风控IV、AUC、KS python计算代码_python如何计算ks代码

一、IV计算代码

def cal_iv(df, label_col, feat_cols, bin=10):
        eps = 0.0000000000001
        target = label_col
        re_list = []
        for col in feat_cols:
            ivs = []
            df2 = df[[col, label_col]]
            df2.dropna()
            if len(df2[col].drop_duplicates()) < 10:
                continue
            else:
                df2 = df2.sort_values(by=col, ascending=True)
                count_0 = float(df2[df2[target] == 0].shape[0])
                count_1 = float(df2[df2[target] == 1].shape[0])
                df2['indexn'] = range(len(df2))
                divs = int(len(df2) / bin)
                up = math.ceil(len(df2) / divs)
                df2['group'] = [int(item / divs) for item in df2['indexn']]
                df3 = df2[['group', target]]
                tmpdata = []
                for i in range(up):
                    df4 = df3[df3['group'] == i]
                    yi = df4[df4[target] == 1].shape[0] + eps
                    tmpdata.append(df4)
                    if yi<1:
                        continue
                    else:
                        df4 = pd.concat(tmpdata,axis=0)
                        tmpdata = []
                    ni = df4[df4[target] == 0].shape[0] + eps
                    iv = (yi / count_1 - ni / count_0) * math.log((yi / count_1) / (ni / count_0))
                    if iv > 1:
                        print('group',i, df4.shape[0], df4[target].mean())
                    ivs.append(iv)
            iv = round(sum(ivs), 3)
            re_list.append({'feature': col, 'iv': iv})
        df_re = pd.DataFrame(re_list)[['feature', 'iv']]
        return df_re.sort_values(by='iv', ascending=False)

方法调用：

cal_iv(df_temp, Y， feas_list, bin=10)

df_temp：数据集，Y：是否逾期标签，feas_list：需要计算IV的 变量

2、 按月和不同Y 下的 IV计算

def iv_distr_v2(df, flag,  feas=feas_list):
 
    df_mob_iv = pd.DataFrame()
# 循环不同的 Y
    for i in  ['mob1_15','mob1_30','mob2_30','mob3_30']:
        print(i)
        df_temp1 = df[df['{}'.format(i)].notnull()]
        for j in list(df_temp1[flag].unique()):
            df_temp2 = df_temp1.loc[df_temp1[flag] == j]
            print(df_temp1.shape,df_temp2.shape)
            iv_temp1 = cal_iv(df_temp2, '{}'.format(i), feas_list, bin=10)
            iv_temp1['month'] = j
            iv_temp1['Y'] = i
 
            df_mob_iv = pd.concat([df_mob_iv, iv_temp1], axis=0)
 
    return df_mob_iv

调用代码：

iv_all = iv_distr_v2(df, flag= 'month',feas=feas_list, )

二 、KS、AUC调用代码，只对 值越大逾期越高的分数有效

import pandas as pd
import numpy as np
from sklearn.metrics import roc_auc_score,roc_curve

## 统计auc
def cal_auc(df, y_true, y_prob):
    try:
        return roc_auc_score(df[y_true], df[y_prob])
    except:
        return np.nan

## 统计ks
def cal_ks(df, y_true, y_prob):
    try:
        fpr, tpr, thre_ = roc_curve(df[y_true], df[y_prob])
        ks = max(tpr - fpr)
        return ks
    except:
        return np.nan