Collected Medications with Dose Text and Timing References

1library(yamaa)23cm <- yamaa_domain("spec.yaml")$output4cm

1import yamaa23cm = yamaa.yamaa_domain("spec.yaml").output4cm

1# Reference solution for the yamaa benchmark sdtm-cm-collected-medications (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)1112odm <- read_csv(13  "/app/input/odm.csv",14  col_types = cols(.default = col_character())15)1617# A plain number carries the dose; anything else (like a range 50-75) stays18# as text. Frequency and route labels map to controlled terminology.19cm <- odm |>20  filter(ItemGroupOID == "IG.CM") |>21  pivot_wider(22    id_cols = c(StudyOID, SubjectKey, ItemGroupRepeatKey),23    names_from = ItemOID,24    values_from = Value,25    values_fn = first26  ) |>27  mutate(28    CMSEQ = as.integer(ItemGroupRepeatKey),29    DOSE_RAW = str_trim(`IT.CM.CMDSTXT`),30    DOSE_PLAIN = str_detect(DOSE_RAW, "^\\d+(\\.\\d+)?$"),31    # BEFORE/SCREENING when the taken-before-study box is checked; ONGOING/32    # END OF STUDY when the ongoing box is checked. An ongoing medication33    # has no end date.34    DOMAIN = "CM",35    STUDYID = StudyOID,36    USUBJID = SubjectKey,37    CMTRT = na_if(`IT.CM.CMTRT`, ""),38    CMINDC = na_if(`IT.CM.CMINDC`, ""),39    CMDOSE = if_else(40      DOSE_PLAIN, suppressWarnings(as.numeric(DOSE_RAW)), NA_real_,41      missing = NA_real_42    ),43    CMDOSTXT = if_else(44      DOSE_PLAIN, NA_character_, na_if(DOSE_RAW, ""), missing = na_if(DOSE_RAW, "")45    ),46    CMDOSU = na_if(`IT.CM.CMDOSU`, ""),47    CMDOSFRQ = case_when(48      `IT.CM.CMDOSFRQ` == "Once daily" ~ "QD",49      `IT.CM.CMDOSFRQ` == "Twice daily" ~ "BID",50      .default = na_if(`IT.CM.CMDOSFRQ`, "")51    ),52    CMROUTE = case_when(53      `IT.CM.CMROUTE` == "By mouth" ~ "ORAL",54      .default = na_if(`IT.CM.CMROUTE`, "")55    ),56    CMSTDTC = na_if(`IT.CM.CMSTDTC`, ""),57    CMENDTC = if_else(58      `IT.CM.CMONGO` == "Y", NA_character_, na_if(`IT.CM.CMENDTC`, ""),59      missing = na_if(`IT.CM.CMENDTC`, "")60    ),61    CMSTRTPT = if_else(`IT.CM.CMPRIOR` == "Y", "BEFORE", NA_character_, missing = NA_character_),62    CMSTTPT = if_else(`IT.CM.CMPRIOR` == "Y", "SCREENING", NA_character_, missing = NA_character_),63    CMENRTPT = if_else(`IT.CM.CMONGO` == "Y", "ONGOING", NA_character_, missing = NA_character_),64    CMENTPT = if_else(65      `IT.CM.CMONGO` == "Y", "END OF STUDY", NA_character_, missing = NA_character_66    )67  ) |>68  arrange(USUBJID, CMSEQ) |>69  select(70    DOMAIN, STUDYID, USUBJID, CMSEQ, CMTRT, CMINDC, CMDOSE, CMDOSTXT,71    CMDOSU, CMDOSFRQ, CMROUTE, CMSTDTC, CMENDTC, CMSTRTPT, CMSTTPT,72    CMENRTPT, CMENTPT73  )7475dir.create("/app/output", showWarnings = FALSE)76write_csv(cm, "/app/output/cm.csv", na = "")

1# Reference solution for the yamaa benchmark sdtm-cm-collected-medications (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 1.67import re8from pathlib import Path910import polars as pl1112odm = pl.read_csv("/app/input/odm.csv", infer_schema=False)1314wide = odm.filter(pl.col("ItemGroupOID") == "IG.CM").pivot(15    index=["StudyOID", "SubjectKey", "ItemGroupRepeatKey"],16    on="ItemOID",17    values="Value",18    aggregate_function="first",19)2021# A plain number carries the dose; anything else (like a range 50-75) stays22# as text. Frequency and route labels map to controlled terminology.23def is_plain_number(value: str | None) -> bool:24    return value is not None and re.fullmatch(r"\d+(\.\d+)?", value.strip() or "") is not None252627rows = []28for record in wide.to_dicts():29    dose_raw = (record.get("IT.CM.CMDSTXT") or "").strip() or None30    if dose_raw is not None and is_plain_number(dose_raw):31        dose, dosetxt = float(dose_raw), None32    else:33        dose, dosetxt = None, dose_raw34    freq_raw = record.get("IT.CM.CMDOSFRQ")35    freq = {"Once daily": "QD", "Twice daily": "BID"}.get(freq_raw, freq_raw) or None36    route_raw = record.get("IT.CM.CMROUTE")37    route = {"By mouth": "ORAL"}.get(route_raw, route_raw) or None38    prior = record.get("IT.CM.CMPRIOR")39    ongo = record.get("IT.CM.CMONGO")40    # BEFORE/SCREENING when the taken-before-study box is checked; ONGOING/41    # END OF STUDY when the ongoing box is checked. An ongoing medication42    # has no end date.43    endtc = record.get("IT.CM.CMENDTC") or None44    if ongo == "Y":45        endtc = None46    rows.append(47        {48            "DOMAIN": "CM",49            "STUDYID": record["StudyOID"],50            "USUBJID": record["SubjectKey"],51            "CMSEQ": int(record["ItemGroupRepeatKey"]),52            "CMTRT": record.get("IT.CM.CMTRT") or None,53            "CMINDC": record.get("IT.CM.CMINDC") or None,54            "CMDOSE": dose,55            "CMDOSTXT": dosetxt,56            "CMDOSU": record.get("IT.CM.CMDOSU") or None,57            "CMDOSFRQ": freq,58            "CMROUTE": route,59            "CMSTDTC": record.get("IT.CM.CMSTDTC") or None,60            "CMENDTC": endtc,61            "CMSTRTPT": "BEFORE" if prior == "Y" else None,62            "CMSTTPT": "SCREENING" if prior == "Y" else None,63            "CMENRTPT": "ONGOING" if ongo == "Y" else None,64            "CMENTPT": "END OF STUDY" if ongo == "Y" else None,65        }66    )6768cm = pl.DataFrame(69    rows,70    schema={71        "DOMAIN": pl.String,72        "STUDYID": pl.String,73        "USUBJID": pl.String,74        "CMSEQ": pl.Int64,75        "CMTRT": pl.String,76        "CMINDC": pl.String,77        "CMDOSE": pl.Float64,78        "CMDOSTXT": pl.String,79        "CMDOSU": pl.String,80        "CMDOSFRQ": pl.String,81        "CMROUTE": pl.String,82        "CMSTDTC": pl.String,83        "CMENDTC": pl.String,84        "CMSTRTPT": pl.String,85        "CMSTTPT": pl.String,86        "CMENRTPT": pl.String,87        "CMENTPT": pl.String,88    },89).sort(["USUBJID", "CMSEQ"])9091Path("/app/output").mkdir(exist_ok=True)92cm.write_csv("/app/output/cm.csv")

1/* opensas reference solution for the yamaa benchmark sdtm-cm-collected-medications.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 sort data=odm out=ordered; by StudyOID SubjectKey ItemGroupRepeatKey; run;12data wide;13  length CMTRT CMINDC CMDOSU CMDOSFRQ CMROUTE CMSTDTC CMENDTC CMPRIOR CMONGO DOSETEXT $1024;14  retain CMTRT CMINDC CMDOSU CMDOSFRQ CMROUTE CMSTDTC CMENDTC CMPRIOR CMONGO DOSETEXT;15  set ordered;16  where ItemGroupOID='IG.CM';17  by StudyOID SubjectKey ItemGroupRepeatKey;18  if first.ItemGroupRepeatKey then do;19    CMTRT=''; CMINDC=''; CMDOSU=''; CMDOSFRQ=''; CMROUTE=''; CMSTDTC=''; CMENDTC=''; CMPRIOR=''; CMONGO=''; DOSETEXT='';20  end;21    if ItemOID='IT.CM.CMTRT' then CMTRT=Value;22  if ItemOID='IT.CM.CMINDC' then CMINDC=Value;23  if ItemOID='IT.CM.CMDOSU' then CMDOSU=Value;24  if ItemOID='IT.CM.CMDOSFRQ' then CMDOSFRQ=Value;25  if ItemOID='IT.CM.CMROUTE' then CMROUTE=Value;26  if ItemOID='IT.CM.CMSTDTC' then CMSTDTC=Value;27  if ItemOID='IT.CM.CMENDTC' then CMENDTC=Value;28  if ItemOID='IT.CM.CMPRIOR' then CMPRIOR=Value;29  if ItemOID='IT.CM.CMONGO' then CMONGO=Value;30  if ItemOID='IT.CM.CMDSTXT' then DOSETEXT=Value;31  if last.ItemGroupRepeatKey then output;32run;33data result; set wide; length DOMAIN $2 STUDYID USUBJID CMDOSTXT CMSTRTPT CMSTTPT CMENRTPT CMENTPT $1024;34DOMAIN='CM'; STUDYID=StudyOID; USUBJID=SubjectKey; CMSEQ=input(ItemGroupRepeatKey,best32.);35if prxmatch('/^[+-]?[0-9]+(\.[0-9]+)?$/',strip(DOSETEXT)) then CMDOSE=input(DOSETEXT,best32.); else CMDOSTXT=DOSETEXT;36if CMDOSFRQ='Once daily' then CMDOSFRQ='QD'; if CMDOSFRQ='Twice daily' then CMDOSFRQ='BID'; if CMROUTE='By mouth' then CMROUTE='ORAL';37if CMPRIOR='Y' then do; CMSTRTPT='BEFORE'; CMSTTPT='SCREENING'; end;38if CMONGO='Y' then do; CMENDTC=''; CMENRTPT='ONGOING'; CMENTPT='END OF STUDY'; end; run;39proc sql;40  create table final as select DOMAIN, STUDYID, USUBJID, CMSEQ, CMTRT, CMINDC, CMDOSE, CMDOSTXT, CMDOSU, CMDOSFRQ, CMROUTE, CMSTDTC, CMENDTC, CMSTRTPT, CMSTTPT, CMENRTPT, CMENTPT from result;41quit;42proc export data=final outfile="/app/output/cm.csv" dbms=csv replace; run;