暑期项目实训个人记录-7

分箱处理

# 定义自动分箱函数
def mono_bin(Y, X, n = 20):
    r = 0
    good=Y.sum()
    bad=Y.count()-good
    while np.abs(r) < 1:
        d1 = pd.DataFrame({"X": X, "Y": Y, "Bucket": pd.qcut(X, n)})
        d2 = d1.groupby('Bucket', as_index = True)
        r, p = stats.spearmanr(d2.mean().X, d2.mean().Y)
        n = n - 1
    d3 = pd.DataFrame(d2.X.min(), columns = ['min'])
    d3['min']=d2.min().X
    d3['max'] = d2.max().X
    d3['sum'] = d2.sum().Y
    d3['total'] = d2.count().Y
    d3['rate'] = d2.mean().Y
    d3['woe']=np.log((d3['rate']/(1-d3['rate']))/(good/bad))
    d3['goodattribute']=d3['sum']/good
    d3['badattribute']=(d3['total']-d3['sum'])/bad
    iv=((d3['goodattribute']-d3['badattribute'])*d3['woe']).sum()
    d4 = (d3.sort_values(by = 'min'))
    print("=" * 60)
    print(d4)
    cut=[]
    cut.append(float('-inf'))
    for i in range(1,n+1):
        qua=X.quantile(i/(n+1))
        cut.append(round(qua,4))
    cut.append(float('inf'))
    woe=list(d4['woe'].round(3))
    return d4,iv,cut,woe