朴素贝叶斯应用：垃圾邮件分类

import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
def preprocessing(text):
    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 tokens if token not in stops]
    
    tokens=[token.lower() for token in tokens if len(tokens)>=3]
    lmtzr=WordNetLemmatizer()
    tokens=[lmtzr.lemmatize(token) for token in tokens]
    preprocessed_text=‘ ‘.join(tokens)
    return preprocessed_text

import csv
file_path=r‘F:\duym\ai\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(preprocessing(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))

# 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‘)#,,norm=‘12‘
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)
print(‘nb_confusion_matrix:‘)
cm=confusion_matrix(y_test,y_nb_pred)
print(cm)
print(‘nb_classification_report‘)
cr=classification_report(y_test,y_nb_pred)
print(cr)

feature_names=vectorizer.get_feature_names()
coefs=clf.coef_
intercept=clf.intercept_
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))