1.读取

file_path = r"E:\da3xia\jiqixuexi\SMSSpamCollection"
sms = open(file_path, 'r', encoding='utf-8')
sms_data = []
sms_lable = []
csv_reader = csv.reader(sms, delimiter='\t')
for r in csv_reader:
    sms_lable.append(r[0])
    sms_data.append(preprocessing(r[1]))   #对每封邮件做预处理
sms.close()

2.数据预处理

#预处理
def preprocessing(text):
    tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]   #用nltk做分词
    stops = stopwords.words('english')   #停用词
    tokens = [token for token in tokens if token not in stops]   #去掉停用词
    lemmatizer = WordNetLemmatizer()

    tag = nltk.pos_tag(tokens)   #词性标注
    newtokens = []
    for i, token in enumerate(tokens):
        if token:
            pos = get_wordnet_pos(tag[i][1])
            if pos:
                word = lemmatizer.lemmatize(token, pos)
                newtokens.append(word)

    return newtokens

3.数据划分—训练集和测试集数据划分

from sklearn.model_selection import train_test_split

x_train,x_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=0, stratify=y_train)

x_train, x_test, y_train, y_test = train_test_split(sms_data, sms_label, test_size=0.2, stratify=sms_label)

4.文本特征提取

sklearn.feature_extraction.text.CountVectorizer

https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html?highlight=sklearn%20feature_extraction%20text%20tfidfvectorizer

sklearn.feature_extraction.text.TfidfVectorizer

https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html?highlight=sklearn%20feature_extraction%20text%20tfidfvectorizer#sklearn.feature_extraction.text.TfidfVectorizer

from sklearn.feature_extraction.text import TfidfVectorizer

tfidf2 = TfidfVectorizer()

观察邮件与向量的关系

向量还原为邮件

tfidf2 = TfidfVectorizer()
X_train = tfidf2.fit_transform(x_train)
X_test = tfidf2.transform(x_test)

4.模型选择

from sklearn.naive_bayes import GaussianNB

from sklearn.naive_bayes import MultinomialNB

说明为什么选择这个模型？

mnb = MultinomialNB()
mnb.fit(X_train, y_train)
y_mnb = mnb.predict(X_test)

因为多项式适用于离散。

5.模型评价：混淆矩阵，分类报告

from sklearn.metrics import confusion_matrix

confusion_matrix = confusion_matrix(y_test, y_predict)

说明混淆矩阵的含义

from sklearn.metrics import classification_report

说明准确率、精确率、召回率、F值分别代表的意义

 

cm = confusion_matrix(y_test, y_mnb)
print("混淆矩阵", cm)
cr = classification_report(y_test, y_mnb)
print("分类报告", cr)
print("精确率", (cm[0][0]+cm[1][1])/np.sum(cm))

 

 

 

6.比较与总结

如果用CountVectorizer进行文本特征生成，与TfidfVectorizer相比，效果如何？