SAS中文论坛

标题: SAS MACRO TO EVALUATE THE PREDICTABILITY OF A SCORECARD [打印本页]

作者: shiyiming 时间: 2010-10-22 13:24
标题: SAS MACRO TO EVALUATE THE PREDICTABILITY OF A SCORECARD
From Wensui Liu's blog

%macro separate(data = , score = , y = , wt = NONE); ***************************************************************; * THIS MACRO IS TO EVALUATE THE PREDICTABILITY OF A SCORECARD *; * ----------------------------------------------------------- *; * PARAMETERS: *; * DATA : INPUT DATASET *; * SCORE : SCORECARD VARIABLE *; * Y : RESPONSE VARIABLE IN (0, 1) *; * WT : WEIGHT VARIABLE IN POSITIVE INTEGER *; * ----------------------------------------------------------- *; * OUTPUTS: *; * &AUC : MACRO VARIABLE FOR AUC STATISTICS *; * &GINI : MACRO VARIABLE FOR GINI COEFFICIENT *; * &KS : MACRO VARIABLE FOR KS STATISTICS *; * &KS_SCORE : MACRO VARIABLE FOR SCORE VALUE MAXIMIZING KS *; * &DIVERGENCE : MACRO VARIABLE FOR DIVERGENCE *; * REPORT : GOOD-BAD SEPARATION REPORT IN HTML FORMAT *; * ----------------------------------------------------------- *; * AUTHOR: <a href="mailto:WENSLIU@PAYPAL.COM">WENSLIU@PAYPAL.COM</a> *; ***************************************************************; options nonumber nodate orientation = landscape linesize = 160 nocenter; *** DEFAULT GROUP NUMBER FOR REPORT ***; %let grp = 10; *** CHECK IF THERE IS WEIGHT VARIABLE ***; %if %upcase(&wt) = NONE %then %do; data _tmp1 (keep = &y &score _wt); set &data; where &y in (1, 0) and &score ~= .; _wt = 1; &score = round(&score., 1); run; %end; %else %do; data _tmp1 (keep = &y &score _wt); set &data; where &y in (1, 0) and &score ~= . and round(&wt., 1) > 0; _wt = round(&wt., 1); &score = round(&score., 1); run; %end; filename lst_out temp; proc printto new print = lst_out; run; *** CONDUCT NON-PARAMETRIC TESTS ***; ods output wilcoxonscores = _wx; ods output kolsmir2stats = _ks; proc npar1way wilcoxon edf data = _tmp1; class &y; var &score; freq _wt; run; proc printto; run; proc sort data = _wx; by class; run; *** CALCULATE ROC AND GINI ***; data _null_; set _wx end = eof; by class; array a{2, 3} _temporary_; if _n_ = 1 then do; a[1, 1] = n; a[1, 2] = sumofscores; a[1, 3] = expectedsum; end; else do; a[2, 1] = n; end; if eof then do; auc = (a[1, 2] - a[1, 3]) / (a[1, 1] * a[2, 1]) + 0.5; gini = 2 * (auc - 0.5); call execute('%global auc; %let auc = '||put(auc, 10.8)||';'); call execute('%global gini; %let gini = '||put(gini, 10.8)||';'); end; run; *** CALCULATE KS ***; data _null_; set _ks; if _n_ = 1 then do; ks = nvalue2 * 100; call execute('%global ks; %let ks = '||put(ks, 10.8)||';'); end; run; *** CAPTURE SCORE POINT FOR MAX KS ***; data _null_; infile lst_out; input @" at Maximum = " ks_score; output; call execute('%global ks_score; %let ks_score = '||put(ks_score, 10.0)||';'); stop; run; proc summary data = _tmp1 nway; class &y; freq _wt; output out = _data_ (drop = _type_ _freq_) mean(&score.) = mean var(&score.) = variance; run; *** CALCULATE DIVERGENCE ***; data _null_; set _last_ end = eof; array a{2, 2} _temporary_; if _n_ = 1 then do; a[1, 1] = mean; a[1, 2] = variance; end; else do; a[2, 1] = mean; a[2, 2] = variance; end; if eof then do; divergence = (a[1, 1] - a[2, 1]) ** 2 / ((a[1, 2] + a[2, 2]) / 2); call execute('%global divergence; %let divergence = '||put(divergence, 10.8)||';'); end; run; *** CAPTURE THE DIRECTION OF SCORE ***; ods listing close; ods output spearmancorr = _cor; proc corr data = _tmp1 spearman; var &y; with &score; run; ods listing; data _null_; set _cor; if &y >= 0 then do; call symput('desc', 'descending'); end; else do; call symput('desc', ' '); end; run; %put &desc; *** DEFINE DECILES WITH WEIGHT VARIABLE ***; proc univariate data = _tmp1 noprint; freq _wt; var &score; output out = _tmp2 pctlpre = decile_ pctlpts = 0 to 100 by %sysevalf(100 / &grp.); run; data _tmp3 (keep = rank _wt &y &score _dwt); set _tmp1; if _n_ = 1 then do; set _tmp2; end; array d[*] decile_:; rank = 999; do i = 2 to dim(d); if &score <= d[i] and rank = 999 then do; rank = i - 1; end; end; _dwt = 1 / _wt; run; proc summary data = _last_ nway; class rank; freq _wt; output out = _data_ (drop = _type_ rename = (_freq_ = freq)) min(&score) = min_score max(&score) = max_score sum(&y) = bads sum(_dwt) = raw; run; proc sql noprint; select sum(bads) into :bcnt from _last_; select sum(freq) - sum(bads) into :gcnt from _last_; quit; proc sort data = _last_ (drop = rank); by &desc min_score; run; data _data_; set _last_; by &desc min_score; i + 1; percent = i * %sysevalf(100 / &grp) / 100; good = freq - bads; odds = good / bads; hit_rate = bads / freq; retain cum_bads cum_freq; cum_bads + bads; cum_freq + freq; cum_hit_rate = cum_bads / cum_freq; cat_rate = bads / &bcnt; retain cum_cat_rate; cum_cat_rate + cat_rate; run; *** GENERATE GAIN CHART ***; ods html file = "%upcase(%trim(&score))_SEPARATION_REPORT.html" style = sasweb; title; proc report data = _last_ box spacing = 1 split = "/" style(header) = [font_face = "courier new"] style(column) = [font_face = "courier new"] style(lines) = [font_face = "courier new"] style(report) = [font_face = "courier new"] style(summary) = [font_face = "courier new" font_style = roman]; column("/GOOD BAD SEPARATION REPORT FOR %upcase(%trim(&score)) WEIGHTED BY %upcase(&wt) IN DATA %upcase(%trim(&data)) / MAXIMUM KS = %trim(&ks) AT SCORE POINT %trim(&ks_score) / / ( AUC STATISTICS = %trim(&auc), GINI COEFFICIENT = %trim(&gini), DIVERGENCE = %trim(&divergence) )/ /" percent min_score max_score raw good bads freq odds hit_rate cum_hit_rate cat_rate cum_cat_rate); define percent / " % " center width = 6 format = percent6.0 order order = data; define min_score / "MIN/SCORE" width = 6 format = 5. analysis min center; define max_score / "MAX/SCORE" width = 6 format = 5. analysis max center; define raw / "RAW/UNITS" width = 10 format = comma9. analysis sum center; define good / "GOOD/#" width = 15 format = comma14. analysis sum; define bads / "BAD/#" width = 15 format = comma14. analysis sum; define freq / "TOTAL/#" width = 15 format = comma14. analysis sum; define odds / "ODDS" width = 10 format = 9. order; define hit_rate / "HIT/RATE" width = 10 format = percent9.2 order center; define cum_hit_rate / "CUMULATIVE/HIT RATE" width = 10 format = percent9.2 order; define cat_rate / "CATCH/RATE" width = 10 format = percent9.2 order center; define cum_cat_rate / "CUMULATIVE/CATCH RATE" width = 10 format = percent9.2 order; rbreak after / summarize style = [font_weight = bold]; run; ods html close; *************************************************; * END OF THE MACRO *; *************************************************; %mend separate;

欢迎光临 SAS中文论坛 (https://mysas.net/forum/)