代码语言：python

所属分类：其他

代码描述：python jieba Tfidf提取文章文本摘要代码，用到了sklearn中的TfidfTransformer转换器。

代码标签： python jieba Tfidf 提取 文章 文本 摘要 代码

下面为部分代码预览，完整代码请点击下载或在bfwstudio webide中打开

#!/usr/local/python3/bin/python3
# -*- coding: utf-8 -*
# coding:utf-8
import jieba
import numpy as np
import collections
from sklearn import feature_extraction  
from sklearn.feature_extraction.text import TfidfTransformer  
from sklearn.feature_extraction.text import CountVectorizer  


def split_sentence(text, punctuation_list='!?。！？'):
    """
    将文本段安装标点符号列表里的符号切分成句子，将所有句子保存在列表里。
    """
    sentence_set = []
    inx_position = 0         #索引标点符号的位置
    char_position = 0        #移动字符指针位置
    for char in text:
        char_position += 1
        if char in punctuation_list:
            next_char = list(text[inx_position:char_position+1]).pop()
            if next_char not in punctuation_list:
                sentence_set.append(text[inx_position:char_position])
                inx_position = char_position
    if inx_position < len(text):
        sentence_set.append(text[inx_position:])

    sentence_with_index = {i:sent for i,sent in enumerate(sentence_set)} #dict(zip(sentence_set, range(len(sentences))))
    return sentence_set,sentence_with_index

def get_tfidf_matrix(sentence_set,stop_word):
    corpus = []
    for sent in sentence_set:
        sent_cut = jieba.cut(sent)
        sent_list = [word for word in sent_cut if word not in stop_word]
        sent_str = ' '.join(sent_list)
        corpus.append(sent_str)

    vectorizer=CountVectorizer()
    transformer=TfidfTransformer()
    tfidf=transformer.fit_transform(vectorizer.fit_transform(corpus))
    # word=vectorizer.get_feature_names()
    tfidf_matrix=tfidf.toarray()
    return np.array(tfidf_matrix)

def get_sentence_with_words_weight(tfidf_matrix):
    sentence_with_words_weight = {}
    for i in range(len(tfidf_matrix)):
        sentence_with_words_weight[i] = np.sum(tfidf_matrix[i])

    max_weight = max(sentence_with_words_weight.values()) #归一化
    min_weight = min(sentence_with_words_weight.values())
    for key in sentence_with_words_weight.keys():
        x = sentence_with_words_weight[key]
        sentence_with_words_weight[key] = (x-min_weight)/(max_weight-min_weight)

    return sentence_with_words_weight

def get_sentence_with_position_weight(sentence_set):
    sentence_with_position_weight = {}
    total_sent = len(sentence_set)
    for i in range(total_sent):
        sentence_with_position_weight[i] = (total_sent - i) / total_sent
    return sentence_with_position_weight

def similarity(sent1,sent2):
    """
    计算余弦相似度
    """
    return np.sum(sent1 * sent2) / 1e-6+(np.sqrt(n.........完整代码请登录后点击上方下载按钮下载查看

网友评论0

取消

评论提交中...

提交评论