from sklearn.metrics import confusion_matrix from sklearn.metrics import classification_report from sklearn.naive_bayes import MultinomialNB from sklearn.model_selection import train_test_split from sklearn.feature_extraction.text import TfidfVectorizer import csv file_path=r'SMSSpamCollectionjsn.txt' a=open(file_path,'r',encoding='utf-8')#预处理 a_data=[] a_label=[] csv_reader=csv.reader(a,delimiter='\t') for line in csv_reader: a_label.append(line[0]) a_data.append(line[1]) a.close() def preprocessing(text): preprocessing_text= text return preprocessing_text #按0.7:0.3比例分为训练集和测试集 X_train, X_test, Y_train, Y_test = train_test_split(a_data, a_label, test_size=0.3, random_state=0,stratify=a_label) ectorizer=TfidfVectorizer(min_df=2,ngram_range=(1,2),stop_words='english',strip_accents='unicode',norm='l2') X_train=vectorizer.fit_transform(X_train) X_test=vectorizer.transform(X_test) clf = MultinomialNB().fit(X_train,Y_train) y_nb_pred = clf.predict(X_test) # 分类结果显示 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_repert:') 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_ily),6034 feature_log_preb intercept = clf.intercept_ # P(y),class_log_prior : array,shape(n... 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]) 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))
辣鸡邮件
猜你喜欢
转载自www.cnblogs.com/lbjdaxiong/p/10073893.html
今日推荐
周排行