1.读取
def read_dataset():
file_path = r'SMSSpamCollection'
sms = open(file_path, encoding='utf-8')
sms_data = []
sms_label = []
csv_reader = csv.reader(sms, delimiter='\t')
for line in csv_reader:
sms_label.append(line[0]) # 提取出标签
sms_data.append(preprocessing(line[1])) # 提取出特征
sms.close()
return sms_data, sms_label
2.数据预处理
def preprocessing(text):
tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)] # 分词
stops = stopwords.words('english') # 使用英文的停用词表
tokens = [token for token in tokens if token not in stops] # 去除停用词
tokens = [token.lower() for token in tokens if len(token) >= 3] # 大小写,短词
lmtzr = WordNetLemmatizer()
tag = nltk.pos_tag(tokens) # 词性
tokens = [lmtzr.lemmatize(token, pos=get_wordnet_pos(tag[i][1])) for i, token in enumerate(tokens)] # 词性还原
preprocessed_text = ' '.join(tokens)
return preprocessed_text
3.数据划分—训练集和测试集数据划分
def split_dataset(data, label):
x_train, x_test, y_train, y_test = train_test_split(data, label, test_size=0.2, random_state=0, stratify=label)
return x_train, x_test, y_train, y_test
4.文本特征提取
sklearn.feature_extraction.text.CountVectorizer
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
def tfidf_dataset(x_train,x_test):
tfidf = TfidfVectorizer()
X_train = tfidf.fit_transform(x_train) # X_train用fit_transform生成词汇表
X_test = tfidf.transform(x_test)
return X_train, X_test, tfidf
4.模型选择
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB
def mnb_model(x_train, x_test, y_train, y_test):
mnb = MultinomialNB()
mnb.fit(x_train, y_train)
ypre_mnb = mnb.predict(x_test)
print("总数:", len(y_test))
print("预测正确数:", (ypre_mnb == y_test).sum())
return ypre_mnb
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
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?
CountVectorizer 与 TfidfVectorizer,这两个类都是特征数值计算的常见方法。对于每一个训练文本,CountVectorizer 只考虑每种词汇在该训练文本中出现的频率,而TfidfVectorizer 除了考量某一词汇在当前训练文本中出现的频率之外,同时关注包含这个词汇的其它训练文本数目的倒数。相比之下,训练文本的数量越多,TfidfVectorizer 这种特征量化方式就更有优势。