樸素貝葉斯算法實現垃圾郵件分類

下面使用樸素貝葉斯模型，對郵件進行分類，識別郵件是不是垃圾郵件。

數據下載地址：

鏈接：https://pan.baidu.com/s/1er-AjWm-inaWPf-r0qxnLA 
提取碼：ohsc

import numpy as np
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB


# 預處理數據
def text_parse(big_string):
    token_list = big_string.split()
    return [tok.lower() for tok in token_list if len(tok)>2]


# 去除列表中重複元素，並以列表形式返回
def create_vocab_list(data_set):
    vocab_set = set({})
    for d in data_set:
        vocab_set = vocab_set | set(d)
        
    return list(vocab_set)


# 統計每一文檔（或郵件）在單詞表中出現的次數，並以列表形式返回
def words_to_vec(vocab_list, input_set):
    return_vec = [0] * len(vocab_list)

    for word in input_set:
        if word in vocab_list:
            return_vec[vocab_list.index(word)] += 1
            
    return return_vec



# 樸素貝葉斯主程序

doc_list, class_list, x = [], [], []

for i in range(1, 26):
    # 讀取第i篇垃圾文件，並以列表形式返回
    word_list = text_parse(open('email/spam/{0}.txt'.format(i), encoding='ISO-8859-1').read())
    doc_list.append(word_list)
    class_list.append(1)
    
    # 讀取第i篇非垃圾文件，並以列表形式返回 
    word_list = text_parse(open('email/ham/{0}.txt'.format(i), encoding='ISO-8859-1').read())
    doc_list.append(word_list)
    class_list.append(0)
    
    
# 將數據向量化
vocab_list = create_vocab_list(doc_list)

for word_list in doc_list:
    x.append(words_to_vec(vocab_list, word_list))


# 分割數據爲訓練集和測試集
x_train, x_test, y_train, y_test = train_test_split(x, class_list, test_size=0.25)
x_train, x_test, y_train, y_test = np.array(x_train), np.array(x_test),\
    np.array(y_train), np.array(y_test)


print("x_train: ")
print(x_train[:5])
print("\n")
print("y_train: ")
print(y_train[:5])
print("\n")


# 訓練模型
nb_model = MultinomialNB()
nb_model.fit(x_train, y_train)


# 測試模型效果
y_pred = nb_model.predict(x_test)


# 輸出預測情況
print("正確值：{0}".format(y_test))
print("預測值：{0}".format(y_pred))
print("準確率：%f%%" % (accuracy_score(y_test, y_pred)*100))

結果如下所示，識別正確率爲92.3%，效果還算可以哦。

x_train: 
[[0 0 0 ... 0 0 0]
 [0 0 0 ... 0 0 0]
 [0 0 0 ... 0 0 0]
 [0 0 0 ... 0 0 0]
 [0 0 0 ... 0 0 0]]


y_train: 
[1 0 0 0 1]


正確值：[1 1 1 1 1 1 1 1 1 1 1 0 0]
預測值：[1 1 1 0 1 1 1 1 1 1 1 0 0]
準確率：92.307692%