Python+gensim实现文本相似度分析详解

from jieba import lcut
from gensim.similarities import SparseMatrixSimilarity
from gensim.corpora import Dictionary
from gensim.models import TfidfModel
# 文本集和搜索词
texts = ['吃鸡这里所谓的吃鸡并不是真的吃鸡，也不是谐音词刺激的意思',
         '而是出自策略射击游戏《绝地求生：大逃杀》里的台词',
         '我吃鸡翅，你吃鸡腿']
keyword = '玩过吃鸡？今晚一起吃鸡'
# 1、将【文本集】生成【分词列表】
texts = [lcut(text) for text in texts]
# 2、基于文本集建立【词典】，并获得词典特征数
dictionary = Dictionary(texts)
num_features = len(dictionary.token2id)
# 3.1、基于词典，将【分词列表集】转换成【稀疏向量集】，称作【语料库】
corpus = [dictionary.doc2bow(text) for text in texts]
# 3.2、同理，用【词典】把【搜索词】也转换为【稀疏向量】
kw_vector = dictionary.doc2bow(lcut(keyword))
# 4、创建【TF-IDF模型】，传入【语料库】来训练
tfidf = TfidfModel(corpus)
# 5、用训练好的【TF-IDF模型】处理【被检索文本】和【搜索词】
tf_texts = tfidf[corpus]  # 此处将【语料库】用作【被检索文本】
tf_kw = tfidf[kw_vector]
# 6、相似度计算
sparse_matrix = SparseMatrixSimilarity(tf_texts, num_features)
similarities = sparse_matrix.get_similarities(tf_kw)
for e, s in enumerate(similarities, 1):
    print('kw 与 text%d 相似度为：%.2f' % (e, s))

import jieba
text = '七月七日长生殿，夜半无人私语时。'
words = jieba.lcut(text)
print(words)

from gensim import corpora
import jieba
# 文本集
text1 = '坚果果实'
text2 = '坚果实在好吃'
texts = [text1, text2]
# 将文本集生成分词列表
texts = [jieba.lcut(text) for text in texts]
print('文本集：', texts)
# 基于文本集建立词典
dictionary = corpora.Dictionary(texts)
print('词典：', dictionary)
# 提取词典特征数
feature_cnt = len(dictionary.token2id)
print('词典特征数：%d' % feature_cnt)

from gensim import corpora
import jieba
text1 = '来东京吃东京菜'
text2 = '东京啊东京啊东京'
texts = [text1, text2]
texts = [jieba.lcut(text) for text in texts]
dictionary = corpora.Dictionary(texts)
print('词典（字典）：', dictionary.token2id)
# 基于词典建立新的【语料库】
corpus = [dictionary.doc2bow(text) for text in texts]
print('语料库：', corpus)

from gensim import corpora
import jieba
text1 = '南方医院无痛人流'
text2 = '北方人流落南方'
texts = [text1, text2]
texts = [jieba.lcut(text) for text in texts]
dictionary = corpora.Dictionary(texts)
# 用【词典】把【搜索词】也转换为【稀疏向量】
keyword = '无痛人流'
kw_vector = dictionary.doc2bow(jieba.lcut(keyword))
print(kw_vector)

from gensim import corpora, models, similarities
import jieba
text1 = '南方医院无痛人流'
text2 = '北方人流浪到南方'
texts = [text1, text2]
texts = [jieba.lcut(text) for text in texts]
dictionary = corpora.Dictionary(texts)
feature_cnt = len(dictionary.token2id.keys())
corpus = [dictionary.doc2bow(text) for text in texts]
# 用语料库来训练TF-IDF模型
tfidf = models.TfidfModel(corpus)
print(tfidf) 
TfidfModel(num_docs=2, num_nnz=9)

from gensim import corpora, models, similarities
import jieba
text1 = '无痛人流并非无痛'
text2 = '北方人流浪到南方'
texts = [text1, text2]
keyword = '无痛人流'
texts = [jieba.lcut(text) for text in texts]
dictionary = corpora.Dictionary(texts)
num_features = len(dictionary.token2id)
corpus = [dictionary.doc2bow(text) for text in texts]
tfidf = models.TfidfModel(corpus)
new_vec = dictionary.doc2bow(jieba.lcut(keyword))
# 相似度计算
index = similarities.SparseMatrixSimilarity(tfidf[corpus], num_features)
print('\nTF-IDF模型的稀疏向量集：')
for i in tfidf[corpus]:
    print(i)
print('\nTF-IDF模型的keyword稀疏向量：')
print(tfidf[new_vec])
print('\n相似度计算：')
sim = index[tfidf[new_vec]]
for i in range(len(sim)):
    print('第', i+1, '句话的相似度为：', sim[i])