andreas/REDCapCAST
1
0
Fork 0
mirror of https://github.com/agdamsbo/REDCapCAST.git synced 2024-11-22 13:30:23 +01:00
Code Issues Packages Projects Releases Wiki Activity

Partial solve to issue #13

Browse Source
This commit is contained in:
Paul W. Egeler, MS, GStat 2019-07-26 12:02:20 -04:00 committed by pegeler
parent 7eb7d5b459
commit a2dcdc73a9
1 changed files with 128 additions and 91 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

209
SAS/REDCap_split.sas
View File

@ -2,7 +2,7 @@
* *
* FILE: REDCap_split.sas * FILE: REDCap_split.sas
* *
* VERSION: 0.0.0 * VERSION: 0.1.0
* *
* PURPOSE: Take a REDCap dataset with multiple events and make into several * PURPOSE: Take a REDCap dataset with multiple events and make into several
* tables with primary and foreign keys * tables with primary and foreign keys
@ -50,10 +50,27 @@
%MACRO REDCAP_SPLIT( %MACRO REDCAP_SPLIT(
DATA_SET = REDCAP /* The name of the SAS dataset created by REDCap */, DATA_SET = REDCAP /* The name of the SAS dataset created by REDCap */,
DATA_DICTIONARY = REDCAP_DATA_DICTIONARY /* The name of the SAS dataset of the data dictionary */ DATA_DICTIONARY = REDCAP_DATA_DICTIONARY /* The name of the SAS dataset of the data dictionary */,
NUMERIC_SUBTABLES = N /* Y/N: Should the subtables be numbered (Y) or should the be based on the name of the repeating instrument (N)? */
); );
/* Find the key that links the base table to child tables */
/* Also check that REDCAP_REPEAT_INSTRUMENT is present in the data */
%LET DSID = %SYSFUNC(OPEN(&DATA_SET));
%LET KEY = %SYSFUNC(VARNAME(&DSID, 1));
%LET CHECK = %SYSFUNC(VARNUM(&DSID, REDCAP_REPEAT_INSTRUMENT));
%LET RC = %SYSFUNC(CLOSE(&DSID));
%IF &CHECK EQ 0 %THEN %DO;
%PUT ERROR: The dataset &DATA_SET does not contain repeating instruments.;
%PUT ERROR: Stopping MACRO.;
%GOTO FINISH;
%END;
/* Remove formatting from repeat instrument field */ /* Remove formatting from repeat instrument field */
%PUT NOTE: Removing formatting from REDCAP_REPEAT_INSTRUMENT in &DATA_SET..;
DATA &DATA_SET.; DATA &DATA_SET.;
SET &DATA_SET.; SET &DATA_SET.;
FORMAT REDCAP_REPEAT_INSTRUMENT; FORMAT REDCAP_REPEAT_INSTRUMENT;
@ -73,120 +90,140 @@
%LET N_SUBTABLES = &SQLOBS; %LET N_SUBTABLES = &SQLOBS;
%PUT INSTRUMENTS: %LEFT(&INSTRUMENTS);
%PUT INSTRUMENT LIST: %LEFT(&INSTRUMENT_LIST);
%PUT N SUBTABLES: %LEFT(&N_SUBTABLES);
QUIT; QUIT;
%IF &N_SUBTABLES GT 0 %THEN %DO; %IF &N_SUBTABLES EQ 0 %THEN %DO;
/* Get information on the variables in the dataset */ %PUT WARNING: There were no records containing repeating instruments in the dataset %LEFT(&DATA_SET).;
PROC CONTENTS %PUT WARNING: No action was taken.;
DATA = &DATA_SET. %GOTO FINISH;
OUT = REDCAP_VARNAMES(KEEP=NAME VARNUM)
NOPRINT;
RUN;
/* Find the key that links the base table to child tables */ %END;
DATA _NULL_;
SET REDCAP_VARNAMES; %PUT N SUBTABLES: %LEFT(&N_SUBTABLES);
IF VARNUM EQ 1 THEN DO; %PUT INSTRUMENTS: %LEFT(&INSTRUMENTS);
CALL SYMPUT("KEY", NAME); %PUT INSTRUMENT LIST: %LEFT(%BQUOTE(&INSTRUMENT_LIST));
STOP;
/* Get information on the variables in the dataset */
PROC CONTENTS
DATA = &DATA_SET.
OUT = REDCAP_VARNAMES(KEEP=NAME VARNUM)
NOPRINT;
RUN;
/* Make a list of fields and their associated forms based on data dictionary */
DATA REDCAP_FIELDS(KEEP=VAR_NAME FORM_NAME);
SET &DATA_DICTIONARY.;
IF FIELD_TYPE EQ "checkbox" THEN DO;
BASENAME = VAR_NAME;
DO I = 1 TO N;
SET REDCAP_VARNAMES POINT=I NOBS=N;
IF PRXMATCH("/^"!!trim(BASENAME)!!"___.+$/", NAME) THEN DO;
VAR_NAME = NAME;
OUTPUT;
END; END;
RUN; END;
END;
ELSE OUTPUT;
RUN;
/* Make a list of fields and their associated forms based on data dictionary */ /* Add instrument status fields to list of fields */
DATA REDCAP_FIELDS(KEEP=VAR_NAME FORM_NAME); PROC SQL;
SET &DATA_DICTIONARY.;
IF FIELD_TYPE EQ "checkbox" THEN DO;
BASENAME = VAR_NAME;
DO I = 1 TO N;
SET REDCAP_VARNAMES POINT=I NOBS=N;
IF PRXMATCH("/^"!!trim(BASENAME)!!"___.+$/", NAME) THEN DO;
VAR_NAME = NAME;
OUTPUT;
END;
END;
END;
ELSE OUTPUT;
RUN;
/* Add instrument status fields to list of fields */
PROC SQL;
CREATE TABLE REDCAP_INSTRUMENT_STATUS_FIELDS AS CREATE TABLE REDCAP_INSTRUMENT_STATUS_FIELDS AS
SELECT DISTINCT TRIM(FORM_NAME)!!"_complete" AS VAR_NAME LENGTH=200, FORM_NAME SELECT DISTINCT TRIM(FORM_NAME)!!"_complete" AS VAR_NAME LENGTH=200, FORM_NAME
FROM REDCAP_DATA_DICTIONARY; FROM &DATA_DICTIONARY.;
QUIT; QUIT;
PROC APPEND PROC APPEND
BASE=REDCAP_FIELDS BASE=REDCAP_FIELDS
DATA=REDCAP_INSTRUMENT_STATUS_FIELDS; DATA=REDCAP_INSTRUMENT_STATUS_FIELDS;
RUN; RUN;
/* Sort out the field names */ DATA REDCAP_FIELDS;
PROC SQL NOPRINT; SET REDCAP_FIELDS;
SELECT VAR_NAME IF LENGTH(VAR_NAME) GT 32 THEN DO;
INTO :VARS_BASE SEPARATED BY ' ' PUT "WARNING: The variable " VAR_NAME "is too long (MAX 32 CHARACTERS).";
FROM REDCAP_FIELDS AS A PUT "WARNING: " VAR_NAME "will not be included in the output dataset.";
WHERE FORM_NAME NOT IN (&INSTRUMENT_LIST); DELETE;
END;
%put Base vars: &VARS_BASE; RUN;
%DO I = 1 %TO &N_SUBTABLES; /* Sort out the field names */
PROC SQL NOPRINT;
%LET INSTRUMENT_I = %SCAN(&INSTRUMENTS,&I,%STR( )); SELECT VAR_NAME
INTO :VARS_BASE SEPARATED BY ' '
FROM REDCAP_FIELDS AS A
WHERE FORM_NAME NOT IN (&INSTRUMENT_LIST);
SELECT VAR_NAME %put Base vars: &VARS_BASE;
INTO :VARS_&INSTRUMENT_I. SEPARATED BY ' '
FROM REDCAP_FIELDS AS A
WHERE FORM_NAME EQ "&INSTRUMENT_I.";
%put &INSTRUMENT_I. vars: &&VARS_&INSTRUMENT_I;
%END;
QUIT;
/* Make new data sets based on field names above */
DATA &DATA_SET._BASE (KEEP = &VARS_BASE);
SET &DATA_SET;
IF MISSING(REDCAP_REPEAT_INSTRUMENT);
RUN;
%DO I = 1 %TO &N_SUBTABLES; %DO I = 1 %TO &N_SUBTABLES;
%LET INSTRUMENT_I = %SCAN(&INSTRUMENTS,&I,%STR( )); %LET INSTRUMENT_I = %SCAN(&INSTRUMENTS,&I,%STR( ));
DATA &DATA_SET._&INSTRUMENT_I. (KEEP = &KEY redcap_repeat_instance &&VARS_&INSTRUMENT_I); SELECT VAR_NAME
SET &DATA_SET; INTO :VARS_&I. SEPARATED BY ' '
FROM REDCAP_FIELDS AS A
WHERE FORM_NAME EQ "&INSTRUMENT_I.";
IF REDCAP_REPEAT_INSTRUMENT EQ "&INSTRUMENT_I."; %PUT &INSTRUMENT_I. vars: &&VARS_&I;
RUN;
%END; %END;
QUIT;
/* Make new data sets based on field names above */
DATA &DATA_SET._BASE (KEEP = &VARS_BASE);
SET &DATA_SET;
IF MISSING(REDCAP_REPEAT_INSTRUMENT);
RUN;
%DO I = 1 %TO &N_SUBTABLES;
%LET INSTRUMENT_I = %SCAN(&INSTRUMENTS,&I,%STR( ));
/* Create either numeric table name or name based on repeating instrument name (see issue #12) */
%IF &NUMERIC_SUBTABLES EQ N %THEN %DO;
%LET SUBTABLE_NAME = &DATA_SET._&INSTRUMENT_I.;
%IF %LENGTH(&SUBTABLE_NAME) GT 32 %THEN %DO;
%PUT ERROR: The table name &SUBTABLE_NAME is %LENGTH(&SUBTABLE_NAME) characters long (MAX 32 CHARACTERS).;
%PUT ERROR: &SUBTABLE_NAME will be skipped. Consider setting NUMERIC_SUBTABLES = Y.;
%GOTO SKIP;
%END;
%END;
%ELSE %DO;
%LET SUBTABLE_NAME = &DATA_SET._&I.;
%END;
DATA &SUBTABLE_NAME (KEEP = &KEY redcap_repeat_instance &&VARS_&I);
SET &DATA_SET;
IF REDCAP_REPEAT_INSTRUMENT EQ "&INSTRUMENT_I.";
RUN;
%PUT NOTE: Records from instrument &INSTRUMENT_I have been placed in &SUBTABLE_NAME;
%SKIP:
%END;
/* Clean up temporary datasets */ /* Clean up temporary datasets */
PROC DATASETS MEMTYPE=DATA LIBRARY=WORK NOLIST; PROC DATASETS MEMTYPE=DATA LIBRARY=WORK NOLIST;
DELETE REDCAP_FIELDS REDCAP_VARNAMES REDCAP_INSTRUMENT_STATUS_FIELDS; DELETE REDCAP_FIELDS REDCAP_VARNAMES REDCAP_INSTRUMENT_STATUS_FIELDS;
RUN; RUN;
%END; %FINISH:
%ELSE %DO;
%PUT THERE WERE NO REPEAT INSTRUMENTS IN THE DATASET %LEFT(&DATA_SET);
%PUT NO ACTION WAS TAKEN;
%END;
%MEND REDCAP_SPLIT; %MEND REDCAP_SPLIT;