十二次作业
1.读取
# 1.读取数据集 def read_dataset(): file_path = r'D:\SMSSpamCollection.txt' 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
# 2、数据预处理 def preprocess(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 wnl = WordNetLemmatizer() tag = nltk.pos_tag(tokens) # 词性 tokens = [wnl.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
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)
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_tes
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
# 4、文本特征提取 # 把文本转化为tf-idf的特征矩阵 def tfidf_dataset(x_train,x_test): tfidf = TfidfVectorizer() X_train = tfidf.fit_transform(x_train) X_test = tfidf.transform(x_test) return X_train, X_test, tfidf # 向量还原成邮件 def revert_mail(x_train, X_train, model): s = X_train.toarray()[0] print("第一封邮件向量表示为:", s) a = np.flatnonzero(X_train.toarray()[0]) # 非零元素的位置(index) print("非零元素的位置:", a) print("向量的非零元素的值:", s[a]) b = model.vocabulary_ # 词汇表 key_list = [] for key, value in b.items(): if value in a: key_list.append(key) # key非0元素对应的单词 print("向量非零元素对应的单词:", key_list) print("向量化之前的邮件:", x_train[0])
5.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?
答 本次邮件数据属于概率性的数据,并不符合正态分布的特征,是不能选择高斯型分布模型,应该选择多项式分布模型
# 5、模型选择 def mnb_model(x_train, x_test, y_train, y_test): mnb = MultinomialNB() mnb.fit(x_train, y_train) pre = mnb.predict(x_test) print("总数:", len(y_test)) print("预测正确数:", (pre == y_test).sum()) print("预测准确率:",sum(pre == y_test) / len(y_test)) return pre
6.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
答:①混淆矩阵 confusion-matrix:
TP(True Positive):真实为0,预测为0
TN(True Negative):真实为1,预测为1
FN(False Negative):真实为0,预测为1
FP(False Positive):真实为1,预测为0
②准确率 accuracy:代表分类器对整个样本判断正确的比重。
③精确率 precision:指被分类器判断正例中的正样本的比重。
④召回率 recall:指被预测为正例的占总的正例的比重。
⑤F值:准确率和召回率的加权调和平均。
# 模型评价:混淆矩阵,分类报告 def class_report(ypre_mnb, y_test): conf_matrix = confusion_matrix(y_test, ypre_mnb) print("=====================================================") print("混淆矩阵:\n", conf_matrix) c = classification_report(y_test, ypre_mnb) print("=====================================================") print("分类报告:\n", c) print("模型准确率:", (conf_matrix[0][0] + conf_matrix[1][1]) / np.sum(conf_matrix))
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?