用pandas计算条件概率，方差，均值，密度函数

import pandas as pd
data = [[‘男’, 6, 180, 12],
[‘男’, 5.92, 190, 11],
[‘男’, 5.58, 170, 12],
[‘男’, 5.92, 165, 10],
[‘女’, 5, 100, 6],
[‘女’, 5.5, 150, 8],
[‘女’, 5.42, 130, 7],
[‘女’, 5.75, 150, 9]]
df = pd.DataFrame(data, columns=[‘性别’,‘身高（英尺）’,‘体重（磅）’,‘脚掌（英寸）’])
x = pd.Series([6,130,8], index=[‘身高（英尺）’,‘体重（磅）’,‘脚掌（英寸）’])
mean_male = df[df[‘性别’]‘男’].mean()
var_male = df[df[‘性别’]‘男’].var()
mean_formale = df[df[‘性别’]‘女’].mean()
var_formale = df[df[‘性别’]‘女’].var()
df2 = pd.concat((x, mean_male, var_male, mean_formale, var_formale), axis=1, keys=[‘x’, ‘mean_male’, ‘var_male’, ‘mean_formale’, ‘var_formale’])
from math import pi, exp, sqrt
def f(x, mean, var):
return exp(-(x-mean)**2/(2varvar))/sqrt(2pivar*var)
df2[‘px_male’] = df2[[‘x’, ‘mean_male’, ‘var_male’]].apply(lambda x:f(x[‘x’],x[‘mean_male’],x[‘var_male’]), axis=1)
df2[‘px_male’] = df2.apply(lambda x:f2(x[‘x’],x[‘mean_male’],x[‘var_male’]), axis=1)
df2[‘px_formale’] = df2[[‘x’, ‘mean_formale’, ‘var_formale’]].apply(lambda x:f(x[‘x’],x[‘mean_formale’],x[‘var_formale’]), axis=1)
pd.Series([df2[‘px_male’].cumprod()[-1]*pr[‘男’], df2[‘px_formale’].cumprod()[-1]*pr[‘女’]], index=[‘男’,‘女’]).argmax()