This example shows bucket binning and weight-of-evidence (WOE) computation in two steps. In the first step, PROC HPBIN does bucket binning and generates the mapping table. In the second step, PROC HPBIN takes the mapping table that is generated in the first step as the BINS_META data set and computes the WOE and the information value (IV).
data ex12; input cl1 $ x0 x1 x2 y $ freq id; cards; a 2 . 7 n 2 1 a 2 2 6 . 3 2 a 3 0 1 o 0 3 c 2 3 7 y . 4 c 2 . 4 n -5 5 a 3 6 7 n 3 6 b 1 4 4 y 4 7 b 2 5 6 y 3 8 b 1 6 4 o 1 9 b 2 3 2 n 3 10 run;
proc hpbin data=ex12 numbin=5; input x1/numbin=4; input x2; ods output Mapping=Mapping; run; proc hpbin data=ex12 WOE BINS_META=Mapping; target y/level=nominal order=desc; run;
Output 3.4.1: Number of Observations Table
Number of Observations Read | 10 |
---|---|
Number of Observations Used | 9 |
Output 3.4.2: Weight-of-Evidence Table
Weight of Evidence | ||||||||
---|---|---|---|---|---|---|---|---|
Variable | Binned Variable | Range | Non-event Count |
Non-event Rate |
Event Count |
Event Rate |
Weight of Evidence |
Information Value |
x1 | BIN_x1 | 2 | 1.00000 | 0 | 0 | 0.91629 | 0.30543 | |
x1 < 1.500000 | 1 | 1.00000 | 0 | 0 | 0.40547 | 0.06758 | ||
1.500000 <= x1 < 3.000000 | 0 | 0 | 0 | 0 | 0 | 0 | ||
3.000000 <= x1 < 4.500000 | 1 | 0.33333 | 2 | 0.66667 | -1.38629 | 0.69315 | ||
4.500000 <= x1 | 2 | 0.66667 | 1 | 0.33333 | 0 | 0 | ||
x2 | BIN_x2 | 0 | 0 | 0 | 0 | 0 | 0 | |
x2 < 2.200000 | 2 | 1.00000 | 0 | 0 | 0.91629 | 0.30543 | ||
2.200000 <= x2 < 3.400000 | 0 | 0 | 0 | 0 | 0 | 0 | ||
3.400000 <= x2 < 4.600000 | 2 | 0.66667 | 1 | 0.33333 | 0 | 0 | ||
4.600000 <= x2 < 5.800000 | 0 | 0 | 0 | 0 | 0 | 0 | ||
5.800000 <= x2 | 2 | 0.50000 | 2 | 0.50000 | -0.69315 | 0.23105 |
Output 3.4.3: Variable Information Value Table
Variable Information Value |
|
---|---|
Variable | Information Value |
x1 | 1.06615 |
x2 | 0.53648 |