ks代码助解

代码实现：

data_test_2 = {'gd':[1,1,1,1,1,1,0,0,0,0,0,0,0],'score':[1,2,0,2,2,7,4,5,4,0,4,18,np.nan]}
data_test_2 = pd.DataFrame(data_test_2)

def ks_calc_cross(data,var_col,y_col):
    '''
    功能: 计算KS值，输出对应分割点和累计分布
    输入值:-
    输出值:
    'ks': KS值，'crossdens': 好坏人累积概率分布以及其差值gap
    '''
    ks_df1 = pd.crosstab(data[var_col],data[y_col])
    print(ks_df1)
    print(ks_df1.cumsum(axis=0))
    print(ks_df1.sum())
    ks_df2 = ks_df1.cumsum(axis=0) / ks_df1.sum()
    print(ks_df2)
    ks_df2['gap'] = abs(ks_df2[0] - ks_df2[1])
    ks = ks_df2['gap'].max()
    return ks

ks_value = ks_calc_cross(data_test_2, 'score', 'gd')
print(ks_value)

gd     0  1
score
0.0    1  1
1.0    0  1
2.0    0  3
4.0    3  0
5.0    1  0
7.0    0  1
18.0   1  0
gd     0  1
score
0.0    1  1
1.0    1  2
2.0    1  5
4.0    4  5
5.0    5  5
7.0    5  6
18.0   6  6
gd
0    6
1    6
dtype: int64
gd            0         1
score
0.0    0.166667  0.166667
1.0    0.166667  0.333333
2.0    0.166667  0.833333
4.0    0.666667  0.833333
5.0    0.833333  0.833333
7.0    0.833333  1.000000
18.0   1.000000  1.000000
0.666666666667

庖丁解牛：

import pandas as pd
import numpy as np

data_test_2 = {'gd':[1,1,1,1,1,1,0,0,0,0,0,0,0],'score':[1,2,0,2,2,7,4,5,4,0,4,18,np.nan]}
data_test_2 = pd.DataFrame(data_test_2)
data_test_2

ks_df1 = pd.crosstab(data_test_2['score'],data_test_2['gd'])
ks_df1

ks_df1.cumsum(axis=0)

ks_df1.sum()

ks_df2 = ks_df1.cumsum(axis=0) / ks_df1.sum()
ks_df2

ks_df2['gap'] = abs(ks_df2[0] - ks_df2[1])
ks_df2

ks_df2['gap'].max()