12.朴素贝叶斯-垃圾邮件分类

1. 读邮件数据集文件，提取邮件本身与标签。

列表

numpy数组

import csv


def read_file():
    file_path = r'D://PycharmProjects//naive_bayes//data//SMSSpamCollection'
    sms = open(file_path, encoding='utf-8')
    csv_reader = csv.reader(sms, delimiter='	')
    for r in csv_reader:
        print(r)
    sms.close()


if __name__ == '__main__':
    read_file()

2.邮件预处理

1. 邮件分句
2. 句子分词
3. 大小写，标点符号，去掉过短的单词
4. 词性还原：复数、时态、比较级
5. 连接成字符串

2.1 传统方法来实现

'''
传统方法实现
'''
# 利用列表、字典、集合等操作进行词频统计
sep = '.,:;?!-_'
exclude = {'a', 'the', 'and', 'i', 'you', 'in'}


def gettxt():
    txt = open(r'D://PycharmProjects//naive_bayes//data//test.txt', 'r').read().lower()  # 大小写
    for ch in sep:
        txt = txt.replace(ch, '')  # 标点符号
    return txt


bigstr = gettxt()  # 获取待统计字符串
biglist = bigstr.split()  # 英文分词列表
bigdict = {}
for word in biglist:
    bigdict[word] = bigdict.get(word, 0) + 1  # 词频统计字典
for word in exclude:
    del(bigdict[word])  # 无意义词
bigitems = list(bigdict.items())
bigitems.sort(key=lambda x: x[1], reverse=True)   # 按词频排序
for i in range(10):
    w, c = bigitems[i]
    print('{0:>10}：{1:<5}'.format(w, c))  # TOP10

2.2 nltk库的安装与使用

pip install nltk

import nltk

nltk.download()     # sever地址改成 http://www.nltk.org/nltk_data/

或

https://github.com/nltk/nltk_data下载gh-pages分支，里面的Packages就是我们要的资源。

将Packages文件夹改名为nltk_data。

或

网盘链接：https://pan.baidu.com/s/1iJGCrz4fW3uYpuquB5jbew    提取码：o5ea

放在用户目录。

----------------------------------

安装完成，通过下述命令可查看nltk版本：

import nltk

print nltk.__doc__

import nltk

print(nltk.__doc__)

2.1 nltk库 分词

nltk.sent_tokenize(text) #对文本按照句子进行分割

nltk.word_tokenize(sent) #对句子进行分词

import nltk

text = "I've been searching for the right words to thank you for this breather. I promise i wont take your help for " 
       "granted and will fulfil my promise. You have been wonderful and a blessing at all times."

sents = nltk.sent_tokenize(text)
sents

nltk.word_tokenize(sents[0])
text.split()

     

2.2 punkt 停用词

from nltk.corpus import stopwords

stops=stopwords.words('english')

*如果提示需要下载punkt

nltk.download(‘punkt’)

或 下载punkt.zip

https://pan.baidu.com/s/1OwLB0O8fBWkdLx8VJ-9uNQ  密码：mema

复制到对应的失败的目录C:UsersAdministratorAppDataRoaming ltk_data okenizers并解压。

from nltk.corpus import stopwords

stops = stopwords.words('english')
print(stops)
print(len(stops))

text = "I've been searching for the right words to thank you for this breather. I promise i wont take your help for " 
        "granted and will fulfil my promise. You have been wonderful and a blessing at all times."
'''
方法一
'''
# tokens = []
# for sent in nltk.sent_tokenize(text):
#     for word in nltk.word_tokenize(sent):
#         tokens.append(word)
# print(tokens)
'''
方法二
'''
tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]
print("分词后的句子：
", tokens)
print("总共有", len(tokens), "个单词")

tokens = [token for token in tokens if token not in stops]
print("去除停用词后的句子：
", tokens)
print("总共有", len(tokens), "个单词")

 

2.3 NLTK 词性标注

nltk.pos_tag(tokens)

2.4 Lemmatisation（词性还原）

from nltk.stem import WordNetLemmatizer

lemmatizer = WordNetLemmatizer()

lemmatizer.lemmatize('leaves') #缺省名词

lemmatizer.lemmatize('best',pos='a')

lemmatizer.lemmatize('made',pos='v')

一般先要分词、词性标注，再按词性做词性还原。

2.5 编写预处理函数

def preprocessing(text):

sms_data.append(preprocessing(line[1])) #对每封邮件做预处理

from nltk.corpus import stopwords
import nltk
import csv


def preprocessing(text):
    """
    预处理
    """
    # text = text.decode("utf-8")
    tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]  # 分词
    stops = stopwords.words('english')  # 使用英文的停用词表
    tokens = [token for token in tokens if token not in stops]  # 去除停用词

    preprocessed_text = ' '.join(tokens)
    return preprocessed_text


def create_dataset():
    """
    导入数据
    """
    file_path = r'D://PycharmProjects//naive_bayes//data//SMSSpamCollection'
    sms = open(file_path, encoding='utf-8')
    sms_data = []
    sms_label = []
    csv_reader = csv.reader(sms, delimiter='	')
    for line in csv_reader:
        sms_label.append(line[0])  # 提取出标签
        sms_data.append(preprocessing(line[1]))  # 提取出特征
    sms.close()
    print("数据集标签：
", sms_label)
    print("数据集特征：
", sms_data)


if __name__ == '__main__':
    create_dataset()

3. 训练集与测试集

4. 词向量

5. 模型

学习链接：https://blog.csdn.net/tinyjian/article/details/79110495

　　　　   https://blog.csdn.net/mingzhiqing/article/details/82971672