自然语言处理项目之新闻主题分类Python实现

'''
#2018-06-10  June Sunday the 23 week, the 161 day SZ
数据来源：链接:https://pan.baidu.com/s/1_w7wOzNkUEaq3KAGco19EQ 密码:87o0
朴素贝叶斯与应用
文本分类问题
经典的新闻主题分类，用朴素贝叶斯做。
#还有点问题。无法正确读取数据。UnicodeDecodeError: 'charmap' codec can't decode byte 0x90 in position 41: character maps to 
folder_path = 'D:/自然语言处理/第2课/Lecture_2/Lecture_2/Naive-Bayes-Text-Classifier/Database/SogouC/Sample'
all_words_list, train_data_list, test_data_list, train_class_list, test_class_list = text_processing(folder_path,test_size=0.2)
'''


import os
import time
import random
import codecs
import jieba  #处理中文
#import nltk  #处理英文
import sklearn
from sklearn.naive_bayes import MultinomialNB
import numpy as np
import pylab as pl
import matplotlib.pyplot as plt

import sys
#reload(sys)
#sys.setdefaultencoding('utf8')
#粗暴的词去重
def make_word_set(words_file):
    words_set = set()
    with open(words_file, 'r') as fp:
        for line in fp.readlines():
            word = line.strip().decode("utf-8")
            if len(word)>0 and word not in words_set: # 去重
                words_set.add(word)
    return words_set
# 文本处理，也就是样本生成过程
def text_processing(folder_path, test_size=0.2):
    folder_list = os.listdir(folder_path)
    data_list = []
    class_list = []

    # 遍历文件夹
    for folder in folder_list:
        new_folder_path = os.path.join(folder_path, folder)
        files = os.listdir(new_folder_path)
        # 读取文件
        j = 1
        for file in files:
            if j > 100: # 怕内存爆掉，只取100个样本文件，你可以注释掉取完
                break
            with open(os.path.join(new_folder_path, file), 'r') as fp:
               raw = fp.read()
            ## 是的，随处可见的jieba中文分词
            #jieba.enable_parallel(4) # 开启并行分词模式，参数为并行进程数，不支持windows
            word_cut = jieba.cut(raw, cut_all=False) # 精确模式，返回的结构是一个可迭代的genertor
            word_list = list(word_cut) # genertor转化为list，每个词unicode格式
            #jieba.disable_parallel() # 关闭并行分词模式
            
            data_list.append(word_list) #训练集list
            class_list.append(folder.decode('utf-8')) #类别
            j += 1
    
    ## 粗暴地划分训练集和测试集
    data_class_list = zip(data_list, class_list)
    random.shuffle(data_class_list)
    index = int(len(data_class_list)*test_size)+1
    train_list = data_class_list[index:]
    test_list = data_class_list[:index]
    train_data_list, train_class_list = zip(*train_list)
    test_data_list, test_class_list = zip(*test_list)
    
    #其实可以用sklearn自带的部分做
    #train_data_list, test_data_list, train_class_list, test_class_list = sklearn.cross_validation.train_test_split(data_list, class_list, test_size=test_size)
    

    # 统计词频放入all_words_dict
    all_words_dict = {}
    for word_list in train_data_list:
        for word in word_list:
            if all_words_dict.has_key(word):
                all_words_dict[word] += 1
            else:
                all_words_dict[word] = 1

    # key函数利用词频进行降序排序
    all_words_tuple_list = sorted(all_words_dict.items(), key=lambda f:f[1], reverse=True) # 内建函数sorted参数需为list
    all_words_list = list(zip(*all_words_tuple_list)[0])

    return all_words_list, train_data_list, test_data_list, train_class_list, test_class_list
def words_dict(all_words_list, deleteN, stopwords_set=set()):
    # 选取特征词
    feature_words = []
    n = 1
    for t in range(deleteN, len(all_words_list), 1):
        if n > 1000: # feature_words的维度1000
            break
            
        if not all_words_list[t].isdigit() and all_words_list[t] not in stopwords_set and 1