passes=20
outvars=vout;
var amount income homeval frequent recency age
domestic apparel marital ntitle gender telind origin
job statecod numcars edlevel;
target purchase;
title 'DMSPLIT: Binary Target';
run;
proc print data=vout(obs=20);
title2 'OUTVARS= Summary Data';
run;
title 'Import and Save Tree from DMSPLT';
proc split dmdbcat=catexa1 indmsplit
outmatrix=trtree
outleaf=leafdata
outtree=savetree;
run;
proc print data=trtree label;
title2 'Training Statistics';
run;
proc print data=leafdata(obs=10) label;
title2 'Leaf Statistics';
run;
data testexa1(drop=ran);
set sampsio.dmexa1;
ran=ranuni(3333);
if ran lt 0.08;
title 'Create Fictitious Score Data Set';
run;
proc split intree=savetree;
score data=testexa1 nodmdb
outfit=tfit out=tout;
title 'Input Tree and Score Test Data';
proc print data=tfit label;
title2 'Fit Statistics for the Scored Data Set';
run;
proc freq data=tout;
tables f_purcha*i_purcha;
title2 'Scored Data';
title3 'Misclassification Table';
run;
proc print data=tout(obs=10) label;
var _node_ a_ a_yes a_no d_purcha f_purcha
i_purcha p_puryes p_purno p_pur r_puryes
r_purno r_pur;
title2 'Score Summary Data';
run;
PROC DMSPLIT Output
Partial Listing of the Splitting Table
The splitting table contains the following information for each split:
node number
q
parent node
q
chi-square value for the split
q
splitting
variable
q
the average of the splitting variable if it is an interval input, or the number of levels if the splitting variable is
q
non-interval.
DMSPLIT: Binary Target
Node Parent ChiSq Split
Value Levels
-------------------------------------------------------------------------
1 0 92.34 FREQUENT 2.36
Node Parent ChiSq Split Value Levels
-------------------------------------------------------------------------
2 1 29.48 STATECOD . 23 31
3 1 30.80 DOMESTIC 3.20
Node Parent ChiSq Split Value Levels
-------------------------------------------------------------------------
4 2 11.58 JOB . 10 4
5 2 13.46 STATECOD . 20 11
6 3 30.88 STATECOD . 35 18
7 3 29.79 STATECOD . 21 24
Node Parent ChiSq Split Value Levels
-------------------------------------------------------------------------
8 4 7.28 JOB . 4 6
9 4 9.90 STATECOD . 2 9
10 5 7.03 HOMEVAL 40000.00
11 5 6.56 HOMEVAL 240000.00
12 6 8.29 STATECOD . 13 22
13 6 8.83 JOB . 5 9
14 7 7.16 STATECOD . 17 4
15 7 11.85 APPAREL 1.67
DMSPLIT: Binary Target
Node Parent ChiSq Split Value Levels
-------------------------------------------------------------------------
17 8 6.06 HOMEVAL 20000.00
18 9 3.00 AGE 34.60
20 10 11.12 STATECOD . 5 11
21 10 5.03 JOB . 10 3
22 11 6.42 FREQUENT 2.29
24 12 6.16 JOB . 5 3
25 12 9.15 EDLEVEL . 2 2
27 13 6.58 AMOUNT 1328.50
29 14 7.98 INCOME 14520.00
30 15 10.10 STATECOD . 13 8
31 15 15.13 JOB . 8 2
Node Parent ChiSq Split Value Levels
-------------------------------------------------------------------------
32 17 11.00 RECENCY 789.37
33 17 4.56 STATECOD . 4 18
36 20 6.11 AGE 29.70
37 20 8.33 DOMESTIC 0.80
38 21 4.34 TELIND . 1 1
40 22 6.40 HOMEVAL 96000.00
41 22 4.00 NTITLE . 2 1
42 24 6.77 RECENCY 232.17
43 24 2.22 EDLEVEL . 1 1
44 25 5.40 MARITAL . 1 1
45 25 13.88 INCOME 21780.00
46 27 9.53 APPAREL 1.67
47 27 15.08 AGE 34.60
49 29 7.08 FREQUENT 9.79
50 30 6.85 APPAREL 0.06
51 30 5.20 FREQUENT 6.61
52 31 7.30 STATECOD . 12 9
Effect Summary Table
The Effect Summary table lists the node in which the effect was first split and the total number of times a split occurred
for the effect.
Effect Summary
Effect Node 1st Split Total Times Split
---------------------------------------------------
FREQUENT 1 47
STATECOD 2 64
DOMESTIC 3 25
JOB 4 35
HOMEVAL 10 23
APPAREL 15 20
AGE 18 44
EDLEVEL 25 12
AMOUNT 27 26
INCOME 29 37
RECENCY 32 39
TELIND 38 4
NTITLE 41 29
MARITAL 44 12
ORIGIN 65 19
NUMCARS 193 10
GENDER 776 2
Partial Listing of the OUTVARS Data Set
DMSPLIT: Binary Target
OUTVARS=
Summary Data