【NLP】Python NLTK获取文本语料和词汇资源

>>> import nltk
>>> nltk.corpus.gutenberg.fileids()

>>> 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']

>>> persuasion=nltk.corpus.gutenberg.words("austen-persuasion.txt")
>>> len(persuasion)
98171
>>> persuasion[:200]
['[', 'Persuasion', 'by', 'Jane', 'Austen', '1818', ...]

num_char = len(gutenberg.raw(fileid))  # 原始文本的长度，包括空格、符号等
	num_words = len(gutenberg.words(fileid)) #词的数量
	num_sents = len(gutenberg.sents(fileid)) #句子的数量
	num_vocab = len(set([w.lower() for w in gutenberg.words(fileid)])) #文本的尺寸
        # 打印出平均词长（包括一个空白符号，如下词长是3）、平均句子长度、和文本中每个词出现的平均次数
	print(int(num_char/num_words),int(num_words/num_sents),int(num_words/num_vocab),fileid)

>>> from nltk.corpus import webtext
>>> for fileid in webtext.fileids():
	print(fileid,webtext.raw(fileid))

>>> for fileid in webtext.fileids():
	print(fileid,len(webtext.words(fileid)),len(webtext.raw(fileid)),len(webtext.sents(fileid)),webtext.encoding(fileid))
 
firefox.txt 102457 564601 1142 ISO-8859-2
grail.txt 16967 65003 1881 ISO-8859-2
overheard.txt 218413 830118 17936 ISO-8859-2
pirates.txt 22679 95368 1469 ISO-8859-2
singles.txt 4867 21302 316 ISO-8859-2
wine.txt 31350 149772 2984 ISO-8859-2

>>> 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', '.']

>>> from nltk.corpus import brown
>>> brown.categories()
['adventure', 'belles_lettres', 'editorial', 'fiction', 'government', 'hobbies', 'humor', 'learned', 'lore', 'mystery', 'news', 'religion', 'reviews', 'romance', 'science_fiction']

>>> import nltk
>>> from nltk.corpus import brown
>>> new_texts=brown.words(categories='news')
>>> fdist=nltk.FreqDist([w.lower() for w in new_texts])
>>> 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

>>> cfd=nltk.ConditionalFreqDist((genre,word) for genre in brown.categories() for word in brown.words(categories=genre))
>>> genres=['news','religion','hobbies','science_fiction','romance','humor']
>>> modals=['can','could','may','might','must','will']
>>> cfd.tabulate(condition=genres,samples=modals)

>>> from nltk.corpus import  reuters
>>> print(reuters.fileids()[:500])

>>> len(reuters.fileids())
10788

>>> len(reuters.categories())
90

>>> 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', 'test/17767', 'test/17769', 'test/18024', 'test/18263', 'test/18908', 'test/19275', 'test/19668', 'training/10175', 'training/1067', 'training/11208', 'training/11316', 'training/11885', 'training/12428', 'training/13099', 'training/13744', 'training/13795', 'training/13852', 'training/13856', 'training/1652', 'training/1970', 'training/2044', 'training/2171', 'training/2172', 'training/2191', 'training/2217', 'training/2232', 'training/3132', 'training/3324', 'training/395', 'training/4280', 'training/4296', 'training/5', 'training/501', 'training/5467', 'training/5610', 'training/5640', 'training/6626', 'training/7205', 'training/7579', 'training/8213', 'training/8257', 'training/8759', 'training/9865', 'training/9958']

>>> from nltk.corpus import inaugural
>>> len(inaugural.fileids())
56
>>> inaugural.fileids()
['1789-Washington.txt', '1793-Washington.txt', '1797-Adams.txt', '1801-Jefferson.txt', '1805-Jefferson.txt', '1809-Madison.txt', '1813-Madison.txt', '1817-Monroe.txt', '1821-Monroe.txt', '1825-Adams.txt', '1829-Jackson.txt', '1833-Jackson.txt', '1837-VanBuren.txt', '1841-Harrison.txt', '1845-Polk.txt', '1849-Taylor.txt', '1853-Pierce.txt', '1857-Buchanan.txt', '1861-Lincoln.txt', '1865-Lincoln.txt', '1869-Grant.txt', '1873-Grant.txt', '1877-Hayes.txt', '1881-Garfield.txt', '1885-Cleveland.txt', '1889-Harrison.txt', '1893-Cleveland.txt', '1897-McKinley.txt', '1901-McKinley.txt', '1905-Roosevelt.txt', '1909-Taft.txt', '1913-Wilson.txt', '1917-Wilson.txt', '1921-Harding.txt', '1925-Coolidge.txt', '1929-Hoover.txt', '1933-Roosevelt.txt', '1937-Roosevelt.txt', '1941-Roosevelt.txt', '1945-Roosevelt.txt', '1949-Truman.txt', '1953-Eisenhower.txt', '1957-Eisenhower.txt', '1961-Kennedy.txt', '1965-Johnson.txt', '1969-Nixon.txt', '1973-Nixon.txt', '1977-Carter.txt', '1981-Reagan.txt', '1985-Reagan.txt', '1989-Bush.txt', '1993-Clinton.txt', '1997-Clinton.txt', '2001-Bush.txt', '2005-Bush.txt', '2009-Obama.txt']

>>> [fileid[:4] for fileid in inaugural.fileids()]
['1789', '1793', '1797', '1801', '1805', '1809', '1813', '1817', '1821', '1825', '1829', '1833', '1837', '1841', '1845', '1849', '1853', '1857', '1861', '1865', '1869', '1873', '1877', '1881', '1885', '1889', '1893', '1897', '1901', '1905', '1909', '1913', '1917', '1921', '1925', '1929', '1933', '1937', '1941', '1945', '1949', '1953', '1957', '1961', '1965', '1969', '1973', '1977', '1981', '1985', '1989', '1993', '1997', '2001', '2005', '2009']

>>> import nltk
>>> 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()

>>> from nltk.corpus import PlaintextCorpusReader
>>> corpus_root=r'E:\dict'
>>> wordlists=PlaintextCorpusReader(corpus_root,'.*')
>>> wordlists.fileids()
['dqdg.txt', 'q0.txt', 'q1.txt', 'q10.txt', 'q2.txt', 'q3.txt', 'q5.txt', 'text.txt']
>>> len(wordlists.words('text.txt')) #如果输入错误或者格式不正确，notepad++转换下编码格式即可
152389

>>> from nltk.corpus import brown
>>> cfd=nltk.ConditionalFreqDist((genre,word) for genre in brown.categories() for word in brown.words(categories=genre))

>>> 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()
['romance', 'news']
>>> len(cfd['news'])
14394
>>> len(cfd['romance'])
8452

>>> from nltk.corpus import brown
>>> import nltk
>>> cfd=nltk.ConditionalFreqDist((genre,word) for genre in brown.categories() for word in brown.words(categories=genre))
>>> len(list(cfd['romance']))
8452
>>> len(set(cfd['romance']))
8452
>>> cfd['news']['The']
806

>>> cfd=nltk.ConditionalFreqDist((target,fileid[:4]) for fileid in inaugural.fileids() for word in inaugural.words(fileid) for target in ['america','citizen'] if word.lower().startswith(target))
>>> cfd.plot(cumulative=True)

cfd.tabulate(conditions=['English','The'],samples=range(10),cumulative=True)

>>> sent=['Emma', 'Woodhouse', ',', 'handsome', ',', 'clever', ',', 'and', 'rich', ',', 'with', 'a', 'comfortable', 'home', 'and', 'happy', 'disposition', ',', 'seemed', 'to', 'unite', 'some', 'of', 'the', 'best', 'blessings', 'of', ]
>>> nltk.bigrams(sent)
<generator object bigrams at 0x0103C180>

import nltk
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)

========================== RESTART: E:/Python/1.py ==========================
>>> cfd['living']
FreqDist({'creature': 7, 'thing': 4, 'substance': 2, ',': 1, '.': 1, 'soul': 1})
>>> generate_model(cfd,'living')

class MyHello:
    def hello():
        print("Hello Python")
    def bnc():
        print("Hello BNC")
    def add(num1,num2):
        print("The sum is \t",str(num1+num2))

============== RESTART: E:/sourceCode/NLPPython/day_03/hello.py ==============
>>> from  hello import *
>>> MyHello.add(1,2)
The sum is   3
>>> MyHello.hello()
Hello Python

class WordsPro:
    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)

========================== RESTART: E:/Python/1.py ==========================
>>> import nltk
>>> from nltk.corpus import gutenberg
>>> len(WordsPro.unusual_words(nltk.corpus.gutenberg.words('austen-sense.txt')))
1601
>>>

>>> from nltk.corpus import stopwprds
>>> stopwords.words('english')

def    content_faction(text):
            stopwords=nltk.corpus.stopwords.words('english')
            content = [w for w in text if w.lower() not in stopwords]
            return len(content)/len(text)

>>> import nltk
>>> from nltk.corpus import reuters
>>> WordsPro.content_faction(nltk.corpus.reuters.words())
0.735240435097661

>>> import nltk
>>> puzzle_letters = nltk.FreqDist('egivrvonl')
>>> obligatory = 'r'#默认选择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]

>>> from nltk.tokenize.stanford_segmenter import StanfordSegmenter
>>> segmenter = StanfordSegmenter(
	path_to_jar=r"E:\tools\stanfordNLTK\jar\stanford-segmenter.jar",
        path_to_slf4j=r"E:\tools\stanfordNLTK\jar\slf4j-api.jar",
        path_to_sihan_corpora_dict=r"E:\tools\stanfordNLTK\jar\data",
        path_to_model=r"E:\tools\stanfordNLTK\jar\data\pku.gz",
        path_to_dict=r"E:\tools\stanfordNLTK\jar\data\dict-chris6.ser.gz"
	)
>>> with open(r"C:\Users\cuitbnc\Desktop\dqdg.txt","r+") as f:
	str=f.read()
 
>>> result = segmenter.segment(str)
>>> with open(r"C:\Users\cuitbnc\Desktop\text1.txt","w") as wf:
            wf.write(result)
1122469
>>> from nltk.corpus import PlaintextCorpusReader
>>> corpus_root=r'E:\dict\StopWord'
>>> wordlists=PlaintextCorpusReader(corpus_root,'.*')
>>> wordlists.fileids()
['baidu.txt', 'chuangda.txt', 'hagongda.txt', 'zhongwen.txt', '中文停用词库.txt', '四川大学机器智能实验室停用词库.txt']
>>> len(wordlists.words('hagongda.txt'))
977
>>> wordlists.words('hagongda.txt')[:100]
['———', '》），', '）÷（', '１', '－', '”，', '）、', '＝（', ':', ...]
>>> stopwords=wordlists.words('hagongda.txt')
>>> content = [w for w in result if w not in stopwords]