information_value.py 文件源码

def discrete(self, x, bin=5):
        #res = np.array([0] * x.shape[-1], dtype=int)
        #?????????????????????WOE?????????????<=?WOE??
        x_copy = pd.Series.copy(x)
        x_copy = x_copy.astype(str)
        #x_copy = x_copy.astype(np.str_)
        #x_copy = x
        x_gt0 = x[x>=0]
        #if x.name == 'TD_PLTF_CNT_1M':
            #bin = 5
            #x_gt0 = x[(x>=0) & (x<=24)]

        for i in range(bin):
            point1 = stats.scoreatpercentile(x_gt0, i * (100.0/bin))
            point2 = stats.scoreatpercentile(x_gt0, (i + 1) * (100.0/bin))
            x1 = x[(x >= point1) & (x <= point2)]
            mask = np.in1d(x, x1)
            #x_copy[mask] = i + 1
            x_copy[mask] = '%s-%s' % (point1,point2)
            #x_copy[mask] = point1
            #print x_copy[mask]
            #print x
        #print x
        return x_copy