1.读取

# 1、读取数据集
def read_dataset():
     file_path = r'SMSSpamCollection'
     sms = open(file_path, encoding='utf-8')
     sms_data = []
     sms_label = []
     csv_reader = csv.reader(sms, delimiter='\t')
     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()
     return sms_data, sms_label

2.数据预处理

# 2、数据预处理
def preprocess(text):
     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
     tokens = [token.lower() for token in tokens if len(token) >= 3]  # 大小写，短词
     wnl = WordNetLemmatizer()
     tag = nltk.pos_tag(tokens)  # 词性
     tokens = [wnl.lemmatize(token, pos=get_wordnet_pos(tag[i][1])) for i, token in enumerate(tokens)]  # 词性还原
     preprocessed_text = ' '.join(tokens)
     return preprocessed_text

3.数据划分—训练集和测试集数据划分

from sklearn.model_selection import train_test_split

x_train,x_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=0, stratify=y_train)

# 3、划分数据集
def split_dataset(data, label):
     x_train, x_test, y_train, y_test = train_test_split(data, label, test_size=0.2, random_state=0, stratify=label)
     return x_train, x_test, y_train, y_test

4.文本特征提取

sklearn.feature_extraction.text.CountVectorizer

https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html?highlight=sklearn%20feature_extraction%20text%20tfidfvectorizer

sklearn.feature_extraction.text.TfidfVectorizer

https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html?highlight=sklearn%20feature_extraction%20text%20tfidfvectorizer#sklearn.feature_extraction.text.TfidfVectorizer

from sklearn.feature_extraction.text import TfidfVectorizer

tfidf2 = TfidfVectorizer()

观察邮件与向量的关系

向量还原为邮件

# 4、文本特征提取
# 把文本转化为tf-idf的特征矩阵
def tfidf_dataset(x_train,x_test):
     tfidf = TfidfVectorizer()
     X_train = tfidf.fit_transform(x_train)  
     X_test = tfidf.transform(x_test)
     return X_train, X_test, tfidf

# 向量还原成邮件
def revert_mail(x_train, X_train, model):
    s = X_train.toarray()[0]
    print("第一封邮件向量表示为：", s)
    a = np.flatnonzero(X_train.toarray()[0])  # 非零元素的位置（index）
    print("非零元素的位置:", a)
    print("向量的非零元素的值：", s[a])
    b = model.vocabulary_  # 词汇表
    key_list = []
    for key, value in b.items():
        if value in a:
            key_list.append(key)  # key非0元素对应的单词
    print("向量非零元素对应的单词：", key_list)
    print("向量化之前的邮件：", x_train[0])

5.模型选择

from sklearn.naive_bayes import GaussianNB

from sklearn.naive_bayes import MultinomialNB

说明为什么选择这个模型？

# 5、模型选择
def mnb_model(x_train, x_test, y_train, y_test):
    mnb = MultinomialNB()
    mnb.fit(x_train, y_train)
    pre = mnb.predict(x_test)
    print("总数：", len(y_test))
    print("预测正确数：", (pre == y_test).sum())
    print("预测准确率：",sum(pre == y_test) / len(y_test))
    return pre

6.模型评价：混淆矩阵，分类报告

from sklearn.metrics import confusion_matrix

confusion_matrix = confusion_matrix(y_test, y_predict)

说明混淆矩阵的含义

from sklearn.metrics import classification_report

说明准确率、精确率、召回率、F值分别代表的意义 

# 6、模型评价
def class_report(pre, y_test):
    conf_matrix = confusion_matrix(y_test, pre)
    print("=====================================================")
    print("混淆矩阵：\n", conf_matrix)
    c = classification_report(y_test, pre)
    print("分类报告：\n", c)
    print("模型准确率：", (conf_matrix[0][0] + conf_matrix[1][1]) / np.sum(conf_matrix))

完整代码：

# -*- coding:utf-8 -*-
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import confusion_matrix, classification_report
import numpy as np
 
import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import csv
def get_wordnet_pos(treebank_tag):# 根据词性，生成还原参数pos
     if treebank_tag.startswith('J'):  # adj
        return nltk.corpus.wordnet.ADJ
     elif treebank_tag.startswith('V'):  # v
        return nltk.corpus.wordnet.VERB
     elif treebank_tag.startswith('N'):  # n
         return nltk.corpus.wordnet.NOUN
     elif treebank_tag.startswith('R'):  # adv
        return nltk.corpus.wordnet.ADV
     else:
       return nltk.corpus.wordnet.NOUN
 
 # 预处理
def preprocessing(text):
     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]  # 停用词
     tokens = [token.lower() for token in tokens if len(token) >= 3]  # 大小写，短词
     lmtzr = WordNetLemmatizer()
     tag = nltk.pos_tag(tokens)  # 词性
     tokens = [lmtzr.lemmatize(token, pos=get_wordnet_pos(tag[i][1])) for i, token in enumerate(tokens)]  # 词性还原
     preprocessed_text = ' '.join(tokens)
     return preprocessed_text
 
# 读取数据集
def read_dataset():
     file_path =r'SMSSpamCollection'
     sms = open(file_path, encoding='utf-8')#读取数据
     sms_label = []  # 存储标题
     sms_data = []#存储数据
     csv_reader = csv.reader(sms, delimiter='\t')
     for line in csv_reader:
        sms_label.append(line[0])  # 提取出标签
        sms_data.append(preprocessing(line[1]))  # 对每封邮件做预处理
     sms.close()
     return sms_data, sms_label
 
# 划分数据集
def split_dataset(data, label):
     x_train, x_test, y_train, y_test = train_test_split(data, label, test_size=0.2, random_state=0, stratify=label)
     return x_train, x_test, y_train, y_test
 
# 把原始文本转化为tf-idf的特征矩阵
def tfidf_dataset(x_train,x_test):
     tfidf = TfidfVectorizer()
     X_train = tfidf.fit_transform(x_train)  # X_train用fit_transform生成词汇表
     X_test = tfidf.transform(x_test)  # X_test要与X_train词汇表相同，因此在X_train进行fit_transform基础上进行transform操作
     return X_train, X_test, tfidf
 
# 向量还原邮件
def revert_mail(x_train, X_train, model):
    s = X_train.toarray()[0]
    print("第一封邮件向量表示为：", s)
    # 该函数输入一个矩阵，返回扁平化后矩阵中非零元素的位置（index）
    a = np.flatnonzero(X_train.toarray()[0])  # 非零元素的位置（index）
    print("非零元素的位置:", a)
    print("向量的非零元素的值：", s[a])
    b = model.vocabulary_  # 词汇表
    key_list = []
    for key, value in b.items():
        if value in a:
            key_list.append(key)  # key非0元素对应的单词
    print("向量非零元素对应的单词：", key_list)
    print("向量化之前的邮件：", x_train[0])
 
# 模型选择（根据数据特点选择多项式分布）
def mnb_model(x_train, x_test, y_train, y_test):
    mnb = MultinomialNB()
    mnb.fit(x_train, y_train)
    ypre_mnb = mnb.predict(x_test)
    print("总数：", len(y_test))
    print("预测正确数：", (ypre_mnb == y_test).sum())
    return ypre_mnb
 
# 模型评价：混淆矩阵，分类报告
def class_report(ypre_mnb, y_test):
    conf_matrix = confusion_matrix(y_test, ypre_mnb)
    print("混淆矩阵：\n", conf_matrix)
    c = classification_report(y_test, ypre_mnb)
    print("------------------------------------------")
    print("分类报告：\n", c)
    print("模型准确率：", (conf_matrix[0][0] + conf_matrix[1][1]) / np.sum(conf_matrix))
 
if __name__ == '__main__':
    sms_data, sms_label = read_dataset() # 读取数据集
    x_train, x_test, y_train, y_test = split_dataset(sms_data, sms_label) # 划分数据集
    X_train, X_test,tfidf = tfidf_dataset(x_train, x_test) # 把原始文本转化为tf-idf的特征矩阵
    revert_mail(x_train, X_train, tfidf) # 向量还原成邮件
    y_mnb = mnb_model(X_train, X_test, y_train,y_test) # 模型选择
    class_report(y_mnb, y_test) # 模型评价

6.比较与总结

如果用CountVectorizer进行文本特征生成，与TfidfVectorizer相比，效果如何？

• CountVectorizer：只考虑词汇在文本中出现的频率，属于词袋模型特征。
• TfidfVectorizer： 除了考量某词汇在文本出现的频率，还关注包含这个词汇的所有文本的数量，能够削减高频没有意义的词汇出现带来的影响, 挖掘更有意义的特征。属于Tfidf特征。
• CountVectorizer与TfidfVectorizer相比，对于负类的预测更加准确，而正类的预测则稍逊色。但总体预测正确率也比TfidfVectorizer稍高，相比之下似乎CountVectorizer更适合进行预测。