作业十二

#垃圾邮件分类
text='''Congratulations ur awarded 500 of CD vouchers or 125gift guaranteed & Free entry 2 100 wkly draw txt MUSIC to 87066 TnCs www.Ldew.com1win150ppmx3age16'''

import  nltk
from nltk.corpus import stopwords
from  nltk.stem import WordNetLemmatizer


#预处理
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(token)>=2]
    lmtzr=WordNetLemmatizer()
    tokens=[lmtzr.lemmatize(token) for token in tokens]
    preprocessed_text=' '.join(tokens)
    return preprocessed_text

preprocessing((text))


#读取数据集
import csv
file_path=r'F:\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))
sms_label


#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(sms_data,test_size=0.3,random_state=0,startify=sms_label)

#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_text=vectorizer.transform(x_test)

X_train
a=X_train.toarray()
print(a)

for i in range(1000):
    for j in range(5984):
        if a[i,j]!=0:
            print(i,j,a[i,j])

#朴素贝叶斯分类器
from sklearn.navie_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_name=vectorizer.get_feature_name()#出现过的单词列表
coefs=clf_coef_ #先验概率
intercept=clf.intercept_
coefs_with_fns=sorted(zip(coefs[0],feature_names))#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))