Python计算KS值并绘制KS曲线

更多风控建模、大数据分析等内容请关注公众号《大数据风控的一点一滴》

python实现KS曲线，相关使用方法请参考上篇博客-R语言实现KS曲线

代码如下：

####################### PlotKS ##########################
def PlotKS(preds, labels, n, asc):

    # preds is score: asc=1
    # preds is prob: asc=0

    pred = preds  # 预测值
    bad = labels  # 取1为bad, 0为good
    ksds = DataFrame({‘bad‘: bad, ‘pred‘: pred})
    ksds[‘good‘] = 1 - ksds.bad

    if asc == 1:
        ksds1 = ksds.sort_values(by=[‘pred‘, ‘bad‘], ascending=[True, True])
    elif 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])
    elif asc == 0:
        ksds2 = ksds.sort_values(by=[‘pred‘, ‘bad‘], ascending=[False, False])
    ksds2.index = range(len(ksds2.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‘] = (ksds[‘cumsum_good1‘] + ksds[‘cumsum_good2‘])/2
    ksds[‘cumsum_bad‘] = (ksds[‘cumsum_bad1‘] + ksds[‘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 = 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=‘gray‘, 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
####################### over ##########################

作图效果如下：

原文地址：http://blog.51cto.com/6093943/2120625