新闻文本分类一简单预测和筛选

一、参考资料

https://blog.csdn.net/qq_28626909/article/details/80382029

二、实验步骤

1.各种读文件，写文件

2.使用jieba分词将中文文本切割

　　对训练集和数据集中的数据进行切割，分别形成切割后的分词文档

3.对处理之后的文本开始用TF-IDF算法进行单词权值的计算

　　

 　　使用已有的算法和接口，生成训练集和数据集的词频矩阵表和矩阵信息表

 4.去掉停用词

　　避开停用词（啊，吗，的等）

 5.贝叶斯预测种类

　　

三、代码实现

1、输入指定文本，预判定文本的种类

# -*- coding: utf-8 -*-
from sklearn.multiclass import OneVsRestClassifier  # 结合SVM的多分类组合辅助器
import sklearn.svm as svm  # SVM辅助器
import jieba
from numpy import *
import os
from sklearn.feature_extraction.text import TfidfTransformer  # TF-IDF向量转换类
from sklearn.feature_extraction.text import CountVectorizer  # 词频矩阵

def readFile(path):
    with open(path, 'r', errors='ignore', encoding='gbk') as file:  # 文档中编码有些问题，所有用errors过滤错误
        content = file.read()
        file.close()
        return content


def saveFile(path, result):
    with open(path, 'w', errors='ignore', encoding='gbk') as file:
        file.write(result)
        file.close()


def segText(inputPath):
    data_list = []
    label_list = []
    fatherLists = os.listdir(inputPath)  # 主目录
    for eachDir in fatherLists:  # 遍历主目录中各个文件夹
        eachPath = inputPath + "/" + eachDir + "/"  # 保存主目录中每个文件夹目录，便于遍历二级文件
        childLists = os.listdir(eachPath)  # 获取每个文件夹中的各个文件
        for eachFile in childLists:  # 遍历每个文件夹中的子文件
            eachPathFile = eachPath + eachFile  # 获得每个文件路径
            content = readFile(eachPathFile)  # 调用上面函数读取内容
            result = (str(content)).replace("
", "").strip()  # 删除多余空行与空格
            cutResult = jieba.cut(result)  # 默认方式分词，分词结果用空格隔开
            # print( " ".join(cutResult))
            label_list.append(eachDir)
            data_list.append(" ".join(cutResult))
    return data_list, label_list


def getStopWord(inputFile):
    stopWordList = readFile(inputFile).splitlines()
    return stopWordList


def getTFIDFMat(train_data, train_label, stopWordList):  # 求得TF-IDF向量
    class0 = ''
    class1 = ''
    class2 = ''
    class3 = ''
    for num in range(len(train_label)):
        if train_label[num] == '体育':
            class0 = class0 + train_data[num]
        elif train_label[num] == '女性':
            class1 = class1 + train_data[num]
        elif train_label[num] == '文学出版':
            class2 = class2 + train_data[num]
        elif train_label[num] == '校园':
            class3 = class3 + train_data[num]
    train = [class0, class1, class2, class3]
    vectorizer = CountVectorizer(stop_words=stopWordList,
                                 min_df=0.5)  # 其他类别专用分类，该类会将文本中的词语转换为词频矩阵，矩阵元素a[i][j] 表示j词在i类文本下的词频
    transformer = TfidfTransformer()  # 该类会统计每个词语的tf-idf权值
    cipin = vectorizer.fit_transform(train)
    tfidf = transformer.fit_transform(cipin)  # if-idf中的输入为已经处理过的词频矩阵
    model = OneVsRestClassifier(svm.SVC(kernel='linear'))
    train_cipin = vectorizer.transform(train_data)
    train_arr = transformer.transform(train_cipin)
    clf = model.fit(train_arr, train_label)

    while 1:
        print('请输入需要预测的文本:')
        a = input()
        sentence_in = [' '.join(jieba.cut(a))]
        b = vectorizer.transform(sentence_in)
        c = transformer.transform(b)
        prd = clf.predict(c)
        print('预测类别：', prd[0])


if __name__ == '__main__':
    data, label = segText('data')
    stopWordList = getStopWord('stop/stopword.txt')  # 获取停用词表
    getTFIDFMat(train_data=data, train_label=label, stopWordList=stopWordList)

2、分批遍历整批文件，筛选出分类错误的文档，并且判断错误率

# -*- coding: utf-8 -*-
# @File  : TFIDF_naive_bayes_wy.py
# @Software: PyCharm
import jieba
from numpy import *
import pickle  # 持久化
import os
from sklearn.feature_extraction.text import TfidfTransformer  # TF-IDF向量转换类
from sklearn.feature_extraction.text import TfidfVectorizer  # TF_IDF向量生成类
from sklearn.datasets.base import Bunch
from sklearn.naive_bayes import MultinomialNB  # 多项式贝叶斯算法
def readFile(path):
    with open(path, 'r', errors='ignore') as file:  # 文档中编码有些问题，所有用errors过滤错误
        content = file.read()
        file.close()
        return content

def saveFile(path, result):
    with open(path, 'w', errors='ignore') as file:
        file.write(result)
        file.close()


def segText(inputPath, resultPath):
    fatherLists = os.listdir(inputPath)  # 主目录
    for eachDir in fatherLists:  # 遍历主目录中各个文件夹
        eachPath = inputPath + eachDir + "/"  # 保存主目录中每个文件夹目录，便于遍历二级文件
        each_resultPath = resultPath + eachDir + "/"  # 分词结果文件存入的目录
        if not os.path.exists(each_resultPath):
            os.makedirs(each_resultPath)
        childLists = os.listdir(eachPath)  # 获取每个文件夹中的各个文件
        for eachFile in childLists:  # 遍历每个文件夹中的子文件
            eachPathFile = eachPath + eachFile  # 获得每个文件路径
            #  print(eachFile)
            content = readFile(eachPathFile)  # 调用上面函数读取内容
            # content = str(content)
            result = (str(content)).replace("
", "").strip()  # 删除多余空行与空格
            # result = content.replace("
","").strip()

            cutResult = jieba.cut(result)  # 默认方式分词，分词结果用空格隔开
            saveFile(each_resultPath + eachFile, " ".join(cutResult))  # 调用上面函数保存文件


def bunchSave(inputFile, outputFile):
    catelist = os.listdir(inputFile)
    bunch = Bunch(target_name=[], label=[], filenames=[], contents=[])
    bunch.target_name.extend(catelist)  # 将类别保存到Bunch对象中
    for eachDir in catelist:
        eachPath = inputFile + eachDir + "/"
        fileList = os.listdir(eachPath)
        for eachFile in fileList:  # 二级目录中的每个子文件
            fullName = eachPath + eachFile  # 二级目录子文件全路径
            bunch.label.append(eachDir)  # 当前分类标签
            bunch.filenames.append(fullName)  # 保存当前文件的路径
            bunch.contents.append(readFile(fullName).strip())  # 保存文件词向量
    with open(outputFile, 'wb') as file_obj:  # 持久化必须用二进制访问模式打开
        pickle.dump(bunch, file_obj)
        # pickle.dump(obj, file, [,protocol])函数的功能：将obj对象序列化存入已经打开的file中。
        # obj：想要序列化的obj对象。
        # file:文件名称。
        # protocol：序列化使用的协议。如果该项省略，则默认为0。如果为负值或HIGHEST_PROTOCOL，则使用最高的协议版本


def readBunch(path):
    with open(path, 'rb') as file:
        bunch = pickle.load(file)
        # pickle.load(file)
        # 函数的功能：将file中的对象序列化读出。
    return bunch


def writeBunch(path, bunchFile):
    with open(path, 'wb') as file:
        pickle.dump(bunchFile, file)


def getStopWord(inputFile):
    stopWordList = readFile(inputFile).splitlines()
    return stopWordList


def getTFIDFMat(inputPath, stopWordList, outputPath,
                tftfidfspace_path,tfidfspace_arr_path,tfidfspace_vocabulary_path):  # 求得TF-IDF向量
    bunch = readBunch(inputPath)
    tfidfspace = Bunch(target_name=bunch.target_name, label=bunch.label, filenames=bunch.filenames, tdm=[],
                       vocabulary={})
    '''读取tfidfspace'''
    tfidfspace_out = str(tfidfspace)
    saveFile(tftfidfspace_path, tfidfspace_out)
    # 初始化向量空间
    vectorizer = TfidfVectorizer(stop_words=stopWordList, sublinear_tf=True, max_df=0.5)
    transformer = TfidfTransformer()  # 该类会统计每个词语的TF-IDF权值
    # 文本转化为词频矩阵，单独保存字典文件
    tfidfspace.tdm = vectorizer.fit_transform(bunch.contents)
    tfidfspace_arr = str(vectorizer.fit_transform(bunch.contents))
    saveFile(tfidfspace_arr_path, tfidfspace_arr)
    tfidfspace.vocabulary = vectorizer.vocabulary_  # 获取词汇
    tfidfspace_vocabulary = str(vectorizer.vocabulary_)
    saveFile(tfidfspace_vocabulary_path, tfidfspace_vocabulary)
    '''over'''
    writeBunch(outputPath, tfidfspace)


def getTestSpace(testSetPath, trainSpacePath, stopWordList, testSpacePath,
                 testSpace_path,testSpace_arr_path,trainbunch_vocabulary_path):
    bunch = readBunch(testSetPath)
    # 构建测试集TF-IDF向量空间
    testSpace = Bunch(target_name=bunch.target_name, label=bunch.label, filenames=bunch.filenames, tdm=[],
                      vocabulary={})
    '''
       读取testSpace
       '''
    testSpace_out = str(testSpace)
    saveFile(testSpace_path, testSpace_out)
    # 导入训练集的词袋
    trainbunch = readBunch(trainSpacePath)
    # 使用TfidfVectorizer初始化向量空间模型  使用训练集词袋向量
    vectorizer = TfidfVectorizer(stop_words=stopWordList, sublinear_tf=True, max_df=0.5,
                                 vocabulary=trainbunch.vocabulary)
    transformer = TfidfTransformer()
    testSpace.tdm = vectorizer.fit_transform(bunch.contents)
    testSpace.vocabulary = trainbunch.vocabulary
    testSpace_arr = str(testSpace.tdm)
    trainbunch_vocabulary = str(trainbunch.vocabulary)
    saveFile(testSpace_arr_path, testSpace_arr)
    saveFile(trainbunch_vocabulary_path, trainbunch_vocabulary)
    # 持久化
    writeBunch(testSpacePath, testSpace)


def bayesAlgorithm(trainPath, testPath,tfidfspace_out_arr_path,
                   tfidfspace_out_word_path,testspace_out_arr_path,
                   testspace_out_word_apth):
    trainSet = readBunch(trainPath)
    testSet = readBunch(testPath)
    clf = MultinomialNB(alpha=0.001).fit(trainSet.tdm, trainSet.label)
    # alpha:0.001 alpha 越小，迭代次数越多，精度越高
    # print(shape(trainSet.tdm))  #输出单词矩阵的类型
    # print(shape(testSet.tdm))
    '''处理bat文件'''
    tfidfspace_out_arr = str(trainSet.tdm)  # 处理
    tfidfspace_out_word = str(trainSet)
    saveFile(tfidfspace_out_arr_path, tfidfspace_out_arr)  # 矩阵形式的train_set.txt
    saveFile(tfidfspace_out_word_path, tfidfspace_out_word)  # 文本形式的train_set.txt

    testspace_out_arr = str(testSet)
    testspace_out_word = str(testSet.label)
    saveFile(testspace_out_arr_path, testspace_out_arr)
    saveFile(testspace_out_word_apth, testspace_out_word)

    '''处理结束'''
    predicted = clf.predict(testSet.tdm)
    total = len(predicted)
    rate = 0
    for flabel, fileName, expct_cate in zip(testSet.label, testSet.filenames, predicted):
        if flabel != expct_cate:
            rate += 1
            print(fileName, ":实际类别：", flabel, "-->预测类别：", expct_cate)
    print("erroe rate:", float(rate) * 100 / float(total), "%")

# 分词，第一个是分词输入，第二个参数是结果保存的路径

if __name__ == '__main__':
    datapath = "./data/"  #原始数据路径
    stopWord_path = "./stop/stopword.txt"#停用词路径
    test_path = "./test/"            #测试集路径
    '''
    以上三个文件路径是已存在的文件路径，下面的文件是运行代码之后生成的文件路径
    dat文件是为了读取方便做的，txt文件是为了给大家展示做的，所以想查看分词，词频矩阵
    词向量的详细信息请查看txt文件，dat文件是通过正常方式打不开的
    '''
    test_split_dat_path =  "./test_set.dat" #测试集分词bat文件路径
    testspace_dat_path ="./testspace.dat"   #测试集输出空间矩阵dat文件
    train_dat_path = "./train_set.dat"  # 读取分词数据之后的词向量并保存为二进制文件
    tfidfspace_dat_path = "./tfidfspace.dat"  #tf-idf词频空间向量的dat文件
    '''
    以上四个dat文件路存储信息
    '''
    test_split_path = './split/test_split/'   #测试集分词路径
    split_datapath = "./split/split_data/"  # 对原始数据分词之后的数据路径
    '''
    以上两个路径是分词之后的文件路径
    '''
    tfidfspace_path = "./tfidfspace.txt"  # 将TF-IDF词向量保存为txt，方便查看
    tfidfspace_arr_path = "./tfidfspace_arr.txt"  # 将TF-IDF词频矩阵保存为txt，方便查看
    tfidfspace_vocabulary_path = "./tfidfspace_vocabulary.txt"  # 将分词的词汇统计信息保存为txt，方便查看
    testSpace_path = "./testSpace.txt"  #测试集分词信息
    testSpace_arr_path = "./testSpace_arr.txt"  #测试集词频矩阵信息
    trainbunch_vocabulary_path = "./trainbunch_vocabulary.txt" #所有分词词频信息
    tfidfspace_out_arr_path = "./tfidfspace_out_arr.txt"   #tfidf输出矩阵信息
    tfidfspace_out_word_path = "./tfidfspace_out_word.txt" #单词形式的txt
    testspace_out_arr_path = "./testspace_out_arr.txt"     #测试集输出矩阵信息
    testspace_out_word_apth ="./testspace_out_word.txt"    #测试集单词信息
    '''
    以上10个文件是dat文件转化为txt文件
    '''

    #输入训练集
    segText(datapath,#读入数据
            split_datapath)#输出分词结果
    bunchSave(split_datapath,#读入分词结果
              train_dat_path)  # 输出分词向量
    stopWordList = getStopWord(stopWord_path)  # 获取停用词表
    getTFIDFMat(train_dat_path, #读入分词的词向量
                stopWordList,    #获取停用词表
                tfidfspace_dat_path, #tf-idf词频空间向量的dat文件
                tfidfspace_path, #输出词频信息txt文件
                tfidfspace_arr_path,#输出词频矩阵txt文件
                tfidfspace_vocabulary_path)  #输出单词txt文件
    '''
    测试集的每个函数的参数信息对照上面的各个信息，是基本相同的
    '''
    #输入测试集
    segText(test_path,
            test_split_path)  # 对测试集读入文件，输出分词结果
    bunchSave(test_split_path,
              test_split_dat_path)  #
    getTestSpace(test_split_dat_path,
                 tfidfspace_dat_path,
                 stopWordList,
                 testspace_dat_path,
                 testSpace_path,
                 testSpace_arr_path,
                 trainbunch_vocabulary_path)# 输入分词文件，停用词，词向量，输出特征空间(txt,dat文件都有)
    bayesAlgorithm(tfidfspace_dat_path,
                   testspace_dat_path,
                   tfidfspace_out_arr_path,
                   tfidfspace_out_word_path,
                   testspace_out_arr_path,
                   testspace_out_word_apth)

四、遇到的问题

1、遇到使用命令下载包的时候，提示安装成功，但是报错信息仍为未安装某包

　　原因：安装包的路径并没有在当前使用的环境下，更改指定的下载路径即可