KNN针对中文文本分类

改编自博客：

http://blog.csdn.net/github_36326955/article/details/54891204

做个笔记

代码按照1 2 3 4的顺序进行即可：

1.py(corpus_segment.py)

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
"""
@version: python2.7.8
@author: XiangguoSun
@contact: [email protected]
@file: corpus_segment.py
@time: 2017/2/5 15:28
@software: PyCharm
"""
import sys
import os
import jieba
# 配置utf-8输出环境
reload(sys)
sys.setdefaultencoding('utf-8')
# 保存至文件
def savefile(savepath, content):
    with open(savepath, "wb") as fp:
        fp.write(content)
    '''''
    上面两行是python2.6以上版本增加的语法，省略了繁琐的文件close和try操作
    2.5版本需要from __future__ import with_statement
    新手可以参考这个链接来学习http://zhoutall.com/archives/325
    '''
# 读取文件
def readfile(path):
    with open(path, "rb") as fp:
        content = fp.read()
    return content

def corpus_segment(corpus_path, seg_path):
    '''''
    corpus_path是未分词语料库路径
    seg_path是分词后语料库存储路径
    '''
    catelist = os.listdir(corpus_path)  # 获取corpus_path下的所有子目录
    '''''
    其中子目录的名字就是类别名，例如：
    train_corpus/art/21.txt中，'train_corpus/'是corpus_path，'art'是catelist中的一个成员
    '''

    # 获取每个目录（类别）下所有的文件
    for mydir in catelist:
        '''''
        这里mydir就是train_corpus/art/21.txt中的art（即catelist中的一个类别）
        '''
        class_path = corpus_path + mydir + "/"  # 拼出分类子目录的路径如：train_corpus/art/
        seg_dir = seg_path + mydir + "/"  # 拼出分词后存贮的对应目录路径如：train_corpus_seg/art/

        if not os.path.exists(seg_dir):  # 是否存在分词目录，如果没有则创建该目录
            os.makedirs(seg_dir)

        file_list = os.listdir(class_path)  # 获取未分词语料库中某一类别中的所有文本
        '''''
        train_corpus/art/中的
        21.txt,
        22.txt,
        23.txt
        ...
        file_list=['21.txt','22.txt',...]
        '''
        for file_path in file_list:  # 遍历类别目录下的所有文件
            fullname = class_path + file_path  # 拼出文件名全路径如：train_corpus/art/21.txt
            content = readfile(fullname)  # 读取文件内容
            '''''此时，content里面存贮的是原文本的所有字符，例如多余的空格、空行、回车等等，
            接下来，我们需要把这些无关痛痒的字符统统去掉，变成只有标点符号做间隔的紧凑的文本内容
            '''
            content = content.replace("\r\n", "")  # 删除换行
            content = content.replace(" ", "")#删除空行、多余的空格
            content_seg = jieba.cut(content)  # 为文件内容分词
            savefile(seg_dir + file_path, " ".join(content_seg))  # 将处理后的文件保存到分词后语料目录

    print "中文语料分词结束！！！"

'''''
如果你对if __name__=="__main__":这句不懂，可以参考下面的文章
http://imoyao.lofter.com/post/3492bc_bd0c4ce
简单来说如果其他python文件调用这个文件的函数，或者把这个文件作为模块
导入到你的工程中时，那么下面的代码将不会被执行，而如果单独在命令行中
运行这个文件，或者在IDE（如pycharm）中运行这个文件时候，下面的代码才会运行。
即，这部分代码相当于一个功能测试。
如果你还没懂，建议你放弃IT这个行业。
'''
if __name__=="__main__":
    #对训练集进行分词
    corpus_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/train/"  # 未分词分类语料库路径
    seg_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/train_corpus_seg/"  # 分词后分类语料库路径,本程序输出结果
    corpus_segment(corpus_path,seg_path)

    #对测试集进行分词
    corpus_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/answer/"  # 未分词分类语料库路径
    seg_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/test_corpus_seg/"  # 分词后分类语料库路径，本程序输出结果
    corpus_segment(corpus_path,seg_path)

2.py(corpus2Bunch.py)

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
"""
@version: python2.7.8
@author: XiangguoSun
@contact: [email protected]
@file: corpus2Bunch.py
@time: 2017/2/7 7:41
@software: PyCharm
"""
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
import os#python内置的包，用于进行文件目录操作，我们将会用到os.listdir函数
import cPickle as pickle#导入cPickle包并且取一个别名pickle
'''''
事实上python中还有一个也叫作pickle的包，与这里的名字相同了，无所谓
关于cPickle与pickle，请参考博主另一篇博文：
python核心模块之pickle和cPickle讲解
http://blog.csdn.net/github_36326955/article/details/54882506
本文件代码下面会用到cPickle中的函数cPickle.dump
'''
from sklearn.datasets.base import Bunch
#这个您无需做过多了解，您只需要记住以后导入Bunch数据结构就像这样就可以了。
#今后的博文会对sklearn做更有针对性的讲解


def _readfile(path):
    '''''读取文件'''
    #函数名前面带一个_,是标识私有函数
    # 仅仅用于标明而已，不起什么作用，
    # 外面想调用还是可以调用，
    # 只是增强了程序的可读性
    with open(path, "rb") as fp:#with as句法前面的代码已经多次介绍过，今后不再注释
        content = fp.read()
    return content

def corpus2Bunch(wordbag_path,seg_path):
    catelist = os.listdir(seg_path)# 获取seg_path下的所有子目录，也就是分类信息
    #创建一个Bunch实例
    bunch = Bunch(target_name=[], label=[], filenames=[], contents=[])
    bunch.target_name.extend(catelist)
    '''''
    extend(addlist)是python list中的函数，意思是用新的list（addlist）去扩充
    原来的list
    '''
    # 获取每个目录下所有的文件
    for mydir in catelist:
        class_path = seg_path + mydir + "/"  # 拼出分类子目录的路径
        file_list = os.listdir(class_path)  # 获取class_path下的所有文件
        for file_path in file_list:  # 遍历类别目录下文件
            fullname = class_path + file_path  # 拼出文件名全路径
            bunch.label.append(mydir)
            bunch.filenames.append(fullname)
            bunch.contents.append(_readfile(fullname))  # 读取文件内容
            '''''append(element)是python list中的函数，意思是向原来的list中添加element，注意与extend()函数的区别'''
    # 将bunch存储到wordbag_path路径中
    with open(wordbag_path, "wb") as file_obj:
        pickle.dump(bunch, file_obj)
    print "构建文本对象结束！！！"

if __name__ == "__main__":#这个语句前面的代码已经介绍过，今后不再注释
    #对训练集进行Bunch化操作：
    wordbag_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/train_word_bag/train_set.dat"  # Bunch存储路径，程序输出
    seg_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/train_corpus_seg/"  # 分词后分类语料库路径，程序输入
    corpus2Bunch(wordbag_path, seg_path)

    # 对测试集进行Bunch化操作：
    wordbag_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/test_word_bag/test_set.dat"  # Bunch存储路径，程序输出
    seg_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/test_corpus_seg/"  # 分词后分类语料库路径，程序输入
    corpus2Bunch(wordbag_path, seg_path)

3.py(TFIDF_space.py)

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
"""
@version: python2.7.8
@author: XiangguoSun
@contact: [email protected]
@file: TFIDF_space.py
@time: 2017/2/8 11:39
@software: PyCharm
"""
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

from sklearn.datasets.base import Bunch
import cPickle as pickle
from sklearn.feature_extraction.text import TfidfVectorizer

def _readfile(path):
    with open(path, "rb") as fp:
        content = fp.read()
    return content

def _readbunchobj(path):
    with open(path, "rb") as file_obj:
        bunch = pickle.load(file_obj)
    return bunch

def _writebunchobj(path, bunchobj):
    with open(path, "wb") as file_obj:
        pickle.dump(bunchobj, file_obj)

def vector_space(stopword_path,bunch_path,space_path,train_tfidf_path=None):

    stpwrdlst = _readfile(stopword_path).splitlines()
    bunch = _readbunchobj(bunch_path)
    tfidfspace = Bunch(target_name=bunch.target_name, label=bunch.label, filenames=bunch.filenames, tdm=[], vocabulary={})

    if train_tfidf_path is not None:
        trainbunch = _readbunchobj(train_tfidf_path)
        tfidfspace.vocabulary = trainbunch.vocabulary
        vectorizer = TfidfVectorizer(stop_words=stpwrdlst, sublinear_tf=True, max_df=0.5,vocabulary=trainbunch.vocabulary)
        tfidfspace.tdm = vectorizer.fit_transform(bunch.contents)

    else:
        vectorizer = TfidfVectorizer(stop_words=stpwrdlst, sublinear_tf=True, max_df=0.5)
        tfidfspace.tdm = vectorizer.fit_transform(bunch.contents)
        tfidfspace.vocabulary = vectorizer.vocabulary_

    _writebunchobj(space_path, tfidfspace)
    print "tf-idf词向量空间实例创建成功！！！"

if __name__ == '__main__':

    # stopword_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/train_word_bag/hlt_stop_words.txt"#输入的文件
    # bunch_path = "train_word_bag/train_set.dat"#输入的文件
    # space_path = "train_word_bag/tfdifspace.dat"#输出的文件
    # vector_space(stopword_path,bunch_path,space_path)
    #
    # bunch_path = "test_word_bag/test_set.dat"#输入的文件
    # space_path = "test_word_bag/testspace.dat"
    # train_tfidf_path="train_word_bag/tfdifspace.dat"
    # vector_space(stopword_path,bunch_path,space_path,train_tfidf_path)

    stopword_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/train_word_bag/hlt_stop_words.txt"#输入的文件

    train_bunch_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/train_word_bag/train_set.dat"#输入的文件
    space_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/train_word_bag/tfidfspace.dat"#输出的文件
    vector_space(stopword_path,train_bunch_path,space_path)

    train_tfidf_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/train_word_bag/tfidfspace.dat"  # 输入的文件，由上面生成
    test_bunch_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/test_word_bag/test_set.dat"#输入的文件
    test_space_path = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204_tenwhy/chinese_text_classification-master/test_word_bag/testspace.dat"#输出的文件

    vector_space(stopword_path,test_bunch_path,test_space_path,train_tfidf_path)

4.py

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
"""
@version: python2.7.8 
@author: XiangguoSun
@contact: [email protected]
@file: NBayes_Predict.py
@time: 2017/2/8 12:21
@software: PyCharm
"""
import sys
reload(sys)
sys.setdefaultencoding('utf-8')

import cPickle as pickle
from sklearn.naive_bayes import MultinomialNB  # 导入多项式贝叶斯算法


# 读取bunch对象
def _readbunchobj(path):
    with open(path, "rb") as file_obj:
        bunch = pickle.load(file_obj)
    return bunch

# 导入训练集
trainpath = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/train_word_bag/tfidfspace.dat"
train_set = _readbunchobj(trainpath)

# 导入测试集
testpath = "/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/test_word_bag/testspace.dat"
test_set = _readbunchobj(testpath)

# 训练分类器：输入词袋向量和分类标签，alpha:0.001 alpha越小，迭代次数越多，精度越高
# clf = MultinomialNB(alpha=0.1).fit(train_set.tdm, train_set.label)

######################################################
#KNN Classifier
from sklearn.neighbors import KNeighborsClassifier
print '*************************\nKNN\n*************************'
clf = KNeighborsClassifier()#default with k=5
clf.fit(train_set.tdm, train_set.label)

# 预测分类结果
predicted = clf.predict(test_set.tdm)

for flabel,file_name,expct_cate in zip(test_set.label,test_set.filenames,predicted):
    if flabel != expct_cate:
        print file_name,": 实际类别:",flabel," -->预测类别:",expct_cate

print "预测完毕!!!"

# 计算分类精度：
from sklearn import metrics
def metrics_result(actual, predict):
    print '精度:{0:.3f}'.format(metrics.precision_score(actual, predict,average='weighted'))
    print '召回:{0:0.3f}'.format(metrics.recall_score(actual, predict,average='weighted'))
    print 'f1-score:{0:.3f}'.format(metrics.f1_score(actual, predict,average='weighted'))

metrics_result(test_set.label, predicted)

依然使用复旦大学的新闻数据集

运行结果（这里复制一部分）：

/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/test_corpus_seg/C16-Electronics/C16-Electronics37.txt : 实际类别: C16-Electronics  -->预测类别: C11-Space
/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/test_corpus_seg/C16-Electronics/C16-Electronics19.txt : 实际类别: C16-Electronics  -->预测类别: C34-Economy
/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/test_corpus_seg/C16-Electronics/C16-Electronics35.txt : 实际类别: C16-Electronics  -->预测类别: C39-Sports
/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/test_corpus_seg/C16-Electronics/C16-Electronics31.txt : 实际类别: C16-Electronics  -->预测类别: C11-Space
/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/test_corpus_seg/C16-Electronics/C16-Electronics52.txt : 实际类别: C16-Electronics  -->预测类别: C17-Communication
/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/test_corpus_seg/C16-Electronics/C16-Electronics07.txt : 实际类别: C16-Electronics  -->预测类别: C17-Communication
/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/test_corpus_seg/C16-Electronics/C16-Electronics02.txt : 实际类别: C16-Electronics  -->预测类别: C34-Economy
/home/appleyuchi/PycharmProjects/MultiNB/csdn_blog/54891204/chinese_text_classification-master/test_corpus_seg/C16-Electronics/C16-Electronics48.txt : 实际类别: C16-Electronics  -->预测类别: C34-Economy
预测完毕!!!
精度:0.890
召回:0.893
f1-score:0.886