垃圾邮件分类

import csv
# 读数据
file_path = r'D:\垃圾邮箱邮件数据\SMSSpamCollectionjsn.txt'
smsData = open(file_path,'r',encoding='utf-8')
E_data = []
E_target = []
csv_reader = csv.reader(smsData,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:
    E_data.append(line[1])
    E_target.append(line[0])
smsData.close()

# 把无意符号替换成空格
E_data_clear = []
for line in E_data:
    # 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(" ")
    # 将处理好后的一行数据追加到存放干净数据的列表
    E_data_clear.append(tempList)

# 去掉长度不大于3的词和没有语义的词
Email_data_clear2 = []
for line in E_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

# 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(Email_data_clear2,E_target,test_size=0.3,random_state=0,stratify=E_target)

# 将其 转化为向量
from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer()
X_train = vectorizer.fit_transform(x_train)
X_test = vectorizer.transform(x_test)

# 观察向量
import numpy as np
X_train = X_train.toarray()
X_test = X_test.toarray()
X_train.shape
# 输出不为0的列
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])

# 贝叶斯分类器
from sklearn.naive_bayes import GaussianNB

clf = GaussianNB()
module = clf.fit(X_train,y_train)
y_predict = module.predict(X_test)

# 输出模型分类
from sklearn.metrics import classification_report
cr = classification_report(y_predict,y_test)
print(cr)
猜你喜欢
