Python中一些自然语言工具的使用的入门教程

>>> from nltk.tokenizer import *
>>> t = Token(TEXT='This is my first test sentence')
>>> WSTokenizer().tokenize(t, addlocs=True) # break on whitespace
>>> print t['TEXT']
This is my first test sentence
>>> print t['SUBTOKENS']
[<This>@[0:4c], <is>@[5:7c], <my>@[8:10c], <first>@[11:16c],
<test>@[17:21c], <sentence>@[22:30c]]
>>> t['foo'] = 'bar'
>>> t
<TEXT='This is my first test sentence', foo='bar',
SUBTOKENS=[<This>@[0:4c], <is>@[5:7c], <my>@[8:10c], <first>@[11:16c],
<test>@[17:21c], <sentence>@[22:30c]]>
>>> print t['SUBTOKENS'][0]
<This>@[0:4c]
>>> print type(t['SUBTOKENS'][0])
<class 'nltk.token.SafeToken'>

>>> from nltk.probability import *
>>> article = Token(TEXT=open('cp-b17.txt').read())
>>> WSTokenizer().tokenize(article)
>>> freq = FreqDist()
>>> for word in article['SUBTOKENS']:
...   freq.inc(word['TEXT'])
>>> freq.B()
1194
>>> freq.count('Python')
12

>>> cf = ConditionalFreqDist()
>>> for word in article['SUBTOKENS']:
...   cf[word['TEXT'][0]].inc(len(word['TEXT']))
...
>>> init_letters = cf.conditions()
>>> init_letters.sort()
>>> for c in init_letters[44:50]:
...   print "Init %s:" % c,
...   for length in range(1,6):
...     print "len %d/%.2f," % (length,cf[c].freq(n)),
...   print
...
Init a: len 1/0.03, len 2/0.03, len 3/0.03, len 4/0.03, len 5/0.03,
Init b: len 1/0.12, len 2/0.12, len 3/0.12, len 4/0.12, len 5/0.12,
Init c: len 1/0.06, len 2/0.06, len 3/0.06, len 4/0.06, len 5/0.06,
Init d: len 1/0.06, len 2/0.06, len 3/0.06, len 4/0.06, len 5/0.06,
Init e: len 1/0.18, len 2/0.18, len 3/0.18, len 4/0.18, len 5/0.18,
Init f: len 1/0.25, len 2/0.25, len 3/0.25, len 4/0.25, len 5/0.25,

>>> from nltk.stemmer.porter import PorterStemmer
>>> PorterStemmer().stem_word('complications')
'complic'

>>> from nltk.tokenizer import *
>>> article = Token(TEXT=open('cp-b17.txt').read())
>>> WSTokenizer().tokenize(article)
>>> from nltk.probability import *
>>> from nltk.stemmer.porter import *
>>> stemmer = PorterStemmer()
>>> stems = FreqDist()
>>> for word in article['SUBTOKENS']:
...   stemmer.stem(word)
...   stems.inc(word['STEM'].lower())
...
>>> word_stems = stems.samples()
>>> word_stems.sort()
>>> word_stems[20:40]
['"generator-bas', '"implement', '"lazili', '"magic"', '"partial',
'"pluggable"', '"primitives"', '"repres', '"secur', '"semi-coroutines."',
'"state', '"understand', '"weightless', '"whatev', '#', '#-----',
'#----------', '#-------------', '#---------------', '#b17:']

>>> article = TS().text_splitter(open('cp-b17.txt').read())
>>> stems = FreqDist()
>>> for word in article:
...   stems.inc(stemmer.stem_word(word.lower()))
...
>>> word_stems = stems.samples()
>>> word_stems.sort()
>>> word_stems[60:80]
['bool', 'both', 'boundari', 'brain', 'bring', 'built', 'but', 'byte',
'call', 'can', 'cannot', 'capabl', 'capit', 'carri', 'case', 'cast',
'certain', 'certainli', 'chang', 'charm']

>>> from nltk.parser.chunk import ChunkedTaggedTokenizer
>>> chunked = "[ the/DT little/JJ cat/NN ] sat/VBD on/IN [ the/DT mat/NN ]"
>>> sentence = Token(TEXT=chunked)
>>> tokenizer = ChunkedTaggedTokenizer(chunk_node='NP')
>>> tokenizer.tokenize(sentence)
>>> sentence['SUBTOKENS'][0]
(NP: <the/DT> <little/JJ> <cat/NN>)
>>> sentence['SUBTOKENS'][0]['NODE']
'NP'
>>> sentence['SUBTOKENS'][0]['CHILDREN'][0]
<the/DT>
>>> sentence['SUBTOKENS'][0]['CHILDREN'][0]['TAG']
'DT'
>>> chunk_structure = TreeToken(NODE='S', CHILDREN=sentence['SUBTOKENS'])
(S:
 (NP: <the/DT> <little/JJ> <cat/NN>)
 <sat/VBD>
 <on/IN>
 (NP: <the/DT> <mat/NN>))

>>> rule1 = ChunkRule('<DT>?<JJ.*>*<NN.*>',
...        'Chunk optional det, zero or more adj, and a noun')
>>> chunkparser = RegexpChunkParser([rule1], chunk_node='NP', top_node='S')
>>> chunkparser.parse(sentence)
>>> print sent['TREE']
(S: (NP: <the/DT> <little/JJ> <cat/NN>)
 <sat/VBD> <on/IN>
 (NP: <the/DT> <mat/NN>))

>>> from nltk.parser.chart import *
>>> grammar = CFG.parse('''
...  S -> NP VP
...  VP -> V NP | VP PP
...  V -> "saw" | "ate"
...  NP -> "John" | "Mary" | "Bob" | Det N | NP PP
...  Det -> "a" | "an" | "the" | "my"
...  N -> "dog" | "cat" | "cookie"
...  PP -> P NP
...  P -> "on" | "by" | "with"
...  ''')
>>> sentence = Token(TEXT='John saw a cat with my cookie')
>>> WSTokenizer().tokenize(sentence)
>>> parser = ChartParser(grammar, BU_STRATEGY, LEAF='TEXT')
>>> parser.parse_n(sentence)
>>> for tree in sentence['TREES']: print tree
(S:
 (NP: <John>)
 (VP:
  (VP: (V: <saw>) (NP: (Det: <a>) (N: <cat>)))
  (PP: (P: <with>) (NP: (Det: <my>) (N: <cookie>)))))
(S:
 (NP: <John>)
 (VP:
  (V: <saw>)
  (NP:
   (NP: (Det: <a>) (N: <cat>))
   (PP: (P: <with>) (NP: (Det: <my>) (N: <cookie>))))))