About Ujjawal

Ujjawal · ‎07-03-2015

Thanks a ton! This logic makes sense completely. Sure, i will check the same.

Ujjawal · ‎07-03-2015

I was able to crack it. When i use KEEP option and select only the categorical variable, the code works fine. But when i run it on full dataset, it throws error. "DSTRCT_Code_NEW " has been assigned both numeric and character. In this case, it treats DSTRCT_Code as a numeric variable so it makes DSTRCT_Code_NEW as numeric variable. The code below works fine with KEEP option. data def1; set def (KEEP = DSTRCT_Code) ; if DSTRCT_Code in(&charvarname.) then DSTRCT_Code_NEW = "&charvarname2."; else DSTRCT_Code_NEW = DSTRCT_Code; run;

Ujjawal · ‎07-02-2015

%put &charvarname.; and %put &charvarname2.; returns what i want. %put &charvarname.; returns 'RS79W', 'RS79C'. And %put &charvarname2.; returns RS79W_RS79C.

Ujjawal · ‎07-02-2015

I have tried putting double quotes "&charvarname2." but it is not working. NOTE: Invalid numeric data, DSTRCT_Code='RS79W'. It seems this line - " if DSTRCT_Code in(&charvarname.) then DSTRCT_Code_NEW = &charvarname2.;" is converting DSTRCT_Code variable into numeric. PERCENT go on a scale of 0 to 100. I know it should be PERCENT <= 5 in my code. I was testing the code and by mistake, i put the wrong code here. Sample District Code Field - DSTRCT_Code RS797 RS798 RS79W RS79C RS797 RS797 RS797 RS798 RS798

Ujjawal · ‎07-02-2015

Hi Experts, I am building a macro in which i am trying to collapse categories of a categorical variable. All the categories of a variable having less than 5% would be combined into one and name the label with their categories names' separated by"_". The problem arises in IF THEN statement using macro variables. proc freq data=def; table DSTRCT_Code / out= abcd; run; PROC SQL NOPRINT; Select catt("'",DSTRCT_Code, "'") INTO : charvarname separated by "," from abcd having PERCENT <= 0.01 and DSTRCT_Code is not null; QUIT; PROC SQL NOPRINT; Select DSTRCT_Code INTO : charvarname2 separated by "_" from abcd having PERCENT <= 0.01 and DSTRCT_Code is not null; QUIT; %put &charvarname.; %put &charvarname2.; options symbolgen mlogic; data def; length DSTRCT_Code_NEW $32.; set def; if DSTRCT_Code in(&charvarname.) then DSTRCT_Code_NEW = &charvarname2.; else DSTRCT_Code_NEW = DSTRCT_Code; run; The above highlighted code returns missing values in DSTRCT_Code. Also i need to make sure if the variable name exceeds 32 characters, it should truncate macro variable upto 32 characters. For example, a variable named" District_Code" having categories A, B and C needs to be combined. So the new variable would be created and named "District_code_NEW" would have a category - "A_B_C" against A, B and C categories of District_Code. Otherwise, same value. Thanks in anticipation!

Ujjawal · ‎07-01-2015

Thanks a ton Ballardw. I tried using the CONSTANT function. Is it used with PROC IML only, Is it correct to use like this ? Lsqr = CONSTANT('SQRTBIG'); srtvar{mi} = sqrt(min(Lsqr, transvars{mi})); sqvar{mi} = min(CONSTANT('LOGBIG',10) ,transvars{mi})**2;

Ujjawal · ‎06-30-2015

Oops. Correct! Exp is the biggest culprit then. I need to cap some variables. Thanks for your time.

Ujjawal · ‎06-30-2015

Thanks for your response. Yes, some values are as small as .00005 and some as big as 99999999.456789. Rounding off is not working to correct them. The PROC LOGISTIC code is shown below. There are 8 independent variables- Original Variable, Square root of it, square, cube, cube root, log, inverse, exp. ODS OUTPUT EFFECTNOTINMODEL = Estimate&i.; PROC LOGISTIC DATA = &output. DESC; MODEL &depvar. = &varName. &srtvar1. &sqvar1. &logvar1. &invvar1. &cbvar1. &cbrtvar1. &expvar1. / SELECTION = S MAXSTEP = 1 DETAILS; RUN; There are some warnings while executing array code - " Invalid argument to function operation : EXP, SQRT and *** " . I thought it is because of missing values. I put condition in array - IF NOT MISSING THEN DO. But these warnings are still coming. Detailed Code : %macro test(input = ,depvar=, output=); data _null_; call symput ("library", put(upcase(substr("&input",1,index("&input",'.')-1)), $8.)); call symput ("datset", put(upcase(substr("&input",index("&input",'.')+1,length("&input"))), $32.)); run; *Selecting numeric variables; proc sql noprint; select name into : numvar separated by " " from dictionary.columns where LIBNAME = "&library" and MEMNAME = "PREDATA" and type = 'num'; quit; %let varn=%sysfunc(countw(&numvar%str( ))); *Run for all the numeric variables; %DO i=1 %TO &varn; *Selecting Variable one by one; %let varName =%scan(%sysfunc(compbl(&numvar)),&i,%str( )); %let srtvar1 = sqrt_&varName.; %let sqvar1 = sq_&varName.; %let logvar1 = log_&varName.; %let invvar1 = inv_&varName.; %let cbvar1 = cb_&varName.; %let cbrtvar1= cbrt_&varName.; %put &varName. &srtvar1.; options symbolgen; ODS OUTPUT EFFECTNOTINMODEL = Estimate&i.; PROC LOGISTIC DATA = &output. DESC; MODEL &depvar. = &varName. &srtvar1. &sqvar1. &logvar1. &invvar1. &cbvar1. &cbrtvar1. / SELECTION = S MAXSTEP = 1 DETAILS; RUN; options nosymbolgen; %end; %mend;

Ujjawal · ‎06-30-2015

Hi Experts, The following error is coming when i run proc logistic on some variables. These variables are transformed variables - For example, sqrt root, cube root, square, exp value etc. ERROR: Floating Point Overflow. ERROR: Termination due to Floating Point Exception What i found on google is that it is because of too large value. This is the code i am using prior to that. data output; set output; array transvars{*} &numvar; array srtvar{*} &srtvar; array sqvar{*} &sqvar; array logvar{*} &logvar; array invvar{*} &invvar; array cbvar{*} &cbvar; array cbrtvar{*} &cbrtvar; array expvar{*} &expvar; do mi = 1 to dim(transvars); if not missing(transvars{mi}) then do; transvars{mi} = round(transvars{mi},.01); srtvar{mi} = round(sqrt(transvars{mi}),.01); logvar{mi} = round(log(max(.0001,transvars{mi})),.01); invvar{mi} = round(1/max(.0001,transvars{mi}),.01); sqvar{mi} = round(transvars{mi}**2,.01); cbvar{mi} = round(transvars{mi}**3,.01); cbrtvar{mi} = round(transvars{mi}**.3333,.01); expvar{mi} = round(exp(max(.0001,transvars{mi})),.01); end; end; drop mi; run; I am rounding off to two digits, still error not resolving.

Ujjawal · ‎06-29-2015

Variables are in the file. Still it is throwing error -"Sqrt_ not found". If you look at error - It is not saying - "Sqrt_Height" not found.

Ujjawal · ‎06-29-2015

Hi Experts, I am in the process of building a macro. The code is shown below. I have concatenated macro variables with some prefix (sqrt_ for square roots etc). When i ask to print using %put, it is showing macro variable with concatenated text correctly. However, when i use it in PROC LOGISTIC, it returns " sqrt_ not found" error. %let varName =%qscan(%sysfunc(compbl(&numvar)),&i,%str( )); %let srtvar1 = sqrt_&varName.; %put &varName. &srtvar1.; options symbolgen; ODS OUTPUT EFFECTNOTINMODEL = Estimate&i.; PROC LOGISTIC DATA = &output. DESC; MODEL &depvar. = &varName. &srtvar1. / SELECTION = S MAXSTEP = 1 DETAILS; RUN; Detailed Code : %macro test(input = ,depvar=, output=); data _null_; call symput ("library", put(upcase(substr("&input",1,index("&input",'.')-1)), $8.)); call symput ("datset", put(upcase(substr("&input",index("&input",'.')+1,length("&input"))), $32.)); run; *Selecting numeric variables; proc sql noprint; select name into : numvar separated by " " from dictionary.columns where LIBNAME = "&library" and MEMNAME = "PREDATA" and type = 'num'; quit; %let varn=%sysfunc(countw(&numvar%str( ))); *Run for all the numeric variables; %DO i=1 %TO &varn; *Selecting Variable one by one; %let varName =%qscan(%sysfunc(compbl(&numvar)),&i,%str( )); %let srtvar1 = sqrt_&varName.; %let sqvar1 = sq_&varName.; %let logvar1 = log_&varName.; %let invvar1 = inv_&varName.; %let cbvar1 = cb_&varName.; %let cbrtvar1= cbrt_&varName.; %put &varName. &srtvar1.; options symbolgen; ODS OUTPUT EFFECTNOTINMODEL = Estimate&i.; PROC LOGISTIC DATA = &output. DESC; MODEL &depvar. = &varName. &srtvar1. &sqvar1. &logvar1. &invvar1. &cbvar1. &cbrtvar1. / SELECTION = S MAXSTEP = 1 DETAILS; RUN; options nosymbolgen; %mend;

Ujjawal · ‎06-26-2015

Thanks a ton Steve for your answer. I know Somer's D and Gini Coefficient. Gini Coefficient = 2 (AUC -1) and AUC = %Concordance + 0.5 (Tied Pairs). It would be great if you share an article of "In linear regression, it is a transformation of the Pearson correlation coefficient.". I am more intersted about application of Gini Coefficient in linear regression. I did not find a single article to support it. Am i correct? - In logistic regression, if gini coefficient is high, logit function is monotonically related to independent variable? In linear regression, if gini coefficient is high, y is linearly related to independent variable?

Ujjawal · ‎06-25-2015

Thanks Xia for looking into it.

Ujjawal · ‎06-25-2015

Thanks Ballardw. I will try and let you know about it. You are always a great help. I bow down to you 🙂

Ujjawal · ‎06-25-2015

I am using Base SAS. Does your answer vary in Base SAS and SAS Enterprise Guide? Thanks!

Online Status	Offline
Date Last Visited	‎02-09-2018 10:54 AM

Distance / Similarity with Events

Moving Average Forecasting

Loading code

Re: code to match merge

Re: code to match merge

Re: Binary Flags

Binary Flags

Use Different variable on clearing filter

Re: Length in CREATE DATA

Re: Length in CREATE DATA

Re: Binary Flags

Re: Binary Flags

Re: Binary Flags

Re: Length in CREATE DATA

Re: Conditional Retain on Multiple Variables

Maximum number of characters in a macro variable

Re: Column Percentage in bar

Re: Macro variable not resolving

Re: Macro variable not resolving

Re: Macro variable not resolving

Re: Macro variable not resolving

Macro variable not resolving

Re: ERROR: Floating Point Overflow

Re: ERROR: Floating Point Overflow

Re: ERROR: Floating Point Overflow

ERROR: Floating Point Overflow

Re: Macro variable not resolving correctly

Macro variable not resolving correctly

Re: Gini Coefficient - Variable Importance Measure

Re: Gini Coefficient - Variable Importance Measure

Re: Pick variables in different combinations

Re: Change date format