#用nltk+jieba发现连词和三连词。
import jieba
import nltk
from nltk.collocations import *
train_corpus = "测试数据库,用户支付表,支付金额,支付用户,测试数据库,用户支付表,支付金额,支付用户"
bigram_measures = nltk.collocations.BigramAssocMeasures()
trigram_measures = nltk.collocations.TrigramAssocMeasures()
finder = BigramCollocationFinder.from_words(jieba.cut(train_corpus))
finder.apply_word_filter(lambda w: w.lower() in [',', '.', ',', '。'])
finder.nbest(bigram_measures.pmi, 10)
finder = TrigramCollocationFinder.from_words(jieba.cut(train_corpus))
finder.apply_word_filter(lambda w: w.lower() in [',', '.', ',', '。'])
finder.nbest(trigram_measures.pmi, 10)
#用gensim+jieba发现连词
import jieba
import gensim
import jieba
import nltk
from nltk.collocations import *
train_corpus = "测试数据库,用户支付表,支付金额,支付用户,测试数据库,用户支付表,支付金额,支付用户"
bigram_measures = nltk.collocations.BigramAssocMeasures()
trigram_measures = nltk.collocations.TrigramAssocMeasures()
finder = BigramCollocationFinder.from_words(jieba.cut(train_corpus))
finder.apply_word_filter(lambda w: w.lower() in [',', '.', ',', '。'])
finder.nbest(bigram_measures.pmi, 10)
finder = TrigramCollocationFinder.from_words(jieba.cut(train_corpus))
finder.apply_word_filter(lambda w: w.lower() in [',', '.', ',', '。'])
finder.nbest(trigram_measures.pmi, 10)
#用gensim+jieba发现连词
import jieba
import gensim