画ks曲线能得到阈值和精确ks

尝试模型代码
1、画出p值

实现ks计算

from sklearn.metrics import roc_curve
from sklearn.pipeline import make_pipeline
import matplotlib
import matplotlib.pyplot as plt
matplotlib.rcParams['font.family']='SimHei'

实现ks计算

from sklearn.metrics import roc_curve
import matplotlib.pyplot as plt
import seaborn as sns
plt.rcParams['font.sans-serif'] = ['SimHei']#中文字体设置-黑体
plt.rcParams['axes.unicode_minus'] = False #解决保存图像是负号'-'显示为方块的问题
sns.set(font='SimHei') #解决Seaborn中文显示的问题
import pandas as pd
from pandas import Series
def PlotKS(preds,labels,n,asc):
#preds is score:asc=1
#preds is prob:asc=0
pred=preds #预测值
bad=labels #1为bad，0为good
ksds=pd.DataFrame({'bad':bad,'pred':pred})
ksds['good']=1-ksds.bad

if asc==1:
    ksds1=ksds.sort_values(by=['pred','bad'],ascending=[True,True])
if asc==0:
    ksds1=ksds.sort_values(by=['pred','bad'],ascending=[False,True])
ksds1.index=range(len(ksds1.pred))
ksds1['cumsum_good1']=1.0*ksds1.good.cumsum()/sum(ksds1.good)
ksds1['cumsum_bad1']=1.0*ksds1.bad.cumsum()/sum(ksds1.bad)

if asc==1:
    ksds2=ksds.sort_values(by=['pred','bad'],ascending=[True,False])
if asc==0:
    ksds2=ksds.sort_values(by=['pred','bad'],ascending=[False,False])
ksds2.index=range(len(ksds1.pred))
ksds2['cumsum_good2']=1.0*ksds2.good.cumsum()/sum(ksds2.good)
ksds2['cumsum_bad2']=1.0*ksds2.bad.cumsum()/sum(ksds2.bad) 

#ksds1,ksds2->average
ksds=ksds1[['cumsum_good1','cumsum_bad1']]
ksds['cumsum_good2']=ksds2['cumsum_good2']
ksds['cumsum_bad2']=ksds2['cumsum_bad2']
ksds['cumsum_good']=(ksds1['cumsum_good1']+ksds2['cumsum_good2'])/2
ksds['cumsum_bad']=(ksds1['cumsum_bad1']+ksds2['cumsum_bad2'])/2

#ks
ksds['ks']=ksds['cumsum_bad']-ksds['cumsum_good']
ksds['tile0']=range(1,len(ksds.ks)+1)
ksds['tile']=1.0*ksds['tile0']/len(ksds['tile0'])

qe=list(np.arange(0,1,1.0/n))
qe.append(1)
qe=qe[1:]

ks_index=Series(ksds.index)
ks_index=ks_index.quantile(q=qe)
ks_index=np.ceil(ks_index).astype(int)
ks_index=list(ks_index)

ksds=ksds.loc[ks_index]
ksds=ksds[['tile','cumsum_good','cumsum_bad','ks']]
ksds0=np.array([[0,0,0,0]])
ksds=np.concatenate([ksds0,ksds],axis=0)
ksds=pd.DataFrame(ksds,columns=['tile','cumsum_good','cumsum_bad','ks'])

ks_value=ksds.ks.max()
ks_pop=ksds.tile[ksds.ks.idxmax()]
print('ks_value is '+ str(np.round(ks_value,4))+' + at pop = '+ str(np.round(ks_pop,4)))

#chart
plt.plot(ksds.tile,ksds.cumsum_good,label='cum_good',color='blue', linestyle='-',linewidth=2)
plt.plot(ksds.tile,ksds.cumsum_bad,label='cum_bad',color='red', linestyle='-',linewidth=2)
plt.plot(ksds.tile,ksds.ks,label='ks',color='green', linestyle='-',linewidth=2)

plt.axvline(ks_pop,color='grey',linestyle='--')
plt.axhline(ks_value,color='green',linestyle='--')
plt.axhline(ksds.loc[ksds.ks.idxmax(),'cumsum_good'],color='blue',linestyle='--')
plt.axhline(ksds.loc[ksds.ks.idxmax(),'cumsum_bad'],color='red',linestyle='--')
plt.title('KS=%s' %np.round(ks_value,4)+
         'at Pop=%s' %np.round(ks_pop,4),fontsize=15)
return ksds

PlotKS(train_out2[:,1], train_date['y'],20,0)
plt.show()