垃圾邮件分类

Posted 2021-01-25 844115-l

1. 数据准备：收集数据与读取

2. 数据预处理：处理数据

3. 训练集与测试集：将先验数据按一定比例进行拆分。

4. 提取数据特征，将文本解析为词向量 。

5. 训练模型：建立模型，用训练数据训练模型。即根据训练样本集，计算词项出现的概率P(xi|y)，后得到各类下词汇出现概率的向量 。

6. 测试模型：用测试数据集评估模型预测的正确率。

混淆矩阵

准确率、精确率、召回率、F值

7. 预测一封新邮件的类别

 

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

#预处理
def preprocessing(text):
    # text = text.decode("utf-8")
    tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]
    stops = stopwords.words(‘english‘)
    tokens = [token for token in tokens if token not in stops]

    tokens = [token.lower() for token in tokens if len(token) >= 3]
    lmtzr = WordNetLemmatizer()
    tokens = [lmtzr.lemmatize(token) for token in tokens]
    preprocessed_text = ‘ ‘.join(tokens)
    return preprocessed_text

#读取数据集
import csv
file_path=r‘C:UserAdministratorDesktopsms.txt‘
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]))
sms.close();


#按0.7:0.3比例分为训练集和测试集

import numpy as np
sms_data=np.array(sms_data)
sms_label=np.array(sms_label)

from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test = train_test_split(sms_data,sms_label,test_size=0.3,random_state=0,stratify=sms_label)

#将其向量化

    from sklearn.feature_extraction.text import TfidfVectorizer
    vectorizer = TfidfVectorizer(min_df=2, ngram_range=(1, 2), stop_words=‘english‘,
                                 strip_accents=‘unicode‘)  # ,norm=‘12‘
    x_train = vectorizer.fit_transform(x_train)
    x_test = vectorizer.transform(x_test)
    return x_train,x_test,vectorizer

def beiNB(x_train, y_train,x_test):

    # 朴素贝叶斯分类器

from sklearn.navie_bayes import MultinomialNB

clf = MultinomialNB().fit(x_train, y_train) 

y_nb_pred = clf.predict(x_test) 
return y_nb_pred,clf 

def result(vectorizer,clf):

    # 分类结果
    from sklearn.metrics import confusion_matrix
    from sklearn.metrics import classification_report
    print(y_nb_pred.shape, y_nb_pred)
    print(‘nb_confusion_matrix:‘)
    cm = confusion_matrix(y_test, y_nb_pred)
    print(cm)
    cr = classification_report(y_test, y_nb_pred)
    print(cr)

feature_name=vectorizer.get_feature_name()#出现过的单词列表
coefs=clf_coef_ #先验概率 P(x_i|y),6034 feaute_log_prob_
intercept=clf.intercept_
coefs_with_fns=sorted(zip(coefs[0],feature_names))#对数概率p(x_i|y)与单词x_i映射

n=10
top=zip(coefs_with_fns[:n],coefs_with_fns[:-(n+1):-1])#最大的10个与最小的10个单词
for (coef_1,fn_1),(coef_2,fn_2) in top:
    print(‘	%.4f	%-15s		%.4f	%-15s‘ % (coef_1,fn_1,coef_2,fn_2))