垃圾邮件分类

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。

8. 考虑如何进行中文的文本分类(期末作业之一)。 

 

要点:

理解朴素贝叶斯算法

理解机器学习算法建模过程

理解文本常用处理流程

理解模型评估方法

#垃圾邮件分类#

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

text = '''As per your request 'Melle Melle (Oru Minnaminunginte Nurungu Vettam)' has been set as your callertune for all Callers. Press *9 to copy your friends Callertune'''

#预处理#
def preprocessing(text):
    #分词#
    tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)] 
#     for sent in nltk.sent_tokenize(text):          #对文本按照句子进行分割
#         for word in nltk.word_tokenize(sent):          #对句子进行分词
#             print(word)
    tokens

    #停用词#
    stops = stopwords.words('english')
    stops

    #去掉停用词
    tokens = [token for token in tokens if token not in stops]
    tokens

    #去掉短于3的词
    tokens = [token.lower() for token in tokens if len(token)>=3]
    tokens

    #词性还原
    lmtzr = WordNetLemmatizer()
    tokens = [lmtzr.lemmatize(token) for token in tokens]
    tokens

    #将剩下的词重新连接成字符串
    preprocessed_text = ' '.join(tokens)
    return preprocessed_text

preprocessing(text)


#读数据#
file_path = r'C:\Users\s2009\Desktop\email.txt'
sms = open(file_path,'r',encoding = 'utf-8')
sms_data = []
sms_target = []
csv_reader = csv.reader(sms,delimiter = '\t')

#将数据分别存入数据列表和目标分类列表#
for line in csv_reader:
    sms_data.append(preprocessing(line[1]))
    sms_target.append(line[0])
sms.close()

print("邮件总数为:",len(sms_target))
sms_target



#将数据分为训练集和测试集#
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(sms_data,sms_target,test_size=0.3,random_state=0,startify=sms_target)
print(len(x_train,len(x_test)))

#将其向量化#
from sklearn.feature_extraction.text import TfidfVectorizer   ##建立数据的特征向量#
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)

import numpy as np               #观察向量
a = X_train.toarray()
#X_test = X_test.toarray()
#X_train.shape
#X_train
 
for i in range(1000):            #输出不为0的列
    for j in range(5984):
        if a[i,j]!=0:
            print(i,j,a[i,j])

#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)

#分类结果显示#
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report

print(y_nb_pred.shape,y_nb_pred)#x_test预测结果
print('nb_confusion_matrix:')
cm=confusion_matrix(y_test,y_nb_pred)#混淆矩阵
print(cm)
print('nb_classification_report:')
cr=classification_report(y_test,y_nb_pred)#主要分类指标的文本报告
print(cr)

feature_name=vectorizer.get_feature_name()#出现过的单词列表
coefs=clf_coef_ #先验概率
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('\t%.4f\t%-15s\t\t%.4f\t%-15s' % (coef_1,fn_1,coef_2,fn_2))

posted @ 2018-12-06 19:46  姚凯雄  阅读(1699)  评论(0编辑  收藏  举报