Record race and ethnicity, with one supplemental record per race

1library(yamaa)23yamaa_spec("spec_dm.yaml")$run()$save()4yamaa_spec("spec_suppdm.yaml")$run()$output

1import yamaa23yamaa.spec("spec_dm.yaml").run().save()4yamaa.spec("spec_suppdm.yaml").run().output

1# Reference solution for the yamaa benchmark sdtm-dm-race-ethnicity (R track).2#3# Written from the benchmark's full prompt and its inputs alone, as an agent4# would write it. Harbor's oracle agent runs it to check that the prompt can5# be solved and that the grader scores a correct answer 1.67library(dplyr, warn.conflicts = FALSE)8library(readr)9library(tidyr)10library(stringr)11library(purrr)1213odm <- read_csv(14  "/app/input/odm.csv",15  col_types = cols(.default = col_character())16)1718race_map <- c(19  "White" = "WHITE",20  "Asian" = "ASIAN",21  "Black or African American" = "BLACK OR AFRICAN AMERICAN",22  "American Indian or Alaska Native" = "AMERICAN INDIAN OR ALASKA NATIVE",23  "Native Hawaiian or Other Pacific Islander" = "NATIVE HAWAIIAN OR OTHER PACIFIC ISLANDER",24  "Other, specify: Fijian" = "OTHER",25  "Subject refused" = "UNKNOWN",26  "Not reported" = "NOT REPORTED"27)2829ethnic_map <- c(30  "Hispanic or Latino" = "HISPANIC OR LATINO",31  "Not Hispanic or Latino" = "NOT HISPANIC OR LATINO",32  "Not reported" = "NOT REPORTED",33  "Unknown" = "UNKNOWN"34)3536map_term <- function(x, lut) {37  out <- unname(lut[x])38  out[is.na(out)] <- NA_character_39  out40}4142subjects <- odm |>43  distinct(StudyOID, SubjectKey) |>44  mutate(45    STUDYID = StudyOID,46    USUBJID = SubjectKey47  )4849race_distinct <- odm |>50  filter(ItemOID == "IT.DM.RACE", Value != "", !is.na(Value)) |>51  distinct(StudyOID, SubjectKey, Value)5253race_per_subject <- race_distinct |>54  group_by(StudyOID, SubjectKey) |>55  summarise(answers = list(sort(unique(Value))), .groups = "drop")5657ethnic_per_subject <- odm |>58  filter(ItemOID == "IT.DM.ETHNIC", Value != "", !is.na(Value)) |>59  group_by(StudyOID, SubjectKey) |>60  summarise(ethnic_answer = first(Value), .groups = "drop")6162dm <- subjects |>63  left_join(race_per_subject, by = c("StudyOID", "SubjectKey")) |>64  left_join(ethnic_per_subject, by = c("StudyOID", "SubjectKey")) |>65  rowwise() |>66  mutate(67    DOMAIN = "DM",68    SUBJID = USUBJID,69    RACE = if (is.null(answers) || length(answers) == 0 || all(is.na(answers))) {70      NA_character_71    } else if (length(answers) >= 2) {72      "MULTIPLE"73    } else {74      map_term(answers[[1]], race_map)75    },76    ETHNIC = map_term(ethnic_answer, ethnic_map)77  ) |>78  ungroup() |>79  select(STUDYID, USUBJID, DOMAIN, SUBJID, RACE, ETHNIC, StudyOID, SubjectKey) |>80  arrange(USUBJID)8182multi <- dm |> filter(RACE == "MULTIPLE")8384suppdm <- race_distinct |>85  inner_join(86    multi |> select(StudyOID, SubjectKey),87    by = c("StudyOID", "SubjectKey")88  ) |>89  left_join(90    subjects |> select(StudyOID, SubjectKey, STUDYID, USUBJID),91    by = c("StudyOID", "SubjectKey")92  ) |>93  arrange(USUBJID, Value) |>94  group_by(STUDYID, USUBJID) |>95  mutate(96    n = row_number(),97    QNAM = paste0("RACE", n),98    QLABEL = paste("Race", n)99  ) |>100  ungroup() |>101  mutate(102    RDOMAIN = "DM",103    IDVAR = "USUBJID",104    IDVARVAL = USUBJID,105    QVAL = map_term(Value, race_map),106    QORIG = "CRF",107    QEVAL = NA_character_108  ) |>109  select(STUDYID, RDOMAIN, USUBJID, IDVAR, IDVARVAL, QNAM, QLABEL, QVAL, QORIG, QEVAL) |>110  arrange(USUBJID, QNAM)111112dir.create("/app/output", showWarnings = FALSE)113write_csv(114  dm |> select(DOMAIN, STUDYID, USUBJID, SUBJID, RACE, ETHNIC),115  "/app/output/dm.csv",116  na = ""117)118write_csv(suppdm, "/app/output/suppdm.csv", na = "")

1# Reference solution for the yamaa benchmark sdtm-dm-race-ethnicity (Python track).2#3# Written from the benchmark's full prompt and its inputs alone, as an agent4# would write it. Harbor's oracle agent runs it to check that the prompt can5# be solved and that the grader scores a correct answer 1.67"""Build DM and SUPPDM from the ODM extract.89Reads /app/input/odm.csv (long format: one row per collected item value)10and writes /app/output/dm.csv (one record per subject) and11/app/output/suppdm.csv (one record per distinct race marked, for12subjects whose RACE is "MULTIPLE").13"""1415import csv16from collections import OrderedDict1718INPUT_DIR = "/app/input"19OUTPUT_DIR = "/app/output"2021RACE_MAP = {22    "White": "WHITE",23    "Asian": "ASIAN",24    "Black or African American": "BLACK OR AFRICAN AMERICAN",25    "American Indian or Alaska Native": "AMERICAN INDIAN OR ALASKA NATIVE",26    "Other, specify: Fijian": "OTHER",27    "Not reported": "NOT REPORTED",28    "Subject refused": "UNKNOWN",29}3031ETHNIC_MAP = {32    "Hispanic or Latino": "HISPANIC OR LATINO",33    "Not Hispanic or Latino": "NOT HISPANIC OR LATINO",34    "Not reported": "NOT REPORTED",35    "Unknown": "UNKNOWN",36}3738DM_COLUMNS = ["DOMAIN", "STUDYID", "USUBJID", "SUBJID", "RACE", "ETHNIC"]39SUPPDM_COLUMNS = [40    "STUDYID",41    "RDOMAIN",42    "USUBJID",43    "IDVAR",44    "IDVARVAL",45    "QNAM",46    "QLABEL",47    "QVAL",48    "QORIG",49    "QEVAL",50]515253def main():54    with open(f"{INPUT_DIR}/odm.csv", newline="", encoding="utf-8") as f:55        rows = list(csv.DictReader(f))5657    # Collect, per subject, every marked race answer and the ethnicity58    # answer, keeping subjects in order of first appearance.59    subjects = OrderedDict()60    for row in rows:61        key = (row["StudyOID"], row["SubjectKey"])62        entry = subjects.setdefault(key, {"races": [], "ethnic": ""})63        if row["ItemOID"] == "IT.DM.RACE":64            if row["Value"]:65                entry["races"].append(row["Value"])66        elif row["ItemOID"] == "IT.DM.ETHNIC":67            entry["ethnic"] = row["Value"]6869    dm_rows = []70    suppdm_rows = []71    for (studyid, usubjid), entry in subjects.items():72        distinct_races = sorted(set(entry["races"]))73        if len(distinct_races) > 1:74            race = "MULTIPLE"75        elif len(distinct_races) == 1:76            race = RACE_MAP.get(distinct_races[0], "")77        else:78            race = ""79        ethnic = ETHNIC_MAP.get(entry["ethnic"], "") if entry["ethnic"] else ""8081        dm_rows.append(82            {83                "DOMAIN": "DM",84                "STUDYID": studyid,85                "USUBJID": usubjid,86                "SUBJID": usubjid,87                "RACE": race,88                "ETHNIC": ethnic,89            }90        )9192        if race == "MULTIPLE":93            for i, answer in enumerate(distinct_races, start=1):94                suppdm_rows.append(95                    {96                        "STUDYID": studyid,97                        "RDOMAIN": "DM",98                        "USUBJID": usubjid,99                        "IDVAR": "USUBJID",100                        "IDVARVAL": usubjid,101                        "QNAM": f"RACE{i}",102                        "QLABEL": f"Race {i}",103                        "QVAL": RACE_MAP.get(answer, ""),104                        "QORIG": "CRF",105                        "QEVAL": "",106                    }107                )108109    with open(f"{OUTPUT_DIR}/dm.csv", "w", newline="", encoding="utf-8") as f:110        writer = csv.DictWriter(f, fieldnames=DM_COLUMNS)111        writer.writeheader()112        writer.writerows(dm_rows)113114    with open(f"{OUTPUT_DIR}/suppdm.csv", "w", newline="", encoding="utf-8") as f:115        writer = csv.DictWriter(f, fieldnames=SUPPDM_COLUMNS)116        writer.writeheader()117        writer.writerows(suppdm_rows)118119120if __name__ == "__main__":121    main()

1/* opensas reference solution for the yamaa benchmark sdtm-dm-race-ethnicity.2   Reads the benchmark inputs and derives the requested output.3   Execute with the existing opensas runtime: opensas /app/output/result.sas. */45data odm;6  length StudyOID MetaDataVersionOID SubjectKey StudyEventOID StudyEventRepeatKey ItemGroupOID ItemGroupRepeatKey ItemOID Value $1024;7  infile "/app/input/odm.csv" dsd dlm="," firstobs=2 truncover lrecl=32767;8  input StudyOID : $char1024. MetaDataVersionOID : $char1024. SubjectKey : $char1024. StudyEventOID : $char1024. StudyEventRepeatKey : $char1024. ItemGroupOID : $char1024. ItemGroupRepeatKey : $char1024. ItemOID : $char1024. Value : $char1024.;9run;1011proc sql;12create table subjects as select distinct StudyOID as STUDYID,SubjectKey as USUBJID from odm;13create table races as select distinct StudyOID as STUDYID,SubjectKey as USUBJID,Value from odm where ItemOID='IT.DM.RACE' and not missing(Value);14quit;15data mapped; set races; length QVAL $1024; if Value in ('White','Asian','Black or African American','American Indian or Alaska Native','Native Hawaiian or Other Pacific Islander') then QVAL=upcase(Value);16else if Value='Other, specify: Fijian' then QVAL='OTHER'; else if Value='Subject refused' then QVAL='UNKNOWN'; else if Value='Not reported' then QVAL='NOT REPORTED'; run;17proc sql; create table racecounts as select STUDYID,USUBJID,count(*) as NRACE from mapped group by STUDYID,USUBJID; quit;18proc sort data=odm out=ordered; by StudyOID SubjectKey; run;19data ethnicity;20  length ETHNIC $1024;21  retain ETHNIC;22  set ordered;2324  by StudyOID SubjectKey;25  if first.SubjectKey then do;26    ETHNIC='';27  end;28    if ItemOID='IT.DM.ETHNIC' then ETHNIC=Value;29  if last.SubjectKey then output;30run;31data ethnic; set ethnicity; length STUDYID USUBJID $1024; STUDYID=StudyOID; USUBJID=SubjectKey;32if ETHNIC in ('Hispanic or Latino','Not Hispanic or Latino','Not reported','Unknown') then ETHNIC=upcase(ETHNIC); else ETHNIC=''; run;33proc sql;34create table dmjoined as select a.*,b.NRACE,c.QVAL,d.ETHNIC from subjects a left join racecounts b on a.STUDYID=b.STUDYID and a.USUBJID=b.USUBJID left join mapped c on a.STUDYID=c.STUDYID and a.USUBJID=c.USUBJID and b.NRACE=1 left join ethnic d on a.STUDYID=d.STUDYID and a.USUBJID=d.USUBJID;35create table multirace as select a.* from mapped a inner join racecounts b on a.STUDYID=b.STUDYID and a.USUBJID=b.USUBJID where b.NRACE>1;36quit;37data dmout; set dmjoined; length DOMAIN $2 SUBJID RACE $1024; DOMAIN='DM'; SUBJID=USUBJID; RACE=QVAL; if NRACE>1 then RACE='MULTIPLE'; keep DOMAIN STUDYID USUBJID SUBJID RACE ETHNIC; run;38proc sort data=multirace; by STUDYID USUBJID Value; run;39data suppout; set multirace; by STUDYID USUBJID; length RDOMAIN $2 IDVAR IDVARVAL QNAM QLABEL QORIG QEVAL $1024; retain N;40if first.USUBJID then N=0; N+1; RDOMAIN='DM'; IDVAR='USUBJID'; IDVARVAL=USUBJID; QNAM=cats('RACE',put(N,best32.)); QLABEL=catx(' ','Race',strip(put(N,best32.))); QORIG='CRF'; QEVAL=''; run;41/* KEEP drops variables but does not set their export order. */42proc sql;43create table dmexport as select DOMAIN,STUDYID,USUBJID,SUBJID,RACE,ETHNIC from dmout;44create table suppdmout as select STUDYID,RDOMAIN,USUBJID,IDVAR,IDVARVAL,QNAM,QLABEL,QVAL,QORIG,QEVAL from suppout;45quit;46proc export data=dmexport outfile='/app/output/dm.csv' dbms=csv replace; run;47proc export data=suppdmout outfile='/app/output/suppdm.csv' dbms=csv replace; run;