DESCRIPTION

     The Natural Language Toolkit (NLTK) is an open source Python library

     for Natural Language Processing.  A free online book is available.

     (If you use the library for academic research, please cite the book.)

     Steven Bird, Ewan Klein, and Edward Loper ().

     Natural Language Processing with Python.  O'Reilly Media Inc.

     http://nltk.org/book

     @version: 2.0.

 :chapter2 rcf$ python

 Python 2.7. (default, Mar   , ::)

 [GCC 4.2. Compatible Apple LLVM 5.0 (clang-500.0.)] on darwin

 Type "help", "copyright", "credits" or "license" for more information.

 >>> import nltk

 >>> nltk.download()

 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

 text2: Sense and Sensibility by Jane Austen

 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 

 >>> text1.concordance("monstrous")

 Building index...

 Displaying  of  matches:

 ong the former , one was of a most monstrous size . ... This came towards us ,

 ON OF THE PSALMS . " Touching that monstrous bulk of the whale or ork we have r

 ll over with a heathenish array of monstrous clubs and spears . Some were thick

 d as you gazed , and wondered what monstrous cannibal and savage could ever hav

 that has survived the flood ; most monstrous and most mountainous ! That Himmal

 they might scout at Moby Dick as a monstrous fable , or still worse and more de

 th of Radney .'" CHAPTER 55 Of the Monstrous Pictures of Whales . I shall ere l

 ing Scenes . In connexion with the monstrous pictures of whales , I am strongly

 ere to enter upon those still more monstrous stories of them which are to be fo

 ght have been rummaged out of this monstrous cabinet there is no telling . But

 of Whale - Bones ; for Whales of a monstrous size are oftentimes cast up dead u

 >>> text1.similar("monstrous")

 Building word-context index...

 abundant candid careful christian contemptible curious delightfully

 determined doleful domineering exasperate fearless few gamesome

 horrible impalpable imperial lamentable lazy loving

 >>> text4.dispersion_plot(["citizens","democracy","freedom","duties","America"])

 >>> len(text1)   #计算text1的词汇个数

 >>> len(set(text1)) #计算text1 不同的词汇个数

 >>> len(text1[])   #计算text1 第一个词的长度
 

 >>> sent1

 ['Call', 'me', 'Ishmael', '.']

 >>> sorted(sent1)

 ['.', 'Call', 'Ishmael', 'me']

 >>> fdist1=FreqDist(text1)    #获取text1的频率分布情况

 >>> fdist1      　　　　　　　　#text1具有19317个样本,但是总体有260819个值

 <FreqDist with  samples and  outcomes>

 >>> keys=fdist1.keys()

 >>> keys[:]                 #获取text1的前50个样本
 [',', 'the', '.', 'of', 'and', 'a', 'to', ';', 'in', 'that', "'", '-', 'his', 'it', 'I', 's', 'is', 'he', 'with', 'was', 'as', '"', 'all', 'for', 'this', '!', 'at', 'by', 'but', 'not', '--', 'him', 'from', 'be', 'on', 'so', 'whale', 'one', 'you', 'had', 'have', 'there', 'But', 'or', 'were', 'now', 'which', '?', 'me', 'like']

 >>> fdist1.items()[:]      #text1的样本分布情况，比如','出现了18713次，总共的词为260819

 [(',', ), ('the', ), ('.', ), ('of', ), ('and', ), ('a', ), ('to', ), (';', ), ('in', ), ('that', ), ("'", ), ('-', ), ('his', ), ('it', ), ('I', ), ('s', ), ('is', ), ('he', ), ('with', ), ('was', ), ('as', ), ('"', ), ('all', ), ('for', ), ('this', ), ('!', ), ('at', ), ('by', ), ('but', ), ('not', ), ('--', ), ('him', ), ('from', ), ('be', ), ('on', ), ('so', ), ('whale', ), ('one', ), ('you', ), ('had', ), ('have', ), ('there', ), ('But', ), ('or', ), ('were', ), ('now', ), ('which', ), ('?', ), ('me', ), ('like', )]

 >>> fdist1.hapaxes()[:]   #text1的样本只出现一次的词

 ['!\'"', '!)"', '!*', '!--"', '"...', "',--", "';", '):', ');--', ',)', '--\'"', '---"', '---,', '."*', '."--', '.*--', '.--"', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '']
3 >>> fdist1['!\'"']
4 1

 >>> long_words=[w for w in set(text1) if len(w) > ]  #获取text1内样本词汇长度大于15的词并按字典序排序

 >>> sorted(long_words)

 ['CIRCUMNAVIGATION', 'Physiognomically', 'apprehensiveness', 'cannibalistically', 'characteristically', 'circumnavigating', 'circumnavigation', 'circumnavigations', 'comprehensiveness', 'hermaphroditical', 'indiscriminately', 'indispensableness', 'irresistibleness', 'physiognomically', 'preternaturalness', 'responsibilities', 'simultaneousness', 'subterraneousness', 'supernaturalness', 'superstitiousness', 'uncomfortableness', 'uncompromisedness', 'undiscriminating', 'uninterpenetratingly']

 >>> fdist1=FreqDist(text1)    #获取text1内样本词汇长度大于7且出现次数大于7的词并按字典序排序
 >>> sorted([wforwin set(text5) if len(w) >  and fdist1[w] > ])  ['American', 'actually', 'afternoon', 'anything', 'attention', 'beautiful', 'carefully', 'carrying', 'children', 'commanded', 'concerning', 'considered', 'considering', 'difference', 'different', 'distance', 'elsewhere', 'employed', 'entitled', 'especially', 'everything', 'excellent', 'experience', 'expression', 'floating', 'following', 'forgotten', 'gentlemen', 'gigantic', 'happened', 'horrible', 'important', 'impossible', 'included', 'individual', 'interesting', 'invisible', 'involved', 'monsters', 'mountain', 'occasional', 'opposite', 'original', 'originally', 'particular', 'pictures', 'pointing', 'position', 'possibly', 'probably', 'question', 'regularly', 'remember', 'revolving', 'shoulders', 'sleeping', 'something', 'sometimes', 'somewhere', 'speaking', 'specially', 'standing', 'starting', 'straight', 'stranger', 'superior', 'supposed', 'surprise', 'terrible', 'themselves', 'thinking', 'thoughts', 'together', 'understand', 'watching', 'whatever', 'whenever', 'wonderful', 'yesterday', 'yourself']

 >>> bigrams(['more','is','said','than','done'])

 [('more', 'is'), ('is', 'said'), ('said', 'than'), ('than', 'done')]

 >>> text1.collocations()

 Building collocations list

 Sperm Whale; Moby Dick; White Whale; old man; Captain Ahab; sperm

 whale; Right Whale; Captain Peleg; New Bedford; Cape Horn; cried Ahab;

 years ago; lower jaw; never mind; Father Mapple; cried Stubb; chief

 mate; white whale; ivory leg; one hand

 >>> type(text1)

 <class 'nltk.text.Text'>

 >>> help('nltk.text.Text')

 Help on class Text in nltk.text:

 nltk.text.Text = class Text(__builtin__.object)

  |  A wrapper around a sequence of simple (string) tokens, which is

  |  intended to support initial exploration of texts (via the

  |  interactive console).  Its methods perform a variety of analyses

  |  on the text's contexts (e.g., counting, concordancing, collocation

  |  discovery), and display the results.  If you wish to write a

  |  program which makes use of these analyses, then you should bypass

  |  the ``Text`` class, and use the appropriate analysis function or

  |  class directly instead.

  |

  |  A ``Text`` is typically initialized from a given document or

  |  corpus.  E.g.:

  |

  |  >>> import nltk.corpus

  |  >>> from nltk.text import Text

  |  >>> moby = Text(nltk.corpus.gutenberg.words('melville-moby_dick.txt'))

  |

  |  Methods defined here:

  |

  |  __getitem__(self, i)

  |

  |  __init__(self, tokens, name=None)

  |      Create a Text object.

  |

  |      :param tokens: The source text.

  |      :type tokens: sequence of str

  |

  |  __len__(self)

  |

  |  __repr__(self)

  |      :return: A string representation of this FreqDist.

  |      :rtype: string

  |

  |  collocations(self, num=, window_size=)

  |      Print collocations derived from the text, ignoring stopwords.

  |

  |      :seealso: find_collocations

  |      :param num: The maximum number of collocations to print.

  |      :type num: int

  |      :param window_size: The number of tokens spanned by a collocation (default=)

  |      :type window_size: int

  |

  |  common_contexts(self, words, num=)

  |      Find contexts where the specified words appear; list

  |      most frequent common contexts first.

  |

  |      :param word: The word used to seed the similarity search

  |      :type word: str

  |      :param num: The number of words to generate (default=)

  |      :type num: int

  |      :seealso: ContextIndex.common_contexts()