分类与监督学习，朴素贝叶斯分类算法

朴素贝叶斯分类算法 实例

利用关于心脏情患者的临床数据集，建立朴素贝叶斯分类模型。

有六个分类变量(分类因子)：性别，年龄、KILLP评分、饮酒、吸烟、住院天数

目标分类变量疾病：–心梗–不稳定性心绞痛

新的实例：–(性别=‘男’，年龄<70, KILLP=‘I'，饮酒=‘是’，吸烟≈‘是”，住院天数<7)

最可能是哪个疾病？

上传演算过程。

编程实现朴素贝叶斯分类算法

利用训练数据集，建立分类模型。

输入待分类项，输出分类结果。

可以心脏情患者的临床数据为例，但要对数据预处理。

import pandas as pd
import numpy as np

dataDF = pd.read_excel(r'data/心脏病患者临床数据.xlsx')

# 数据处理，对男女（男1女0），年龄（<70 -1,70-80 0,>80 1），
# 住院天数(<7 -1,7-14 0,>14 1)三个列进行处理
sex = []
for s in dataDF['性别']:
    if s == '男':
        sex.append(1)
    else:
        sex.append(0)

age = []
for a in dataDF['年龄']:
    if a == '<70':
        age.append(-1)
    elif a == '70-80':
        age.append(0)
    else:
        age.append(1)

days = []
for d in dataDF['住院天数']:
    if d == '<7':
        days.append(-1)
    elif d == '7-14':
        days.append(0)
    else:
        days.append(1)

# 另外生成一份处理后的DF
dataDF2 = dataDF
dataDF2['性别'] = sex
dataDF2['年龄'] = age
dataDF2['住院天数'] = days

# 转为数组用于计算
dataarr = np.array(dataDF)
dataarr

# 用贝叶斯模型判断病人属于哪种病:性别=‘男’，年龄<70, KILLP=1，饮酒=‘是’，吸烟=‘是”，住院天数<7
def beiyesi(sex, age, KILLP, drink, smoke, days):
    # 初始化变量
    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
    
    for line in dataarr:
        if line[6] == '心梗':# 计算在心梗条件下出现各症状的次数
            y1 += 1
            if line[0] == sex:
                x1_y1 += 1
            if line[1] == age:
                x2_y1 += 1
            if line[2] == KILLP:
                x3_y1 += 1
            if line[3] == drink:
                x4_y1 += 1
            if line[4] == smoke:
                x5_y1 += 1
            if line[5] == days:
                x6_y1 += 1
        else: # 计算不稳定性心绞痛条件下出现各症状的次数
            y2 += 1
            if line[0] == sex:
                x1_y2 += 1
            if line[1] == age:
                x2_y2 += 1
            if line[2] == KILLP:
                x3_y2 += 1
            if line[3] == drink:
                x4_y2 += 1
            if line[4] == smoke:
                x5_y2 += 1
            if line[5] == days:
                x6_y2 += 1
    # print('y1:',y1,' y2:',y2)
            
            
    # 计算,转为x|y1, x|y2
    # print('x1_y1:',x1_y1, ' x2_y1:',x2_y1, ' x3_y1:',x3_y1, ' x4_y1:',x4_y1, ' x5_y1:',x5_y1, ' x6_y1:',x6_y1)
    # print('x1_y2:',x1_y2, ' x2_y2:',x2_y2, ' x3_y2:',x3_y2, ' x4_y2:',x4_y2, ' x5_y2:',x5_y2, ' x6_y2:',x6_y2)
    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
    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
    x_y1 = x1_y1 * x2_y1 * x3_y1 * x4_y1 * x5_y1 * x6_y1
    x_y2 = x1_y2 *  x2_y2 * x3_y2 * x4_y2 * x5_y2 * x6_y2

        
    # 计算各症状出现的概率
    x1,x2,x3,x4,x5,x6 = 0,0,0,0,0,0
    for line in dataarr:
        if line[0] == sex:
            x1 += 1
        if line[1] == age:
            x2 += 1
        if line[2] == KILLP:
            x3 += 1
        if line[3] == drink:
            x4 += 1
        if line[4] == smoke:
            x5 += 1
        if line[5] == days:
            x6 += 1
    # print('x1:',x1, ' x2:',x2, ' x3:',x3, ' x4:',x4, ' x5:',x5, ' x6:',x6)
    # 计算
    length = len(dataarr)
    x = x1/length * x2/length * x3/length * x4/length * x5/length * x6/length
    # print('x:',x)
    
    # 分别计算 给定症状下心梗 和 不稳定性心绞痛 的概率
    y1_x = (x_y1)*(y1/length)/x
    # print(y1_x)
    y2_x = (x_y2)*(y2/length)/x
    
    # 判断是哪中疾病的可能性大
    if y1_x > y2_x:
        print('该病人患有心梗的可能性大，可能性为：',y1_x)
    else:
        print('该病人患有不稳定性心绞痛的可能性较大，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
beiyesi(1,-1,1,'是','是',-1)