python实现 Gaussian naive bayes高斯朴素贝叶斯

import numpy as np
import matplotlib.pyplot as plt
from scipy import io
from scipy import stats
import os
from sklearn.metrics import precision_recall_curve
from sklearn.naive_bayes import GaussianNB
def prior(yTrain):
    '''
    :param yTrain: 训练数据集样本的类别标签   <class 'numpy.ndarray'> (218, 1)
    :return: num_classes*1 numpy.ndarray 每个类别的先验概率
    '''
    num_total=yTrain.shape[0]
    # num_class_1=np.sum(yTrain==1)
    # num_class_2 = np.sum(yTrain == 2)
    # num_class_3 = np.sum(yTrain == 3)
    # num_class_4 = np.sum(yTrain == 4)
    # num_class_5 = np.sum(yTrain == 5)

    p=np.zeros((5,1))
    for i in range(p.shape[0]):
        p[i,0]=np.sum(yTrain==i+1)/num_total
    return p

def likelihood(xTrain, yTrain):
    '''
    :param xTrain: 训练数据集的样本特征矩阵
    :param yTrain: 训练数据集样本的标签矩阵
    :return: 条件概率：条件均值和条件方差
            M  numpy.ndarray  shape=[num_feat,num_classes]
            其中的第c列，第m行表示，在当前类别为c的条件下，特征m的均值
            V  numpy.ndarray  shape=[num_feat,num_classes]
            其中的第c列，第m行表示，在当前类别为c的条件下，特征m的方差
    '''

    num_feat=xTrain.shape[1]

    num_classes=5

    M=np.zeros((num_feat,num_classes))
    V=np.ones((num_feat,num_classes))

    for c in range(num_classes):
        # num_class_examples=np.sum(yTrain==c+1)

        # num_class_examples : scalar  表示训练数据集中属于当前类别的样本总数

        temp_class_examples=xTrain[np.where(np.squeeze(yTrain,axis=1)==c+1)]

        # print('temp_class_examples',temp_class_examples.shape)

        # temp_class_examples  numpy.ndarray shape=[num_class_examples,num_feat]
        # 表示训练数据集中属于当前类别的样本的所有特征

        M[:,c]=np.mean(temp_class_examples,axis=0)

        # temp_mean numpy.ndarray shape=[num_feat,] 表示在当前类别下，每个维度特征的平均值