Standardize Collected Sex, Race, and Age

1library(yamaa)23yamaa_spec("spec.yaml")$run()$output

1import yamaa23yamaa.spec("spec.yaml").run().output

1# Reference solution for the yamaa benchmark adam-adsl-demographics (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(stringr)1011dm <- read_csv(12  "/app/input/dm.csv",13  col_types = cols(.default = col_character())14)1516adsl <- dm |>17  mutate(18    SEX = str_trim(coalesce(SEX, "")),19    SEX = if_else(SEX == "", "U", SEX),20    SEXN = case_when(21      SEX == "M" ~ 1L,22      SEX == "F" ~ 2L,23      SEX == "U" ~ 0L24    ),25    RACEN = case_when(26      is.na(RACE) ~ NA_integer_,27      RACE == "WHITE" ~ 1L,28      RACE == "BLACK OR AFRICAN AMERICAN" ~ 2L,29      RACE == "ASIAN" ~ 3L,30      RACE == "MULTIPLE" ~ 4L,31      .default = 99L32    ),33    .age_num = suppressWarnings(as.numeric(str_trim(coalesce(AGE, "")))),34    AGE = if_else(35      !is.na(.age_num) & floor(.age_num) == .age_num,36      as.integer(.age_num),37      NA_integer_38    ),39    AGEGR1 = case_when(40      is.na(AGE) ~ "UNKNOWN",41      AGE < 18 ~ "<18",42      AGE < 65 ~ "18-64",43      .default = ">=65"44    )45  ) |>46  select(STUDYID, USUBJID, SEX, SEXN, RACE, RACEN, AGE, AGEGR1)4748dir.create("/app/output", showWarnings = FALSE)49write_csv(adsl, "/app/output/adsl.csv", na = "")

1# Reference solution for the yamaa benchmark adam-adsl-demographics (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"""Create ADSL demographics from the DM dataset.89One record per subject. Reads /app/input/dm.csv and writes10/app/output/adsl.csv with columns:11STUDYID, USUBJID, SEX, SEXN, RACE, RACEN, AGE, AGEGR112"""1314import csv15import os1617INPUT_DIR = "/app/input"18OUTPUT_DIR = "/app/output"1920SEXN_MAP = {"M": 1, "F": 2, "U": 0}21RACEN_MAP = {22    "WHITE": 1,23    "BLACK OR AFRICAN AMERICAN": 2,24    "ASIAN": 3,25    "MULTIPLE": 4,26}272829def main():30    with open(os.path.join(INPUT_DIR, "dm.csv"), newline="") as f:31        dm = list(csv.DictReader(f))3233    rows = []34    for rec in dm:35        sex_raw = (rec.get("SEX") or "").strip()36        sex = sex_raw if sex_raw else "U"37        sexn = SEXN_MAP.get(sex, 0)3839        race = (rec.get("RACE") or "").strip()40        if race == "":41            racen = ""42        elif race in RACEN_MAP:43            racen = RACEN_MAP[race]44        else:45            racen = 994647        age_raw = (rec.get("AGE") or "").strip()48        if age_raw == "":49            age = ""50            agegr1 = "UNKNOWN"51        else:52            age = int(float(age_raw))53            if age < 18:54                agegr1 = "<18"55            elif age < 65:56                agegr1 = "18-64"57            else:58                agegr1 = ">=65"5960        rows.append(61            {62                "STUDYID": rec.get("STUDYID", ""),63                "USUBJID": rec.get("USUBJID", ""),64                "SEX": sex,65                "SEXN": sexn,66                "RACE": race,67                "RACEN": racen,68                "AGE": age,69                "AGEGR1": agegr1,70            }71        )7273    os.makedirs(OUTPUT_DIR, exist_ok=True)74    fieldnames = ["STUDYID", "USUBJID", "SEX", "SEXN", "RACE", "RACEN", "AGE", "AGEGR1"]75    with open(os.path.join(OUTPUT_DIR, "adsl.csv"), "w", newline="") as f:76        writer = csv.DictWriter(f, fieldnames=fieldnames)77        writer.writeheader()78        writer.writerows(rows)798081if __name__ == "__main__":82    main()

1/* opensas reference solution for the yamaa benchmark adam-adsl-demographics.2   Reads the benchmark inputs and derives the requested output.3   Execute with the existing opensas runtime: opensas /app/output/result.sas. */45data dm;6  length STUDYID USUBJID SEX RACE $1024;7  infile "/app/input/dm.csv" dsd dlm="," firstobs=2 truncover lrecl=32767;8  input STUDYID : $char1024. USUBJID : $char1024. SEX : $char1024. RACE : $char1024. AGE;9run;1011data result;12  length AGEGR1 $7;13  set dm;14  if missing(SEX) then SEX='U';15  select(SEX); when('M') SEXN=1; when('F') SEXN=2; otherwise SEXN=0; end;16  select(RACE);17    when('') RACEN=.; when('WHITE') RACEN=1;18    when('BLACK OR AFRICAN AMERICAN') RACEN=2;19    when('ASIAN') RACEN=3; when('MULTIPLE') RACEN=4; otherwise RACEN=99;20  end;21  if AGE ne int(AGE) then AGE=.;22  if missing(AGE) then AGEGR1='UNKNOWN';23  else if AGE<18 then AGEGR1='<18';24  else if AGE<65 then AGEGR1='18-64'; else AGEGR1='>=65';25run;2627proc sql;28  create table final as select STUDYID, USUBJID, SEX, SEXN, RACE, RACEN, AGE, AGEGR1 from result;29quit;30proc export data=final outfile="/app/output/adsl.csv" dbms=csv replace; run;