Breaking News: Grepper is joining You.com. Read the official announcement!

java

Zany Zebra answered on June 30, 2023 Popularity 1/10 Helpfulness 1/10

answer java

java

Comment

from __future__ import print_function
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn import feature_extraction
from os import listdir
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans, MiniBatchKMeans
import jieba
import os
import re
import shutil
import glob

labels = []#用于存储所有文本标题
def loadDataset():
    '''导入文本数据集，建立语料库'''
    all_file = listdir('F:/今日新闻/过滤')
    corpus = []
    typetext = open('C:/Users/Yoshine/Desktop/stop.txt',encoding='UTF-8')#加载停用词表
    texts = ['\u3000','\n','']
    for word in typetext:
        word = word.strip()
        texts.append(word)
    for i in range(0,len(all_file)):
       filename = all_file[i]
       filelabel = filename.split('.')[0]
       labels.append(filelabel)#所有文本标题
       file_add = 'F:/今日新闻/过滤/' + filename
       doc = open(file_add,encoding='utf-8').read()
       data = jieba.cut(doc)#对打开的文本进行分词
       data_adj=""
       delete_word = []
       for item in data:#运用停用词表进行过滤
            if item not in texts:
                data_adj= data_adj+item + ' '
            else:
                delete_word.append(item)
       corpus.append(data_adj)
    return corpus

def transform(dataset, n_features=1000):
    '''将文本数据转化为词频矩阵'''
    vectorizer = TfidfVectorizer(max_df=0.5, max_features=n_features, min_df=2, use_idf=True)
    X = vectorizer.fit_transform(dataset)

    return X, vectorizer
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
39
40
41
42
43
44
45
46

Popularity 1/10 Helpfulness 1/10 Language java

Source: blog.csdn.net

Tags: java

Link to this answer
Share Copy Link

Contributed on Jun 30 2023

Zany Zebra

0 Answers Avg Quality 2/10

java

Contents

More Related Answers

java

Grepper

Documentation

Social

Legal

Contact

Oops, You will need to install Grepper and log-in to perform this action.