数据挖掘与算法 第十二次作业

朴素贝叶斯应用：垃圾邮件分类

import csv  # 读数据

file_path = r'C:\Users\s2009\Desktop\垃圾邮箱邮件数据\SMSSpamCollectionjsn.txt'
EmailData = open(file_path,'r',encoding='utf-8')
Email_data = []
Email_target = []
csv_reader = csv.reader(EmailData,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:
    Email_data.append(line[1])
    Email_target.append(line[0])
EmailData.close()  # 把无意义的符号都替换成空格
 

Email_data_clear = []
for line in Email_data:
    # line :'Go until jurong point, crazy.. Available only in bugis n great world la e buffet...'   每一行都去掉无意义符号并按空格分词
    for char in line:
        if char.isalpha() is False:   # 不是字母，发生替换操作:
           
            newString = line.replace(char," ")
    tempList = newString.split(" ")
   
    Email_data_clear.append(tempList)    # 将处理好后的一行数据追加到存放干净数据的列表
 

Email_data_clear2 = []
for line in Email_data_clear:
    tempList = []
    for word in line:
        if word != '' and len(word) > 3 and word.isalpha():
            tempList.append(word)
    tempString = ' '.join(tempList)
    Email_data_clear2.append(tempString)
Email_data_clear = Email_data_clear2   # 去掉长度不大于3的词和没有语义的词
 

from sklearn.model_selection import train_test_split  # 将数据分为训练集和测试集
x_train,x_test,y_train,y_test = train_test_split(Email_data_clear2,Email_target,test_size=0.3,random_state=0,stratify=Email_target)
 

from sklearn.feature_extraction.text import TfidfVectorizer
tfidf = TfidfVectorizer()
X_train = tfidf.fit_transform(x_train)
X_test = tfidf.transform(x_test)  # 建立数据的特征向量
 

import numpy as np
X_train = X_train.toarray()
X_test = X_test.toarray()
X_train.shape# 观察向量

for i in range(X_train.shape[0]):
    for j in range(X_train.shape[1]):
        if X_train[i][j] != 0:
            print(i,j,X_train[i][j])  # 输出不为0的列
 
# 建立模型
from sklearn.naive_bayes import GaussianNB
gnb = GaussianNB()
module = gnb.fit(X_train,y_train)
y_predict = module.predict(X_test)
 
# 输出模型分类的各个指标
from sklearn.metrics import classification_report
cr = classification_report(y_predict,y_test)
print(cr)