Text Cleanup

1library(yamaa)23adae <- yamaa_domain("spec.yaml")$output4adae

1import yamaa23adae = yamaa.yamaa_domain("spec.yaml").output4adae

1# Reference solution for the yamaa benchmark adam-adae-text-cleanup (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)1011ae <- read_csv(12  "/app/input/ae.csv",13  col_types = cols(AESEQ = col_integer(), .default = col_character())14)1516adae <- ae |>17  mutate(18    # AE, a hyphen, and exactly three digits; missing is 0, any other shape19    # is -1, and the digits give the number.20    AEREFNUM = case_when(21      is.na(AESPID) | AESPID == "" ~ 0L,22      str_detect(AESPID, "^AE-[0-9]{3}$") ~ suppressWarnings(as.integer(str_sub(AESPID, 4, 6))),23      .default = -1L24    ),25    AETERMLO = tolower(AETERM),26    AERELLC = if_else(is.na(AEREL) | AEREL == "", "not reported", tolower(AEREL)),27    AREL = toupper(AERELLC)28  ) |>29  select(30    STUDYID, USUBJID, AESEQ, AESPID, AEREFNUM, AETERM, AETERMLO, AERELLC, AREL31  )3233dir.create("/app/output", showWarnings = FALSE)34write_csv(adae, "/app/output/adae.csv", na = "")

1# Reference solution for the yamaa benchmark adam-adae-text-cleanup (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 pl1011ae = pl.read_csv("/app/input/ae.csv", infer_schema=False).with_columns(12    pl.col("AESEQ").cast(pl.Int64)13)1415# AE, a hyphen, and exactly three digits; missing is 0, any other shape is16# -1, and the digits give the number.17aerefnum = (18    pl.when(pl.col("AESPID").is_null() | (pl.col("AESPID") == ""))19    .then(0)20    .when(pl.col("AESPID").str.contains(r"^AE-[0-9]{3}$"))21    .then(pl.col("AESPID").str.slice(3).cast(pl.Int64))22    .otherwise(-1)23    .cast(pl.Int64)24)25aerellc = (26    pl.when(pl.col("AEREL").is_null() | (pl.col("AEREL") == ""))27    .then(pl.lit("not reported"))28    .otherwise(pl.col("AEREL").str.to_lowercase())29)3031adae = (32    ae.with_columns(33        AEREFNUM=aerefnum,34        AETERMLO=pl.col("AETERM").str.to_lowercase(),35        AERELLC=aerellc,36    )37    .with_columns(AREL=pl.col("AERELLC").str.to_uppercase())38    .select(39        "STUDYID",40        "USUBJID",41        "AESEQ",42        "AESPID",43        "AEREFNUM",44        "AETERM",45        "AETERMLO",46        "AERELLC",47        "AREL",48    )49)5051Path("/app/output").mkdir(exist_ok=True)52adae.write_csv("/app/output/adae.csv")

1/* opensas reference solution for the yamaa benchmark adam-adae-text-cleanup.2   Reads the benchmark inputs and derives the requested output.3   Execute with the existing opensas runtime: opensas /app/output/result.sas. */45data ae;6  length STUDYID USUBJID AESPID AETERM AEREL $1024;7  infile "/app/input/ae.csv" dsd dlm="," firstobs=2 truncover lrecl=32767;8  input STUDYID : $char1024. USUBJID : $char1024. AESEQ AESPID : $char1024. AETERM : $char1024. AEREL : $char1024.;9run;1011data result;12  length AETERMLO AERELLC AREL $1024;13  set ae;14  if missing(AESPID) then AEREFNUM=0;15  else if prxmatch('/^AE-[0-9]{3}$/',strip(AESPID)) then AEREFNUM=input(substr(AESPID,4,3),best32.);16  else AEREFNUM=-1;17  AETERMLO=lowcase(AETERM); AERELLC=lowcase(AEREL);18  if missing(AEREL) then AERELLC='not reported';19  AREL=upcase(AERELLC);20run;2122proc sql;23  create table final as select STUDYID, USUBJID, AESEQ, AESPID, AEREFNUM, AETERM, AETERMLO, AERELLC, AREL from result;24quit;25proc export data=final outfile="/app/output/adae.csv" dbms=csv replace; run;