word2vec结合TF_IDF进行多标签文本分类（三）_word2vec和tfidf的结合

本文是在Word2vec的基础上结合TF_IDF对中文文本分类的方式。数据格式见此链接
关于TF_IDF的理论可自行搜索
具体方式参考下图：

from gensim.models import Word2Vec
from tensorflow.keras.callbacks import EarlyStopping
from tensorflow.keras.preprocessing.sequence import pad_sequences
import re
import jieba
from sklearn.preprocessing import MultiLabelBinarizer
from tensorflow.keras.models import Model, load_model, Sequential
from tensorflow.keras.layers import Dense, LSTM, Dropout, Embedding, Bidirectional, SpatialDropout1D
import numpy as np
from sklearn.model_selection import train_test_split
from Attention_LSTM.att import Attention
import matplotlib.pyplot as plt
import jieba.analyse
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer


def clear_character(sentence):
    pattern1 = '[a-zA-Z0-9]'
    pattern2 = re.compile(u'[^\s1234567890' + '\u4e00-\u9fa5]+')
    pattern3 = '[’!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~]+【】'
    line1 = re.sub(pattern1, '', sentence)
    line2 = re.sub(pattern2, '', line1)
    line3 = re.sub(pattern3, '', line2)
    new_Sentence = ''.join(line3.split())
    return new_Sentence


def content_split(segment):
    seg = " ".join(jieba.cut(segment))
    return seg


def rm_stop_word(wordlist, stop):
    filtered_words = [word for word in wordlist if word not in stop]
    return filtered_words


def train_word2vec(x_data):
    model = Word2Vec(x_data, sg=1, size=200, window=5, min_count=0, negative=1, sample=0.01, workers=
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38