import jieba
from gensim import corpora, models, similarities

# 文本數(shù)據(jù)集
data = ['張文宏談為何這個冬天總生病',
        '“為什么這個冬天我們好像一直在生??？”張文宏這樣說→']

# 分詞
token_list = []
for sentence in data:
    tokens = [word for word in jieba.lcut(sentence)]
    token_list.append(tokens)
print(token_list)

# 詞典，單詞映射唯一ID
dic = corpora.Dictionary(token_list)

# 文本轉(zhuǎn)化為文檔-詞袋（document-term）表示
corpus = [dic.doc2bow(doc) for doc in token_list]
print(corpus)

# 生成模型
lda_model = models.LsiModel(corpus, num_topics=2, id2word=dic)

# 主題及其詞匯
for topic in lda_model.print_topics():
    print(topic)

# 索引
index = similarities.MatrixSimilarity(lda_model[corpus])

query = '為什么這個冬天我們好像一直在生病'

# 預處理
query_bow = dic.doc2bow(jieba.lcut(query))

# 相似性得分
sims = index[lda_model[query_bow]]

sims = sorted(enumerate(sims), key=lambda item: -item[1])

for document_id, similarity in sims:
    print(document_id, similarity)

import jieba
from gensim import corpora, models, similarities
if __name__ == '__main__':
    base_data = [
        "好雨知時節(jié)，當春乃發(fā)生。隨風潛入夜，潤物細無聲。野徑云俱黑，江船火獨明。曉看紅濕處，花重錦官城。",
        "君問歸期未有期，巴山夜雨漲秋池。何當共剪西窗燭，卻話巴山夜雨時。",
        "莫聽穿林打葉聲，何妨吟嘯且徐行。竹杖芒鞋輕勝馬，誰怕？一蓑煙雨任平生。料峭春風吹酒醒，微冷，山頭斜照卻相迎?；厥紫騺硎捝?，歸去，也無風雨也無晴。",
        "天街小雨潤如酥，草色遙看近卻無。最是一年春好處，絕勝煙柳滿皇都。",
        "古木陰中系短篷，杖藜扶我過橋東。沾衣欲濕杏花雨，吹面不寒楊柳風。",
        "少年聽雨歌樓上。紅燭昏羅帳。壯年聽雨客舟中。江闊云低、斷雁叫西風。 而今聽雨僧廬下。鬢已星星也。悲歡離合總無情。一任階前、點滴到天明。",
        "雨里雞鳴一兩家，竹溪村路板橋斜。婦姑相喚浴蠶去，閑看中庭梔子花。",
        "一夕輕雷落萬絲，霽光浮瓦碧參差。有情芍藥含春淚，無力薔薇臥曉枝。"
    ]
    # 1.將base_data中的數(shù)據(jù)進行遍歷后分詞
    base_items = [[i for i in jieba.lcut(item)] for item in base_data]
    print(base_items)
    # 2.生成詞典
    dictionary = corpora.Dictionary(base_items)
    # 3.通過doc2bow稀疏向量生成語料庫
    corpus = [dictionary.doc2bow(item) for item in base_items]
    # 4.通過TF模型算法，計算出tf值
    tf = models.TfidfModel(corpus)
    # 5.通過token2id得到特征數(shù)（字典里面的鍵的個數(shù)）
    num_features = len(dictionary.token2id.keys())
    # 6.計算稀疏矩陣相似度，建立一個索引
    index = similarities.MatrixSimilarity(tf[corpus], num_features=num_features)
    # 7.處理測試數(shù)據(jù)
    test_text = "風雨凄凄，雞鳴喈喈。既見君子，云胡不夷。風雨瀟瀟，雞鳴膠膠。既見君子，云胡不瘳。風雨如晦，雞鳴不已。既見君子，云胡不喜。"
    test_words = [word for word in jieba.cut(test_text)]
    print(test_words)
    # 8.新的稀疏向量
    new_vec = dictionary.doc2bow(test_words)
    # 9.算出相似度
    sims = index[tf[new_vec]]
    print(list(sims))

from jieba import lcut
from gensim.similarities import SparseMatrixSimilarity
from gensim.corpora import Dictionary
from gensim.models import TfidfModel
# 文本集和搜索詞
texts = ['吃雞這里所謂的吃雞并不是真的吃雞，也不是諧音詞刺激的意思',
         '而是出自策略射擊游戲《絕地求生：大逃殺》里的臺詞',
         '我吃雞翅，你吃雞腿']
keyword = '玩過吃雞？今晚一起吃雞'
# 1、將【文本集】生成【分詞列表】
texts = [lcut(text) for text in texts]
# 2、基于文本集建立【詞典】，并獲得詞典特征數(shù)
dictionary = Dictionary(texts)
num_features = len(dictionary.token2id)
# 3.1、基于詞典，將【分詞列表集】轉(zhuǎn)換成【稀疏向量集】，稱作【語料庫】
corpus = [dictionary.doc2bow(text) for text in texts]
# 3.2、同理，用【詞典】把【搜索詞】也轉(zhuǎn)換為【稀疏向量】
kw_vector = dictionary.doc2bow(lcut(keyword))
# 4、創(chuàng)建【TF-IDF模型】，傳入【語料庫】來訓練
tfidf = TfidfModel(corpus)
# 5、用訓練好的【TF-IDF模型】處理【被檢索文本】和【搜索詞】
tf_texts = tfidf[corpus]  # 此處將【語料庫】用作【被檢索文本】
tf_kw = tfidf[kw_vector]
# 6、相似度計算
sparse_matrix = SparseMatrixSimilarity(tf_texts, num_features)
similarities = sparse_matrix.get_similarities(tf_kw)
for e, s in enumerate(similarities, 1):
    print('kw 與 text%d 相似度為：%.2f' % (e, s))

from gensim import corpora, models, similarities
import jieba
text1 = '無痛人流并非無痛'
text2 = '北方人流浪到南方'
texts = [text1, text2]
keyword = '無痛人流'
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))
# 相似度計算
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相似度計算：')
sim = index[tfidf[new_vec]]
for i in range(len(sim)):
    print('第', i+1, '句話的相似度為：', sim[i])