Parent Linkage

1library(yamaa)23suppmh <- yamaa_domain("spec.yaml")$output4suppmh

1import yamaa23suppmh = yamaa.yamaa_domain("spec.yaml").output4suppmh

1# Reference solution for the yamaa benchmark sdtm-suppmh-linkage (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)1011mh <- read_csv(12  "/app/input/mh.csv",13  col_types = cols(.default = col_character())14)15raw <- read_csv(16  "/app/input/mh_supp_raw.csv",17  col_types = cols(.default = col_character())18)1920# The parent sequence number, matched on subject and condition term.21parents <- mh |> select(STUDYID, USUBJID, MHSEQ, MHTERM)2223suppmh <- raw |>24  pivot_longer(25    cols = c(MHFAMHX, MHCONF),26    names_to = "QNAM",27    values_to = "QVAL"28  ) |>29  filter(!is.na(QVAL) & QVAL != "") |>30  inner_join(parents, by = c("STUDYID", "USUBJID", "MHTERM")) |>31  mutate(32    RDOMAIN = "MH",33    IDVAR = "MHSEQ",34    IDVARVAL = MHSEQ,35    QLABEL = case_when(36      QNAM == "MHFAMHX" ~ "Family History",37      QNAM == "MHCONF" ~ "Confirmed by Medical Records"38    ),39    QORIG = "Collected",40    QEVAL = NA_character_41  ) |>42  arrange(USUBJID, suppressWarnings(as.integer(MHSEQ)), QNAM) |>43  select(44    STUDYID, RDOMAIN, USUBJID, IDVAR, IDVARVAL, QNAM, QLABEL, QVAL, QORIG, QEVAL45  )4647dir.create("/app/output", showWarnings = FALSE)48write_csv(suppmh, "/app/output/suppmh.csv", na = "")

1# Reference solution for the yamaa benchmark sdtm-suppmh-linkage (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 pl1011mh = pl.read_csv("/app/input/mh.csv", infer_schema=False)12raw = pl.read_csv("/app/input/mh_supp_raw.csv", infer_schema=False)1314labels = {"MHFAMHX": "Family History", "MHCONF": "Confirmed by Medical Records"}1516# The parent sequence number, matched on subject and condition term.17parents = mh.select("STUDYID", "USUBJID", "MHSEQ", "MHTERM")1819records = []20for qnam in ("MHFAMHX", "MHCONF"):21    collected = (22        raw.filter(pl.col(qnam).is_not_null() & (pl.col(qnam) != ""))23        .join(parents, on=["STUDYID", "USUBJID", "MHTERM"], how="inner")24        .select(25            "STUDYID",26            "USUBJID",27            "MHSEQ",28            QNAM=pl.lit(qnam),29            QLABEL=pl.lit(labels[qnam]),30            QVAL=pl.col(qnam),31        )32    )33    records.append(collected)3435suppmh = (36    pl.concat(records)37    .with_columns(38        RDOMAIN=pl.lit("MH"),39        IDVAR=pl.lit("MHSEQ"),40        IDVARVAL=pl.col("MHSEQ"),41        QORIG=pl.lit("Collected"),42        QEVAL=pl.lit(None, dtype=pl.String),43    )44    .with_columns(pl.col("MHSEQ").cast(pl.Int64).alias("_seq"))45    .sort(["USUBJID", "_seq", "QNAM"])46    .select(47        "STUDYID",48        "RDOMAIN",49        "USUBJID",50        "IDVAR",51        "IDVARVAL",52        "QNAM",53        "QLABEL",54        "QVAL",55        "QORIG",56        "QEVAL",57    )58)5960Path("/app/output").mkdir(exist_ok=True)61suppmh.write_csv("/app/output/suppmh.csv")

1/* opensas reference solution for the yamaa benchmark sdtm-suppmh-linkage.2   Reads the benchmark inputs and derives the requested output.3   Execute with the existing opensas runtime: opensas /app/output/result.sas. */45data mh;6  length STUDYID USUBJID MHTERM $1024;7  infile "/app/input/mh.csv" dsd dlm="," firstobs=2 truncover lrecl=32767;8  input STUDYID : $char1024. USUBJID : $char1024. MHSEQ MHTERM : $char1024.;9run;1011data mh_supp_raw;12  length STUDYID USUBJID MHTERM MHFAMHX MHCONF $1024;13  infile "/app/input/mh_supp_raw.csv" dsd dlm="," firstobs=2 truncover lrecl=32767;14  input STUDYID : $char1024. USUBJID : $char1024. MHTERM : $char1024. MHFAMHX : $char1024. MHCONF : $char1024.;15run;1617proc sql; create table qualified as select a.*,b.MHSEQ from mh_supp_raw a inner join mh b on a.STUDYID=b.STUDYID and a.USUBJID=b.USUBJID and a.MHTERM=b.MHTERM; quit;18data result; set qualified; length RDOMAIN IDVAR IDVARVAL QNAM QLABEL QVAL QORIG QEVAL $1024; RDOMAIN='MH'; IDVAR='MHSEQ'; IDVARVAL=strip(put(MHSEQ,best32.)); QORIG='Collected'; QEVAL='';19if not missing(MHFAMHX) then do; QNAM='MHFAMHX'; QLABEL='Family History'; QVAL=MHFAMHX; output; end;20if not missing(MHCONF) then do; QNAM='MHCONF'; QLABEL='Confirmed by Medical Records'; QVAL=MHCONF; output; end; run;21proc sql;22  create table final as select STUDYID, RDOMAIN, USUBJID, IDVAR, IDVARVAL, QNAM, QLABEL, QVAL, QORIG, QEVAL from result;23quit;24proc export data=final outfile="/app/output/suppmh.csv" dbms=csv replace; run;