朴素贝叶斯应用：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。

import csv
file_path = r"C:/Users/sms.txt"
sms = open(file_path,'r',encoding = 'utf-8')
sms_data = []
sms_label = []
csv_reader = csv.reader(sms,delimiter='\t')
for line in csv_reader:
    sms_label.append(line[0])
    sms_data.append(line[1])
sms.close()
print("邮件总数:",len(sms_label))
print(sms_data)
print(sms_label)

#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)
#print(sms_data)
#print(sms_label)

from sklearn.model_selection import train_test_split#训练集与测试集
a_train,a_test,b_train,b_test = train_test_split(sms_data,sms_label,test_size=0.3,random_state=0,stratify=sms_label)
#print(a_train)
#print(a_test)
#print(b_train)
#print(b_test)

from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer(min_df = 2,ngram_range=(1,2),stop_words='english',strip_accents='unicode',norm='l2')
a1= vectorizer.fit_transform(a_train)
a2= vectorizer.transform(a_test)
#print(a1)
#print(b2)

from sklearn.naive_bayes import MultinomialNB
clf=MultinomialNB().fit(a1,b_train)
y_nb_pred=clf.predict(a2)
#print(y_nb_pred)

#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_matrik：')
cm=confusion_matrix(b_test,y_nb_pred)
print(cm)
print('nb_classification_report:')
cr=classification_report(b_test,y_nb_pred)
print(cr)
feature_names=vectorizer.get_feature_names()
coefs=clf.coef_#先验概率 P(x_i|y),6034 feature_log_prob_
intercept=clf.intercept_#P(y),class_log_prior_:array,shape(n_classes,)
coefs_with_fns=sorted(zip(coefs[0],feature_names))

n=10
top=zip(coefs_with_fns[:n],coefs_with_fns[:-(n+1):-1])
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))

print(sms_label)
print(len(a_train),len(b_test))
print(a1.shape,a2.shape)
print(a_train)
print(a1)

                            
#预测一封新邮件的类别。
new_email=['新邮件']
vectorizer(new_email)
clf.predict(new_email)

 

转载于:https://www.cnblogs.com/a1234tt/p/10078544.html