python使用朴素贝叶斯算法对数据进行分类代码

以下是使用朴素贝叶斯算法对数据进行分类的Python代码示例：

import numpy as np

#生成样本数据
x = np.array([[1, 'S'], [1, 'M'], [1, 'M'], [1, 'S'], [1, 'S'], 
              [2, 'S'], [2, 'M'], [2, 'M'], [2, 'L'], [2, 'L'], 
              [3, 'L'], [3, 'M'], [3, 'M'], [3, 'L'], [3, 'L']])
y = np.array(['No', 'No', 'Yes', 'Yes', 'No', 'No', 'No', 'Yes', 
              'Yes', 'Yes', 'Yes', 'Yes', 'Yes', 'Yes', 'No'])

#创建字典
def create_dict(data):
    dict = {}
    for i in range(data.shape[1]):
        dict[i] = {}
        for j in range(data.shape[0]):
            if data[j][i] not in dict[i]:
                dict[i][data[j][i]] = 0
            dict[i][data[j][i]] += 1
    return dict

#计算先验概率
def calculate_prior_prob(y):
    dict = {}
    for i in range(len(y)):
        if y[i] not in dict:
            dict[y[i]] = 0
        dict[y[i]] += 1
    for key in dict:
        dict[key] /= len(y)
    return dict

#计算条件概率
def calculate_cond_prob(x, y, dict):
    cond_prob = {}
    for key in dict:
        cond_prob[key] = {}
        for item in dict[key]:
            cond_prob[key][item] = {}
            for i in range(x.shape[1]):
                cond_prob[key][item][i] = 0
    for i in range(len(y)):
        for j in range(x.shape[1]):
            cond_prob[y[i]][x[i][j]][j] += 1
    for key in dict:
        for item in dict[key]:
            for j in range(x.shape[1]):
                cond_prob[key][item][j] /= dict[key][item]
    return cond_prob

#朴素贝叶斯分类
def naive_bayes_predict(x, prior_prob, cond_prob):
    y_pred = []
    for i in range(x.shape[0]):
        max_prob = 0
        max_prob_class = ''
        for key in prior_prob:
            prob = prior_prob[key]
            for j in range(x.shape[1]):
                prob *= cond_prob[key][x[i][j]][j]
            if prob > max_prob:
                max_prob = prob
                max_prob_class = key
        y_pred.append(max_prob_class)
    return y_pred

#使用朴素贝叶斯算法进行分类
dict = create_dict(x)
prior_prob = calculate_prior_prob(y)
cond_prob = calculate_cond_prob(x, y, dict)
y_pred = naive_bayes_predict(x, prior_prob, cond_prob)

#输出分类结果
print('Predicted classes:', y_pred)

该代码使用朴素贝叶斯算法对样本数据进行分类，输出分类结果。其中，实现了创建字典、计算先验概率、计算条件概率和朴素贝叶斯分类等核心步骤。