How to extract content keywords from python _python

This article illustrates how Python extracts content keywords. Share to everyone for your reference. The specific analysis is as follows:

A very efficient extraction of content keyword Python code, this code can only be used in English article content, Chinese because to participle, this piece of code can do nothing, but to add participle function, the effect and English is the same.

Copy Code code as follows:

# Coding=utf-8
Import NLTK
From Nltk.corpus import Brown
# This is a fast and simple noun phrase extractor (based on NLTK)
# Feel free to use it, just keep-a link to this post
# http://thetokenizer.com/2013/05/09/efficient-way-to-extract-the-main-topics-of-a-sentence/
# Create by Shlomi Babluki
# May, 2013

# This is we fast part of Speech tagger
#############################################################################
Brown_train = brown.tagged_sents (categories= ' news ')
Regexp_tagger = NLTK. Regexptagger (
[R ' ^-? [0-9]+ (. [ 0-9]+)? $ ', ' CD ',
(R ' (-|:|;) $', ':'),
(R ' \ *$ ', ' MD '),
(R ' (the|the| a|a| An|an) $ ', ' at '),
(R '. *able$ ', ' JJ '),
(R ' ^[a-z].*$ ', ' NNP '),
(R '. *ness$ ', ' NN '),
(R '. *ly$ ', ' RB '),
(R '. *s$ ', ' NNS '),
(R '. *ing$ ', ' VBG '),
(R '. *ed$ ', ' VBD '),
(R '. * ', ' NN ')
])
Unigram_tagger = NLTK. Unigramtagger (Brown_train, Backoff=regexp_tagger)
Bigram_tagger = NLTK. Bigramtagger (Brown_train, Backoff=unigram_tagger)
#############################################################################
# this are our semi-cfg; Extend it according to your own needs
#############################################################################
CFG = {}
cfg["NNP+NNP"] = "NNP"
cfg["Nn+nn"] = "NNI"
cfg["Nni+nn"] = "NNI"
cfg["JJ+JJ"] = "JJ"
cfg["Jj+nn"] = "NNI"
#############################################################################
Class Npextractor (object):
def __init__ (self, sentence):
Self.sentence = sentence
# Split the sentence into SINGLW words/tokens
def tokenize_sentence (self, sentence):
tokens = nltk.word_tokenize (sentence)
return tokens
# normalize Brown Corpus ' tags ("nn", "NN-PL", "NNS" > "NN")
def normalize_tags (self, tagged):
n_tagged = []
For T in Tagged:
If t[1] = = "Np-tl" or t[1] = = "NP":
N_tagged.append ((t[0], "NNP"))
Continue
If T[1].endswith ("-tl"):
N_tagged.append ((t[0), t[1][:-3])
Continue
If T[1].endswith ("S"):
N_tagged.append ((t[0), t[1][:-1])
Continue
N_tagged.append ((t[0), t[1])
Return n_tagged
# Extract The main topics from the sentence
def extract (self):
Tokens = Self.tokenize_sentence (self.sentence)
tags = self.normalize_tags (bigram_tagger.tag (tokens))
Merge = True
While merge:
Merge = False
For x in range (0, Len (tags)-1):
T1 = tags[x]
T2 = tags[x + 1]
Key = "%s+%s"% (T1[1], t2[1])
Value = Cfg.get (Key, ')
If value:
Merge = True
Tags.pop (x)
Tags.pop (x)
Match = '%s%s '% (T1[0], t2[0])
pos = value
Tags.insert (x, (Match, POS))
Break
matches = []
For T in Tags:
If t[1] = = "NNP" or t[1] = = "NNI":
#if t[1] = = "NNP" or t[1] = = "NNI" or t[1] = = "NN":
Matches.append (T[0])
return matches
# Main method, just run ' python np_extractor.py '
def main ():
Sentence = "Swayy is a beautiful new dashboard for discovering and curating online content."
Np_extractor = npextractor (sentence)
result = Np_extractor.extract ()
Print ' This sentence is about:%s '% ', '. Join (Result)
if __name__ = = ' __main__ ':
Main ()

I hope this article will help you with your Python programming.