分类与监督学习，朴素贝叶斯分类算法(代码片段)

import numpy as np
import pandas
data=pandas.read_excel(‘心脏病患者临床数据.xlsx‘)
data
#对性别进行处理（男为0，女为1）
xingbie=[]
for i in data[‘性别‘]:
    if i ==‘男‘:
        xingbie.append(0)
    else:
        xingbie.append(1)
#对年龄段进行预处理（<70为1，70-80为2，>80为3）
ages=[]
for j in data[‘年龄‘]:
    if j ==‘<70‘:
        ages.append(1)
    elif j ==‘70-80‘:
        ages.append(2)
    else:
        ages.append(3)
#对住院天数进行处理（<70为1，7-14为2，>14为3）
days=[]
for k in data[‘住院天数‘]:
    if k==‘<7‘:
        days.append(1)
    elif k==‘7-14‘:
        days.append(2)
    else:
        days.append(3)
#处理后的数据
data1=data
data1[‘性别‘]=xingbie
data1[‘年龄‘]=ages
data1[‘住院天数‘]=days
#将数据转成数组
data_arr=np.array(data1)
data_arr
#利用贝叶斯算法对给定的组别进行分类
def NB(xingbie, ages, KILLP, drink, smoke, days):
    #初始化值
    x1_y1,x2_y1,x3_y1,x4_y1,x5_y1,x6_y1 = 0,0,0,0,0,0
    x1_y2,x2_y2,x3_y2,x4_y2,x5_y2,x6_y2 = 0,0,0,0,0,0
    y1 = 0
    y2 = 0
    #计算为心梗的概率
    for a in data_arr:
        if a[6]==‘心梗‘:
            y1+=1
            if a[0]==xingbie:
                x1_y1+=1
            if a[1]==ages:
                x2_y1+=1
            if a[2]==KILLP:
                x3_y1+=1
            if a[3]==drink:
                x4_y1+=1
            if a[4]==smoke:
                x5_y1+=1
            if a[5]==days:
                x6_y1+=1
        else:#计算患有不稳定性心绞痛的概率
            y2+=1
            if a[0]==xingbie:
                x1_y2+=1
            if a[1]==ages:
                x2_y2+=1
            if a[2]==KILLP:
                x3_y2+=1
            if a[3]==drink:
                x4_y2+=1
            if a[4]==smoke:
                x5_y2+=1
            if a[5]==days:
                x6_y2+=1
    #计算每种症状在心梗下的概率
    x1_y1, x2_y1, x3_y1, x4_y1, x5_y1, x6_y1 = x1_y1/y1, x2_y1/y1, x3_y1/y1, x4_y1/y1, x5_y1/y1, x6_y1/y1
    #计算每种症状在不稳定性心绞痛的概率
    x1_y2, x2_y2, x3_y2, x4_y2, x5_y2, x6_y2 = x1_y2/y2, x2_y2/y2, x3_y2/y2, x4_y2/y2, x5_y2/y2, x6_y2/y2
    #多个症状在心梗下的概率
    x_y1 = x1_y1 * x2_y1 * x3_y1 * x4_y1 * x5_y1 * x6_y1
    #多个症状在不稳定性心绞痛下的概率
    x_y2 = x1_y2 *  x2_y2 * x3_y2 * x4_y2 * x5_y2 * x6_y2
    ##初始化各个特征x的值
    x1,x2,x3,x4,x5,x6=0,0,0,0,0,0
    for a in data_arr:
        if a[0]==xingbie:
            x1+=1
        if a[1]==ages:
            x2+=1
        if a[2]==KILLP:
            x3+=1
        if a[3]==drink:
            x4+=1
        if a[4]==smoke:
            x5+=1
        if a[5]==days:
            x6+=1
    lens = len(data_arr)
    #所有x的可能性
    x = x1/lens * x2/lens * x3/lens * x4/lens * x5/lens* x6/lens
    # 分别计算心梗和不稳定性心绞痛的概率
    y1_x = (x_y1)*(y1/lens)/x
    print(y1_x)
    y2_x = (x_y2)*(y2/lens)/x
    print(y2_x)
    # 判断是哪中疾病的可能更大
    if y1_x > y2_x:
        print(‘病人患心梗的可能更大，可能性为：‘,y1_x)
    else:
        print(‘病人患不稳定性心绞痛的可能更大，可能性为：‘,y2_x)

# 判断：性别=‘男’，年龄<70, KILLP=1，饮酒=‘是’，吸烟=‘是”，住院天数<7
NB(0,1,1,‘是‘,‘是‘,1)