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。

8. 考虑如何进行中文的文本分类（期末作业之一）。 

 

要点：

理解朴素贝叶斯算法

理解机器学习算法建模过程

理解文本常用处理流程

理解模型评估方法

 

import csv
from sklearn.model_selection import train_test_split
import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from sklearn.naive_bayes import  MultinomialNB


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 tokens if token not in stops]

    tokens = [token.lower() for token in tokens if len(token) >= 3]
    lmtzr = WordNetLemmatizer()
    tokens = [lmtzr.lemmatize(token) for token in tokens]
    preprocessed_text = ' '.join(tokens)
    return preprocessed_text

def read_data():
    '''读取文件并进行预处理'''
    sms=open(r'H:\数据挖掘算法\12.3\sms.txt','r',encoding='utf-8')
    sms_data = []
    sms_label = []
    csv_reader=csv.reader(sms,delimiter='\t')
    nltk.download('punkt')
    nltk.download('wordnet')
    for line in csv_reader:
        print(line)
        sms_label.append(line[0])
        sms_data.append(preprocessing(line[1]))
    sms.close()
    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))
    print(x_train)
    return sms_data,sms_label,x_train,x_test,y_train,y_test

def xiangliang(x_train,x_test):
    # 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)
    return x_train,x_test,vectorizer

def beiNB(x_train, y_train,x_test):
    # 朴素贝叶斯分类器
    clf = MultinomialNB().fit(x_train, y_train)
    y_nb_pred = clf.predict(x_test)
    return y_nb_pred,clf

def result(vectorizer,clf):
    # 分类结果
    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)
    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))

if __name__ == '__main__':
    sms_data,sms_lable,x_train,x_test,y_train,y_test = read_data()
    X_train,X_test,vectorizer = xiangliang(x_train,x_test)
    y_nb_pred,clf = beiNB(X_train, y_train,X_test)
    result(vectorizer,clf)