Aşağıdaki kod, bahsettiğiniz örneklere dayanarak yaptığım basit bir Gazete'dir. Gelen
# -*- coding: utf-8 -*-
import codecs
from lxml.html.builder import DT
import os
import re
from nltk.chunk.util import conlltags2tree
from nltk.chunk import ChunkParserI
from nltk.tag import pos_tag
from nltk.tokenize import wordpunct_tokenize
def sub_leaves(tree, node):
return [t.leaves() for t in tree.subtrees(lambda s: s.node == node)]
class Gazetteer(ChunkParserI):
"""
Find and annotate a list of words that matches patterns.
Patterns may be regular expressions in the form list of tuples.
Every tuple has the regular expression and the iob tag for this one.
Before applying gazetteer words a part of speech tagging should
be performed. So, you have to pass your tagger as a parameter.
Example:
>>> patterns = [(u"Αθήνα[ς]?", "LOC"), (u"Νομική[ς]? [Σσ]χολή[ς]?", "ORG")]
>>> gazetteer = Gazetteer(patterns, nltk.pos_tag, nltk.wordpunct_tokenize)
>>> text = u"Η Νομική σχολή της Αθήνας"
>>> t = gazetteer.parse(text)
>>> print(unicode(t))
... (S Η/DT (ORG Νομική/NN σχολή/NN) της/DT (LOC Αθήνας/NN))
"""
def __init__(self, patterns, pos_tagger, tokenizer):
"""
Initialize the class.
:param patterns:
The patterns to search in text is a list of tuples with regular
expression and the tag to apply
:param pos_tagger:
The tagger to use for applying part of speech to the text
:param tokenizer:
The tokenizer to use for tokenizing the text
"""
self.patterns = patterns
self.pos_tag = pos_tagger
self.tokenize = tokenizer
self.lookahead = 0 # how many words it is possible to be a gazetteer word
self.words = [] # Keep the words found by applying the regular expressions
self.iobtags = [] # For each set of words keep the coresponding tag
def iob_tags(self, tagged_sent):
"""
Search the tagged sentences for gazetteer words and apply their iob tags.
:param tagged_sent:
A tokenized text with part of speech tags
:type tagged_sent: list
:return:
yields the IOB tag of the word with it's character, eg. B-LOCATION
:rtype:
"""
i = 0
l = len(tagged_sent)
inside = False # marks the I- tag
iobs = []
while i < l:
word, pos_tag = tagged_sent[i]
j = i + 1 # the next word
k = j + self.lookahead # how many words in a row we may search
nextwords, nexttags = [], [] # for now, just the ith word
add_tag = False # no tag, this is O
while j <= k:
words = ' '.join([word] + nextwords) # expand our word list
if words in self.words: # search for words
index = self.words.index(words) # keep index to use for iob tags
if inside:
iobs.append((word, pos_tag, 'I-' + self.iobtags[index])) # use the index tag
else:
iobs.append((word, pos_tag, 'B-' + self.iobtags[index]))
for nword, ntag in zip(nextwords, nexttags): # there was more than one word
iobs.append((nword, ntag, 'I-' + self.iobtags[index])) # apply I- tag to all of them
add_tag, inside = True, True
i = j # skip tagged words
break
if j < l: # we haven't reach the length of tagged sentences
nextword, nexttag = tagged_sent[j] # get next word and it's tag
nextwords.append(nextword)
nexttags.append(nexttag)
j += 1
else:
break
if not add_tag: # unkown words
inside = False
i += 1
iobs.append((word, pos_tag, 'O')) # it's an Outsider
return iobs
def parse(self, text, conlltags=True):
"""
Given a text, applies tokenization, part of speech tagging and the
gazetteer words with their tags. Returns an conll tree.
:param text: The text to parse
:type text: str
:param conlltags:
:type conlltags:
:return: An conll tree
:rtype:
"""
# apply the regular expressions and find all the
# gazetteer words in text
for pattern, tag in self.patterns:
words_found = set(re.findall(pattern, text)) # keep the unique words
if len(words_found) > 0:
for word in words_found: # words_found may be more than one
self.words.append(word) # keep the words
self.iobtags.append(tag) # and their tag
# find the pattern with the maximum words.
# this will be the look ahead variable
for word in self.words: # don't care about tags now
nwords = word.count(' ')
if nwords > self.lookahead:
self.lookahead = nwords
# tokenize and apply part of speech tagging
tagged_sent = self.pos_tag(self.tokenize(text))
# find the iob tags
iobs = self.iob_tags(tagged_sent)
if conlltags:
return conlltags2tree(iobs)
else:
return iobs
if __name__ == "__main__":
patterns = [(u"Αθήνα[ς]?", "LOC"), (u"Νομική[ς]? [Σσ]χολή[ς]?", "ORG")]
g = Gazetteer(patterns, pos_tag, wordpunct_tokenize)
text = u"Η Νομική σχολή της Αθήνας"
t = g.parse(text)
print(unicode(t))
dir_with_lists = "Lists"
patterns = []
tags = []
for root, dirs, files in os.walk(dir_with_lists):
for f in files:
lines = codecs.open(os.path.join(root, f), 'r', 'utf-8').readlines()
tag = os.path.splitext(f)[0]
for l in lines[1:]:
patterns.append((l.rstrip(), tag))
tags.append(tag)
text = codecs.open("sample.txt", 'r', "utf-8").read()
#g = Gazetteer(patterns)
t = g.parse(text.lower())
print unicode(t)
for tag in set(tags):
for gaz_word in sub_leaves(t, tag):
print gaz_word[0][0], tag
if __name__ == "__main__": kod patterns = [(u"Αθήνα[ς]?", "LOC"), (u"Νομική[ς]? [Σσ]χολή[ς]?", "ORG")] desenleri yapmak nerede bir örnek görebilirsiniz.
Kodda daha sonra, Lists adlı bir dizinden dosyaları okuyun (yukarıdaki koda sahip olduğunuz klasöre koyun). Her dosyanın adı Gazete’nin etiketi olur. Bu nedenle, LOC.txt gibi konumlar için desenleri (LOC etiketi), Kişiler için PERSON.txt gibi dosyaları yapın.
http://www.nltk.org/howto/chunk.html? – alvas
Zaten bu web sayfasını okudum ve buradaki soruma bir çözüm bulunmuyor. –