如何建立一个包含bigrams的gensim字典?

from gensim.models import Phrases
from gensim.models.phrases import Phraser
from gensim import models



docs = ['new york is is united states', 'new york is most populated city in the world','i love to stay in new york']

token_ = [doc.split(" ") for doc in docs]
bigram = Phrases(token_, min_count=1, threshold=2,delimiter=b' ')


bigram_phraser = Phraser(bigram)

bigram_token = []
for sent in token_:
    bigram_token.append(bigram_phraser[sent])

输出为: [['new york', 'is', 'is', 'united', 'states'],['new york', 'is', 'most', 'populated', 'city', 'in', 'the', 'world'],['i', 'love', 'to', 'stay', 'in', 'new york']]

#now you can make dictionary of bigram token 
dict = gensim.corpora.Dictionary(bigram_token)

print(dict.token2id)
#Convert the word into vector, and now you can use tfidf model from gensim 
corpus = [dict.doc2bow(text) for text in bigram_token]

tfidf_model = models.TfidfModel(corpus)

在创建词典之前,你必须“短语化”你的语料库来检测bigrams。

我建议您在输入字典之前也对其进行词干或柠檬化处理,下面是一个使用nltk词干分析器函数的示例:

import re
from gensim.models.phrases import Phrases, Phraser
from gensim.corpora.dictionary import Dictionary
from gensim.models import TfidfModel
from nltk.stem.snowball import SnowballStemmer as Stemmer

stemmer = Stemmer("YOUR_LANG") # see nltk.stem.snowball doc

stopWords = {"YOUR_STOPWORDS_FOR_LANG"} # as a set

docs = ["LIST_OF_STR"]

def tokenize(text):
    """
    return list of str from a str
    """
    # keep lowercase alphanums and "-" but not "_"
    return [w for w in re.split(r"_+|[^\w-]+", text.lower()) if w not in stopWords]

docs = [tokenize(doc) for doc in docs]
phrases = Phrases(docs)
bigrams = Phraser(phrases)
corpus = [[stemmer.stem(w) for w in bigrams[doc]] for doc in docs]
dictionary = Dictionary(corpus)
# and here is your tfidf model:
tfidf = TfidfModel(dictionary=dictionary, normalize=True)