使用 NLTK 的实例

下面是我自己的实际例子，可以帮助其他人查找这个问题(请原谅样本文本，这是我在 维基百科上找到的第一个例子) :

import nltk
import pprint


tokenizer = None
tagger = None


def init_nltk():
global tokenizer
global tagger
tokenizer = nltk.tokenize.RegexpTokenizer(r'\w+|[^\w\s]+')
tagger = nltk.UnigramTagger(nltk.corpus.brown.tagged_sents())


def tag(text):
global tokenizer
global tagger
if not tokenizer:
init_nltk()
tokenized = tokenizer.tokenize(text)
tagged = tagger.tag(tokenized)
tagged.sort(lambda x,y:cmp(x[1],y[1]))
return tagged


def main():
text = """Mr Blobby is a fictional character who featured on Noel
Edmonds' Saturday night entertainment show Noel's House Party,
which was often a ratings winner in the 1990s. Mr Blobby also
appeared on the Jamie Rose show of 1997. He was designed as an
outrageously over the top parody of a one-dimensional, mute novelty
character, which ironically made him distinctive, absurd and popular.
He was a large pink humanoid, covered with yellow spots, sporting a
permanent toothy grin and jiggling eyes. He communicated by saying
the word "blobby" in an electronically-altered voice, expressing
his moods through tone of voice and repetition.


There was a Mrs. Blobby, seen briefly in the video, and sold as a
doll.


However Mr Blobby actually started out as part of the 'Gotcha'
feature during the show's second series (originally called 'Gotcha
Oscars' until the threat of legal action from the Academy of Motion
Picture Arts and Sciences[citation needed]), in which celebrities
were caught out in a Candid Camera style prank. Celebrities such as
dancer Wayne Sleep and rugby union player Will Carling would be
enticed to take part in a fictitious children's programme based around
their profession. Mr Blobby would clumsily take part in the activity,
knocking over the set, causing mayhem and saying "blobby blobby
blobby", until finally when the prank was revealed, the Blobby
costume would be opened - revealing Noel inside. This was all the more
surprising for the "victim" as during rehearsals Blobby would be
played by an actor wearing only the arms and legs of the costume and
speaking in a normal manner.[citation needed]"""
tagged = tag(text)
l = list(set(tagged))
l.sort(lambda x,y:cmp(x[1],y[1]))
pprint.pprint(l)


if __name__ == '__main__':
main()

产出:

[('rugby', None),
('Oscars', None),
('1990s', None),
('",', None),
('Candid', None),
('"', None),
('blobby', None),
('Edmonds', None),
('Mr', None),
('outrageously', None),
('.[', None),
('toothy', None),
('Celebrities', None),
('Gotcha', None),
(']),', None),
('Jamie', None),
('humanoid', None),
('Blobby', None),
('Carling', None),
('enticed', None),
('programme', None),
('1997', None),
('s', None),
("'", "'"),
('[', '('),
('(', '('),
(']', ')'),
(',', ','),
('.', '.'),
('all', 'ABN'),
('the', 'AT'),
('an', 'AT'),
('a', 'AT'),
('be', 'BE'),
('were', 'BED'),
('was', 'BEDZ'),
('is', 'BEZ'),
('and', 'CC'),
('one', 'CD'),
('until', 'CS'),
('as', 'CS'),
('This', 'DT'),
('There', 'EX'),
('of', 'IN'),
('inside', 'IN'),
('from', 'IN'),
('around', 'IN'),
('with', 'IN'),
('through', 'IN'),
('-', 'IN'),
('on', 'IN'),
('in', 'IN'),
('by', 'IN'),
('during', 'IN'),
('over', 'IN'),
('for', 'IN'),
('distinctive', 'JJ'),
('permanent', 'JJ'),
('mute', 'JJ'),
('popular', 'JJ'),
('such', 'JJ'),
('fictional', 'JJ'),
('yellow', 'JJ'),
('pink', 'JJ'),
('fictitious', 'JJ'),
('normal', 'JJ'),
('dimensional', 'JJ'),
('legal', 'JJ'),
('large', 'JJ'),
('surprising', 'JJ'),
('absurd', 'JJ'),
('Will', 'MD'),
('would', 'MD'),
('style', 'NN'),
('threat', 'NN'),
('novelty', 'NN'),
('union', 'NN'),
('prank', 'NN'),
('winner', 'NN'),
('parody', 'NN'),
('player', 'NN'),
('actor', 'NN'),
('character', 'NN'),
('victim', 'NN'),
('costume', 'NN'),
('action', 'NN'),
('activity', 'NN'),
('dancer', 'NN'),
('grin', 'NN'),
('doll', 'NN'),
('top', 'NN'),
('mayhem', 'NN'),
('citation', 'NN'),
('part', 'NN'),
('repetition', 'NN'),
('manner', 'NN'),
('tone', 'NN'),
('Picture', 'NN'),
('entertainment', 'NN'),
('night', 'NN'),
('series', 'NN'),
('voice', 'NN'),
('Mrs', 'NN'),
('video', 'NN'),
('Motion', 'NN'),
('profession', 'NN'),
('feature', 'NN'),
('word', 'NN'),
('Academy', 'NN-TL'),
('Camera', 'NN-TL'),
('Party', 'NN-TL'),
('House', 'NN-TL'),
('eyes', 'NNS'),
('spots', 'NNS'),
('rehearsals', 'NNS'),
('ratings', 'NNS'),
('arms', 'NNS'),
('celebrities', 'NNS'),
('children', 'NNS'),
('moods', 'NNS'),
('legs', 'NNS'),
('Sciences', 'NNS-TL'),
('Arts', 'NNS-TL'),
('Wayne', 'NP'),
('Rose', 'NP'),
('Noel', 'NP'),
('Saturday', 'NR'),
('second', 'OD'),
('his', 'PP$'),
('their', 'PP$'),
('him', 'PPO'),
('He', 'PPS'),
('more', 'QL'),
('However', 'RB'),
('actually', 'RB'),
('also', 'RB'),
('clumsily', 'RB'),
('originally', 'RB'),
('only', 'RB'),
('often', 'RB'),
('ironically', 'RB'),
('briefly', 'RB'),
('finally', 'RB'),
('electronically', 'RB-HL'),
('out', 'RP'),
('to', 'TO'),
('show', 'VB'),
('Sleep', 'VB'),
('take', 'VB'),
('opened', 'VBD'),
('played', 'VBD'),
('caught', 'VBD'),
('appeared', 'VBD'),
('revealed', 'VBD'),
('started', 'VBD'),
('saying', 'VBG'),
('causing', 'VBG'),
('expressing', 'VBG'),
('knocking', 'VBG'),
('wearing', 'VBG'),
('speaking', 'VBG'),
('sporting', 'VBG'),
('revealing', 'VBG'),
('jiggling', 'VBG'),
('sold', 'VBN'),
('called', 'VBN'),
('made', 'VBN'),
('altered', 'VBN'),
('based', 'VBN'),
('designed', 'VBN'),
('covered', 'VBN'),
('communicated', 'VBN'),
('needed', 'VBN'),
('seen', 'VBN'),
('set', 'VBN'),
('featured', 'VBN'),
('which', 'WDT'),
('who', 'WPS'),
('when', 'WRB')]

我是 Streamhacker.com的作者(谢谢你的提及，我从这个问题中获得了相当多的点击流量)。你到底想干什么？NLTK 有很多用于完成各种事情的工具，但是缺乏关于如何使用这些工具以及如何最好地使用它们的清晰信息。它还面向学术问题，因此将 教学方法示例转换为实际解决方案可能会很繁重。

NLP 通常非常有用，因此您可能希望将搜索范围扩大到文本分析的一般应用程序。我使用 NLTK 通过提取概念图生成文件分类来帮助 MOSS 2010。效果非常好。用不了多久，文件就开始以有用的方式集群起来。

为了理解文本分析，你常常不得不偏离你习惯思考的方式。例如，文本分析对于发现非常有用。然而，大多数人甚至不知道搜索和发现之间的区别。如果您仔细阅读这些主题，您可能会“发现”使用 NLTK 的方法。

另外，考虑一下不使用 NLTK 的文本文件的世界视图。您有一堆随机长度的字符串，它们由空格和标点符号分隔。一些标点符号改变了它的使用方式，比如句号(也是一个小数点和缩写的后缀标记)使用 NLTK，您可以获得单词以及更多内容，从而获得部分词性。现在您已经掌握了内容。使用 NLTK 发现文档中的概念和操作。使用 NLTK 了解文档的“含义”。在这种情况下，意义指的是文档中的基本关系。

对 NLTK 感到好奇是件好事。文本分析将在未来几年内大规模突破。那些明白这一点的人将更适合于更好地利用新的机会。