樸素貝葉斯應用：垃圾郵件分類

1. 數據準備：收集數據與讀取

2. 數據預處理：處理數據

3. 訓練集與測試集：將先驗數據按必定比例進行拆分。

4. 提取數據特徵，將文本解析爲詞向量 。

5. 訓練模型：創建模型，用訓練數據訓練模型。即根據訓練樣本集，計算詞項出現的機率P(xi|y)，後獲得各種下詞彙出現機率的向量 。

6. 測試模型：用測試數據集評估模型預測的正確率。

混淆矩陣

準確率、精確率、召回率、F值

7. 預測一封新郵件的類別。

8. 考慮如何進行中文的文本分類（期末做業之一）。 

 

要點：

理解樸素貝葉斯算法

理解機器學習算法建模過程

理解文本經常使用處理流程

理解模型評估方法

 

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


# 預處理
def preprocessing(text):
    # text = text.decode("utf-8")
    tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]  # 進行分詞
    stops = stopwords.words('a')  # 去掉停用詞
    tokens = [token for token in tokens if token not in stops]

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

def read_data():
    '''讀取文件並進行預處理'''
    sms=open(r'G:\大三\數據挖掘\SMSS\SMSSpamCollectionjs.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


# 向量化
def xiangliang(x_train, x_test):
    from sklearn.feature_extraction.text import TfidfVectorizer
    vectorizer = TfidfVectorizer(min_df=2, ngram_range=(1, 2), stop_words='a',
                                 strip_accents='unicode')  # ,norm='12'
    x_train = vectorizer.fit_transform(x_train)
    x_test = vectorizer.transform(x_test)
    return x_train, x_test, vectorizer


# 樸素貝葉斯分類器
def beiNB(x_train, y_train, x_test):
    clf = MultinomialNB().fit(x_train, y_train)
    y_nb_pred = clf.predict(x_test)
    return y_nb_pred, clf


def result(vectorizer, clf):
    # 分類結果
    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)