垃圾邮件分类2

1.读取

file_path=r'D:PycharmProjectsdataSMSSpamCollection'
sms=open(file_path,'r',encoding='utf-8')
sms_data=[]
sms_label=[]
csv_reader=csv.reader(sms,delimiter='	')
for line in csv_reader:
    sms_label.append(line[0])
    sms_data.append(preprocessing(line[1]))#对每封邮件做预处理
sms.close()

print(sms_label)
print(sms_data)

2.数据预处理

import csv
import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer

print(nltk.__doc__)

def get_wordnet_pos(treebank_tag):
    if treebank_tag.startswith('J'):
        return nltk.corpus.wordnet.ADJ
    elif treebank_tag.startswith('V'):
        return nltk.corpus.wordnet.VERB
    elif treebank_tag.startswith('N'):
        return nltk.corpus.wordnet.NOUN
    elif treebank_tag.startswith('R'):
        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")#停用词
    tokens = [token for token in tokens if token not in stops]#去掉停用词
    tokens = [token.lower() for token in tokens if len(token) >= 3]#将大写字母变为小写

    tag=nltk.pos_tag(tokens)#词性
    lmtzr = WordNetLemmatizer()
    tokens = [lmtzr.lemmatize(token,pos=get_wordnet_pos(tag[i][1])) for i,token in enumerate(tokens)]
    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)

# 按0.8:0.2比例分为训练集和测试集
import numpy as np
from sklearn.model_selection import train_test_split

sms_data = np.array(sms_data)
sms_label = np.array(sms_label)
x_train, x_test, y_train, y_test = train_test_split(sms_data, sms_label, test_size=0.2, random_state=0,
                                                    stratify=sms_label)
print(len(sms_data),len(x_train),len(x_test))
print(x_train)

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.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