一起学习朴素贝叶斯

P(A|B) = P(AB)/P(B)P(B|A) = P(AB)/P(A)所以：P(A|B) = P(B|A) * P(A) / P(B)

P(B) = P(A1B) + P(A1B) + ··· + P(AnB)     = ∑P(AiB)     = ∑P(B|Ai) * P(Ai) ·······················（i=1，2，····，n）

P(Ak|B) = [ P(Ak) * P(B|Ak) ] / ∑P(B|Ai) * P(Ai） ·········（i=1，2，····，n）

P(Ak|B) = P(Ak) * P(B|Ak)

# sklearn 实现文本分类import osimport random from numpy import *from numpy.ma import arangefrom sklearn.pipeline import Pipeline# TfidfVectorizer 文本特征提取（根据词出现的频率及在语句中的重要性）# HashingVectorizer 文本的特征哈希# CountVectorizer 将文本转换为每个词出现的个数的向量
from sklearn.feature_extraction.text import TfidfVectorizerfrom sklearn.naive_bayes import BernoulliNBfrom sklearn.naive_bayes import MultinomialNBimport matplotlib.pyplot as plt
# 获取样本集def get_dataset():    data = []    for root, dirs, files in os.walk(r'./mix20_rand700_tokens_cleaned/tokens/neg'):        for file in files:            realpath = os.path.join(root, file)            with open(realpath, errors='ignore') as f:                data.append((f.read(), 'bad'))    for root, dirs, files in os.walk(r'./mix20_rand700_tokens_cleaned/tokens/pos'):        for file in files:            realpath = os.path.join(root, file)            with open(realpath, errors='ignore') as f:                data.append((f.read(), 'good'))    random.shuffle(data)    return data    # 处理训练集与测试集
def train_and_test_data(data_):    # 训练集和测试集的比例为7:3    filesize = int(0.7 * len(data_))    # 训练集    train_data_ = [each[0] for each in data_[:filesize]]    train_target_ = [each[1] for each in data_[:filesize]]    # 测试集    test_data_ = [each[0] for each in data_[filesize:]]    test_target_ = [each[1] for each in data_[filesize:]]    return train_data_, train_target_, test_data_, test_target_    """多项式模型：在多项式模型中， 设某文档d=(t1,t2,…,tk)，tk是该文档中出现过的单词，允许重复，则先验概率P(c)= 类c下单词总数/整个训练样本的单词总数类条件概率P(tk|c)=(类c下单词tk在各个文档中出现过的次数之和+1)/(类c下单词总数+|V|)V是训练样本的单词表（即抽取单词，单词出现多次，只算一个），|V|则表示训练样本包含多少种单词。 P(tk|c)可以看作是单词tk在证明d属于类c上提供了多大的证据，而P(c)则可以认为是类别c在整体上占多大比例(有多大可能性)。"""def mnb(train_da, train_tar, test_da, test_tar):    nbc = Pipeline([        ('vect', TfidfVectorizer()),        ('clf', MultinomialNB(alpha=1.0)),    ])    nbc.fit(train_da, train_tar)  # 训练我们的多项式模型贝叶斯分类器    predict = nbc.predict(test_da)  # 在测试集上预测结果    count = 0  # 统计预测正确的结果个数    for left, right in zip(predict, test_tar):        if left == right:            count += 1    # print("多项式模型：", count / len(test_target))    return count / len(test_tar)
"""伯努利模型：P(c)= 类c下文件总数/整个训练样本的文件总数P(tk|c)=(类c下包含单词tk的文件数+1)/(类c下单词总数+2)"""def bnb(train_da, train_tar, test_da, test_tar):    nbc_1 = Pipeline([        ('vect', TfidfVectorizer()),        ('clf', BernoulliNB(alpha=1.0)),    ])    nbc_1.fit(train_da, train_tar)  # 训练我们的多项式模型贝叶斯分类器    predict = nbc_1.predict(test_da)  # 在测试集上预测结果
    count = 0  # 统计预测正确的结果个数    for left, right in zip(predict, test_tar):        if left == right:            count += 1    # print("伯努利模型：", count / len(test_target))    return count / len(test_tar)
# 训练十次x = arange(10)y1 = []y2 = []for i in x:    print(i)    data = get_dataset()    train_data, train_target, test_data, test_target = train_and_test_data(data)    y1.append(mnb(train_data, train_target, test_data, test_target))    y2.append(bnb(train_data, train_target, test_data, test_target))
print(x)print(y1)print(y2)
plt.plot(x, y1, lw='2', label='MultinomialNB')plt.plot(x, y2, lw='2', label='BernoulliNB')plt.legend(loc="upper right")plt.ylim(0, 1)plt.grid(True)plt.show()