Derive a Chain of Population Flags

1library(yamaa)23adsl <- yamaa_domain("spec.yaml")$output4adsl

1import yamaa23adsl = yamaa.yamaa_domain("spec.yaml").output4adsl

1# Reference solution for the yamaa benchmark adam-adsl-flag-chain (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)910dm <- read_csv(11  "/app/input/dm.csv",12  col_types = cols(AGE = col_integer(), RANDDT = col_date(), .default = col_character())13)14ex <- read_csv(15  "/app/input/ex.csv",16  col_types = cols(EXSEQ = col_integer(), EXSTDTC = col_date(), .default = col_character())17)1819first_exposure <- ex |>20  group_by(STUDYID, USUBJID) |>21  summarise(22    TRTSDT = if (all(is.na(EXSTDTC))) as.Date(NA) else min(EXSTDTC, na.rm = TRUE),23    .groups = "drop"24  )2526adsl <- dm |>27  left_join(first_exposure, by = c("STUDYID", "USUBJID")) |>28  mutate(29    SAFFL = if_else(!is.na(TRTSDT), "Y", "N"),30    RANDFL = if_else(!is.na(RANDDT), "Y", "N"),31    ITTFL = if_else(RANDFL == "Y", "Y", "N"),32    POPFL = if_else(SAFFL == "Y" & ITTFL == "Y", "Y", "N"),33    AGEGR1 = if_else(AGE < 65, "<65", ">=65")34  ) |>35  mutate(.idx = row_number()) |>36  arrange(STUDYID, AGE, USUBJID) |>37  group_by(STUDYID) |>38  mutate(AGERNK = row_number()) |>39  ungroup() |>40  arrange(.idx) |>41  select(42    POPFL, SAFFL, ITTFL, TRTSDT, RANDDT, AGEGR1, AGERNK,43    STUDYID, USUBJID, AGE44  )4546dir.create("/app/output", showWarnings = FALSE)47write_csv(adsl, "/app/output/adsl.csv", na = "")

1# Reference solution for the yamaa benchmark adam-adsl-flag-chain (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 1.67from pathlib import Path89import polars as pl1011dm = pl.read_csv("/app/input/dm.csv", infer_schema=False).with_columns(12    pl.col("RANDDT").str.to_date(strict=False),13    pl.col("AGE").cast(pl.Int64, strict=False),14)15ex = pl.read_csv("/app/input/ex.csv", infer_schema=False).with_columns(16    pl.col("EXSTDTC").str.to_date(strict=False),17)1819first_exposure = ex.group_by(["STUDYID", "USUBJID"]).agg(20    TRTSDT=pl.col("EXSTDTC").min()21)2223adsl = (24    dm.join(first_exposure, on=["STUDYID", "USUBJID"], how="left", maintain_order="left")25    .with_columns(26        SAFFL=pl.when(pl.col("TRTSDT").is_not_null())27        .then(pl.lit("Y"))28        .otherwise(pl.lit("N")),29        RANDFL=pl.when(pl.col("RANDDT").is_not_null())30        .then(pl.lit("Y"))31        .otherwise(pl.lit("N")),32    )33    .with_columns(34        ITTFL=pl.when(pl.col("RANDFL") == "Y")35        .then(pl.lit("Y"))36        .otherwise(pl.lit("N")),37    )38    .with_columns(39        POPFL=pl.when((pl.col("SAFFL") == "Y") & (pl.col("ITTFL") == "Y"))40        .then(pl.lit("Y"))41        .otherwise(pl.lit("N")),42        AGEGR1=pl.when(pl.col("AGE") < 65)43        .then(pl.lit("<65"))44        .when(pl.col("AGE") >= 65)45        .then(pl.lit(">=65"))46        .otherwise(None),47    )48)4950# Rank by age within the study, youngest first, USUBJID breaking ties.51ranked = (52    adsl.with_columns(__idx=pl.int_range(pl.len()))53    .sort(["STUDYID", "AGE", "USUBJID"], nulls_last=True)54    .with_columns(AGERNK=pl.int_range(1, pl.len() + 1).over("STUDYID"))55    .sort("__idx")56    .drop("__idx")57    .select(58        "POPFL",59        "SAFFL",60        "ITTFL",61        "TRTSDT",62        "RANDDT",63        "AGEGR1",64        "AGERNK",65        "STUDYID",66        "USUBJID",67        "AGE",68    )69)7071Path("/app/output").mkdir(exist_ok=True)72ranked.write_csv("/app/output/adsl.csv")

1/* opensas reference solution for the yamaa benchmark adam-adsl-flag-chain.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 RANDDT $1024;7  infile "/app/input/dm.csv" dsd dlm="," firstobs=2 truncover lrecl=32767;8  input STUDYID : $char1024. USUBJID : $char1024. AGE RANDDT : $char1024.;9run;1011data ex;12  length STUDYID USUBJID EXSTDTC $1024;13  infile "/app/input/ex.csv" dsd dlm="," firstobs=2 truncover lrecl=32767;14  input STUDYID : $char1024. USUBJID : $char1024. EXSEQ EXSTDTC : $char1024.;15run;1617proc sql;18  create table firstex as select STUDYID,USUBJID,min(EXSTDTC) as TRTSDT from ex where not missing(EXSTDTC) group by STUDYID,USUBJID;19  create table joined as select a.*,b.TRTSDT from dm as a left join firstex as b on a.STUDYID=b.STUDYID and a.USUBJID=b.USUBJID;20quit;21data ranked; set joined; NOAGE=missing(AGE); run;22proc sort data=ranked; by STUDYID NOAGE AGE USUBJID; run;23data result;24  length POPFL SAFFL ITTFL $1 AGEGR1 $4;25  set ranked; by STUDYID;26  if first.STUDYID then AGERNK=0; AGERNK+1;27  SAFFL='N'; ITTFL='N'; POPFL='N';28  if not missing(TRTSDT) then SAFFL='Y';29  if not missing(RANDDT) then ITTFL='Y';30  if SAFFL='Y' and ITTFL='Y' then POPFL='Y';31  if not missing(AGE) then do;32    if AGE<65 then AGEGR1='<65'; else AGEGR1='>=65';33  end;34run;3536proc sql;37  create table final as select POPFL, SAFFL, ITTFL, TRTSDT, RANDDT, AGEGR1, AGERNK, STUDYID, USUBJID, AGE from result;38quit;39proc export data=final outfile="/app/output/adsl.csv" dbms=csv replace; run;