'S', 'P', 'L', 'OW1', 'ZH', 'AH0', 'N'])
('explosions', ['IH0', 'K', 'S', 'P', 'L', 'OW1', 'ZH', 'AH0', 'N', 'Z'])
('explosive', ['IH0', 'K', 'S', 'P', 'L', 'OW1', 'S', 'IH0', 'V'])
('explosively', ['EH2', 'K', 'S', 'P', 'L', 'OW1', 'S', 'IH0', 'V', 'L', 'IY0'])
>> for word, pron in entries:
...     if len(pron) == 3:
...        ph1,ph2,ph3 = pron
...        if ph1 == 'P' and ph3 == 'T':
...           print (word,ph2)
...
pait EY1
pat AE1
pate EY1
patt AE1
peart ER1
peat IY1
peet IY1
peete IY1
pert ER1
...
>>> syllable = ['N','IH0','K','S']
>>> [word for word, pron in entries if pron[-4:]==syllable]
["atlantic's", 'audiotronics', 'avionics', 'beatniks', 'calisthenics', 'centronics', 'chamonix', 'chetniks', "clinic's", 'clinics', 'conics',...]

#找p开头的三音素词
>>> p3 = [(pron[0]+'-'+pron[2],word)
...        for (word,pron) in entries
...        if pron[0] == 'P' and len(pron) == 3]
>>> cfd = nltk.ConditionalFreqDist(p3)
>>> for template in cfd.conditions():
...     if len(cfd[template])>10:
...        words = cfd[template].keys()
...        wordlist = ''.join(words)
...        print (template,wordlist[:70]+"...")
...
P-P paappaapepappapepapppauppeeppeppippipepipppooppoppopepopppoppepup...
P-R paarpairparpareparrpearpeerpierpoorpooreporporeporrpour...
P-K pacpackpaekpaikpakpakepaquepeakpeakepechpeckpeekpercperkpicpickpikpike...
P-S pacepasspastspeacepearsepeaseperceperspersepescepiecepissposposspostsp...
P-L pahlpailpaillepalpalepallpaulpaulepaullpealpealepearlpearlepeelpeelepe...
P-N paignpainpainepanpanepawnpaynepeinepenpenhpennpinpinepinnponpoonpunpyn...
P-Z paispaizpao'spaspausepawspayspazpeaspeasepei'sperzpezpiespoe'spoisepos...
P-T paitpatpatepattpeartpeatpeetpeetepertpetpetepettpietpiettepitpittpotpo...
P-CH patchpautschpeachperchpetschpetschepichepiechpietschpitchpitschpoachpo...
P-UW1 perupeughpewplewplueprewpruprueprughpshewpugh...
>>> text = ['natural','language','processing']
>>> prondict = nltk.corpus.cmudict.dict()
>>> [ph for w in text for ph in prondict[w][0]]
['N', 'AE1', 'CH', 'ER0', 'AH0', 'L', 'L', 'AE1', 'NG', 'G', 'W', 'AH0', 'JH', 'P', 'R', 'AA1', 'S', 'EH0', 'S', 'IH0', 'NG']

比较词典

>>> from nltk.corpus import swadesh
>>> swadesh.fileids()
['be', 'bg', 'bs', 'ca', 'cs', 'cu', 'de', 'en', 'es', 'fr', 'hr', 'it', 'la', 'mk', 'nl', 'pl', 'pt', 'ro', 'ru', 'sk', 'sl', 'sr', 'sw', 'uk']
>>> swadesh.words('en')
['I', 'you (singular), thou', 'he', 'we', 'you (plural)', 'they', 'this', 'that', 'here', 'there', 'who', 'what', 'where', 'when', 'how', 'not', 'all', 'many', 'some', 'few', ...]
#通过entries()方法指定一个语言链来访问多语言中的同源词
>>> fr2en = swadesh.entries(['fr','en'])
>>> fr2en
[('je', 'I'), ('tu, vous', 'you (singular), thou'), ('il', 'he'), ('nous', 'we'), ('vous', 'you (plural)'), ('ils, elles', 'they'), ('ceci', 'this'), ('cela', 'that'), ('ici', 'here'), ...]
>>> translate = dict(fr2en)
>>> translate['chien']
'dog'
>>> translate['jeter']
'throw'
#将德语-英语和西班牙语-英语相互转换成一个词典，更新翻译
>>> de2en = swadesh.entries(['de','en'])
>>> es2en = swadesh.entries(['es','en'])
>>> translate.update(dict(de2en))
>>> translate.update(dict(es2en))
>>> translate['Hund']
'dog'
>>> translate['perro']
'dog'
#比较日耳曼语和拉丁语族的不同
>>> languages = ['en','de','nl','es','fr','pt','la']
>>> for i in [139,140,141,142]:
...     print (swadesh.entries(languages)[i])
...
('say', 'sagen', 'zeggen', 'decir', 'dire', 'dizer', 'dicere')
('sing', 'singen', 'zingen', 'cantar', 'chanter', 'cantar', 'canere')
('play', 'spielen', 'spelen', 'jugar', 'jouer', 'jogar, brincar', 'ludere')
('float', 'schweben', 'zweven', 'flotar', 'flotter', 'flutuar, boiar', 'fluctuare')

Wordnet

#同义词
>>> from nltk.corpus import wordnet as wn
>>> wn.synsets('motorcar')
[Synset('car.n.01')]
#motorcar被定义为car的第一个名词意义，car.n.01被称为synset或同义词集
#此处报错
>>> wn.synset('car.n.01').lemma_names
<bound method Synset.lemma_names of Synset('car.n.01')

修改方式

>>> wn.synset('car.n.01').lemma_names()
['car', 'auto', 'automobile', 'machine', 'motorcar']
>>> print(wn.synset('car.n.01').definition())
a motor vehicle with four wheels; usually propelled by an internal combustion engine

>>> wn.synset('car.n.01').examples()
['he needs a car to get to work']
#将词语进行标注，这种同义词集和词的配对叫做词条
>>> wn.synset('car.n.01').lemmas()
[Lemma('car.n.01.car'), Lemma('car.n.01.auto'), Lemma('car.n.01.automobile'), Lemma('car.n.01.machine'), Lemma('car.n.01.motorcar')]
>>> wn.lemma('car.n.01.automobile')
Lemma('car.n.01.automobile')
>> wn.lemma('car.n.01.automobile').synset()
Synset('car.n.01')
>>> wn.lemma('car.n.01.automobile').name()
'automobile'
>>> wn.synsets('car')
[Synset('car.n.01'), Synset('car.n.02'), Synset('car.n.03'), Synset('car.n.04'), Synset('cable_car.n.01')]

报错与修改方式

>>> for synset in wn.synsets('car'):
...     print (synset.lemma_names)
...
<bound method Synset.lemma_names of Synset('car.n.01')>
<bound method Synset.lemma_names of Synset('car.n.02')>
<bound method Synset.lemma_names of Synset('car.n.03')>
<bound method Synset.lemma_names of Synset('car.n.04')>
<bound method Synset.lemma_names of Synset('cable_car.n.01')>
>>> for synset in wn.synsets('car'):
...     print (synset.lemma_names())
...
['car', 'auto', 'automobile', 'machine', 'motorcar']
['car', 'railcar', 'railway_car', 'railroad_car']
['car', 'gondola']
['car', 'elevator_car']
['cable_car', 'car']

>>> wn.lemmas('car')
[Lemma('car.n.01.car'), Lemma('car.n.02.car'), Lemma('car.n.03.car'), Lemma('car.n.04.car'), Lemma('cable_car.n.01.car')]
>>> motorcar = wn.synset('car.n.01')
>>> types_of_motorcar = motorcar.hyponyms()
>>> types_of_motorcar[26]
Synset('stanley_steamer.n.01')

WordNet的层次结构
报错

#下位词
>>> sorted([lemma.name for synset in types_of_motorcar for lemma in synset.lemmas])
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "<stdin>", line 1, in <listcomp>
TypeError: 'method' object is not iterable

修改方式

>>> sorted([lemma.name() for synset in types_of_motorcar for lemma in synset.lemmas()])
['Model_T', 'S.U.V.', 'SUV', 'Stanley_Steamer', 'ambulance', 'beach_waggon', ...]

>>> motorcar.hypernyms()
[Synset('motor_vehicle.n.01')]
>>> paths = motorcar.hypernym_paths()
>>> len(paths)
2

#报错
>>> [synset.name for synset in paths[0]]
[<bound method Synset.name of Synset('entity.n.01')>, <bound method Synset.name of Synset('physical_entity.n.01')>, <bound method Synset.name of Synset('object.n.01')>, <bound method Synset.name of Synset('whole.n.02')>, <bound method Synset.name of Synset('artifact.n.01')>, <bound method Synset.name of Synset('instrumentality.n.03')>, <bound method Synset.name of Synset('container.n.01')>, <bound method Synset.name of Synset('wheeled_vehicle.n.01')>, <bound method Synset.name of Synset('self-propelled_vehicle.n.01')>, <bound method Synset.name of Synset('motor_vehicle.n.01')>, <bound method Synset.name of Synset('car.n.01')>]
#修改方式
>>> [synset.name() for synset in paths[0]]
['entity.n.01', 'physical_entity.n.01', 'object.n.01', 'whole.n.02', 'artifact.n.01', 'instrumentality.n.03', 'container.n.01', 'wheeled_vehicle.n.01', 'self-propelled_vehicle.n.01', 'motor_vehicle.n.01', 'car.n.01']
#用如下方式得到一个最一般的上位（或者根上位）同义词集
>>> motorcar.root_hypernyms()
[Synset('entity.n.01')]

更多的词汇关系

#WordNet网络的一个漫游方式是从物品到部分或者包含其中的东西。
>>> wn.synset('tree.n.01').part_meronyms()
[Synset('burl.n.02'), Synset('crown.n.07'), Synset('limb.n.02'), Synset('stump.n.01'), Synset('trunk.n.01')]
#一棵树的实质是包括心材和边材组成的
>>> wn.synset('tree.n.01').substance_meronyms()
[Synset('heartwood.n.01'), Synset('sapwood.n.01')]
#树木的集合形成了森林
>>> wn.synset('tree.n.01').member_holonyms()
[Synset('forest.n.01')]

报错

>>> for synset in wn.synsets('mint',wn.NOUN):
...     print(synset.name + ':',synset.definition)
...
Traceback (most recent call last):
  File "<stdin>", line 2, in <module>
TypeError: unsupported operand type(s) for +: 'method' and 'str'

修改方式

>>> for synset in wn.synsets('mint',wn.NOUN):
...     print(synset.name() + ':',synset.definition())
...
batch.n.02: (often followed by `of') a large number or amount or extent
mint.n.02: any north temperate plant of the genus Mentha with aromatic leaves and small mauve flowers
mint.n.03: any member of the mint family of plants
mint.n.04: the leaves of a mint plant used fresh or candied
mint.n.05: a candy that is flavored with a mint oil
mint.n.06: a plant where money is coined by authority of the government

>>> wn.synset('mint.n.04').part_holonyms()
[Synset('mint.n.02')]
>>> wn.synset('mint.n.04').substance_holonyms()
[Synset('mint.n.05')]
#蕴含
>>> wn.synset('walk.v.01').entailments()
[Synset('step.v.01')]
>>> wn.synset('eat.v.01').entailments()
[Synset('chew.v.01'), Synset('swallow.v.01')]
>>> wn.synset('tease.v.03').entailments()
[Synset('arouse.v.07'), Synset('disappoint.v.01')]
#反义词
>>> wn.lemma('supply.n.02.supply').antonyms()
[Lemma('demand.n.02.demand')]
>>> wn.lemma('rush.v.01.rush').antonyms()
[Lemma('linger.v.04.linger')]
>>> wn.lemma('horizontal.a.01.horizontal').antonyms()
[Lemma('vertical.a.01.vertical'), Lemma('inclined.a.02.inclined')]
>>> wn.lemma('staccato.r.01.staccato').antonyms()
[Lemma('legato.r.01.legato')]

语义相似度

>>> right = wn.synset('right_whale.n.01')
>>> orca = wn.synset('orca.n.01')
>>> minke = wn.synset('minke_whale.n.01')
>>> tortoise = wn.synset('tortoise.n.01')
>>> novel = wn.synset('novel.n.01')
>>> right.lowest_common_hypernyms(minke)
[Synset('baleen_whale.n.01')]
>>> right.lowest_common_hypernyms(orca)
[Synset('whale.n.02')]
>>> right.lowest_common_hypernyms(tortoise)
[Synset('vertebrate.n.01')]
>>> right.lowest_common_hypernyms(novel)
[Synset('entity.n.01')]
>>> wn.synset('baleen_whale.n.01').min_depth()
14
>>> wn.synset('whale.n.02').min_depth()
13
>>> wn.synset('vertebrate.n.01').min_depth()
8
>>> wn.synset('entity.n.01').min_depth()
0
>>> right.path_similarity(minke)
0.25
>>> right.path_similarity(orca)
0.16666666666666666
>>> right.path_similarity(tortoise)
0.07692307692307693
>>> right.path_similarity(novel)
0.043478260869565216