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

 

import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer

#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)]
    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

#讀取數據集
import csv
file_path=r'C:\User\Administrator\Desktop\sms.txt'
sms=open(file_path,'r',encoding='utf-8')
sms_data=[]
sms_label=[]
csv_reader=csv.reader(sms,delimiter='\t')
for line in csv_reader:
    sms_label.append(line[0])
    sms_data.append(preprocessing(line[1]))
sms.close();


#按0.7:0.3比例分爲訓練集和測試集

import numpy as np
sms_data=np.array(sms_data)
sms_label=np.array(sms_label)

from sklearn.model_selection import train_test_split

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)

#將其向量化

    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):

    # 樸素貝葉斯分類器

from sklearn.navie_bayes import MultinomialNB

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_name=vectorizer.get_feature_name()#出現過的單詞列表
coefs=clf_coef_ #先驗機率 P(x_i|y),6034 feaute_log_prob_
intercept=clf.intercept_
coefs_with_fns=sorted(zip(coefs[0],feature_names))#對數機率p(x_i|y)與單詞x_i映射

n=10
top=zip(coefs_with_fns[:n],coefs_with_fns[:-(n+1):-1])#最大的10個與最小的10個單詞
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))