ModelEvaluate.py 文件源码

def cal_ks(y,y_prob,pos_label=1,return_split=False,decimals=0):
    '''
    ??KS????????
    y: ?????series?????????{0,1}?{-1,1}??
    y_prob: ?????dataframe???????????????????????????????????
            ?????????series?????????dataframe?????
    pos_label: int?????positive?????
    return_split: ??????????
    decimals: ?????????
    ??KS??????????????sklearn???????
    '''
    y=pd.Series(pd.Series(y).values)
    if len(y_prob.shape)==1:
        y_pred=pd.Series(pd.Series(y_prob).values)
    else:
        y_pred=pd.Series(pd.DataFrame(y_prob).iloc[:,1].values)
    Bad=y_pred[y==pos_label]
    Good=y_pred[y!=pos_label]
    ks, pvalue = stats.ks_2samp(Bad.values, Good.values)
    if not return_split:
        return ks
    crossfreq=pd.crosstab(y_pred.round(decimals),y)
    crossdens = crossfreq.cumsum(axis=0) / crossfreq.sum()
    crossdens['gap'] = abs(crossdens[0] - crossdens[1])
    score_split = crossdens[crossdens['gap'] == crossdens['gap'].max()].index[0]
    return score_split