朴素贝叶斯应用：垃圾邮件分类

!pip install nltk

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 token not in stops]
    
    
    tokens=[token.lower() for tokens in tokens if len(token)>=3]
    lmtzr= WordNetsLemmatize()
    tokens=[lmtzr.lemmatize(token) for token in tokens]
    preprocessed_text=‘‘.jion(tokens)
    return preprocessed_text


##读取数据集
import csv
file_path = r"D:\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()

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)
print(len(sms_data),len(x_train),len(x_test))
x_train


结果：

##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‘)
X_train=vectorizer.fit_transform(x_train)
X_test=vectorizer.transform(x_test)


##朴素贝叶斯分类器
from sklearn.naive_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的预测结果
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_names=vectorizer.get_feature_names()   ##出现过的单词列表
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,)Smoothed empirical log probability for each class
coefs_with_fns=sorted(zip(coefs[0],feature_name))  ##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))  ##查看准确率、召回率、F值、精确率


结果：

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