DeepHealth/evaluate_all_runs_linux.sh

#!/usr/bin/env bash
#
# Recursively evaluate every completed run under runs/.
#
# A directory is considered a runnable run when it contains both:
#   - train_config.json
#   - best_model.pt
#
# Each missing report is scheduled independently:
#   - evaluate_auc.py
#       -> df_auc_delphi2m_report.csv
#   - evaluate_auc_v2.py
#       -> df_auc_landmark_delphi2m_report.csv
#
# Existing non-empty reports are skipped unless --force is supplied. Each
# evaluation task uses one GPU.
# Tasks on the same GPU run sequentially; different GPUs run in parallel.
#
# Examples:
#   bash evaluate_all_runs_linux.sh --gpus 0
#   bash evaluate_all_runs_linux.sh --gpus 0,1,2,3
#   bash evaluate_all_runs_linux.sh --gpus 0,1 --force
#   bash evaluate_all_runs_linux.sh --gpus 0,1 --dry-run
#

set -uo pipefail

SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
cd "$SCRIPT_DIR"

RUNS_ROOT="$SCRIPT_DIR/runs"
LOG_ROOT="$SCRIPT_DIR/batch_logs/evaluate_all_runs"
GPU_CSV="0"
PYTHON_BIN="${PYTHON_BIN:-python}"
NUM_WORKERS=4
NUM_WORKERS_AUC=4
FORCE=0
DRY_RUN=0

TOKEN_REPORT="df_auc_delphi2m_report.csv"
LANDMARK_REPORT="df_auc_landmark_delphi2m_report.csv"

usage() {
    cat <<'EOF'
Usage:
  bash evaluate_all_runs_linux.sh [options]

Options:
  --gpus LIST            Comma-separated GPU ids (default: 0).
  --runs-root PATH       Root directory scanned recursively (default: ./runs).
  --log-root PATH        Evaluation log root.
  --python PATH          Python executable (default: $PYTHON_BIN or python).
  --num-workers N        DataLoader workers per evaluation (default: 4).
  --num-workers-auc N    CPU AUC workers per evaluation (default: 4).
  --force                Recompute both AUC reports even when they exist.
  --dry-run              Discover runs and print scheduled evaluations only.
  -h, --help             Show this help message.

Completion files:
  evaluate_auc.py        df_auc_delphi2m_report.csv
  evaluate_auc_v2.py     df_auc_landmark_delphi2m_report.csv

Existing non-empty completion files are skipped independently unless --force
is supplied.
EOF
}

while (($# > 0)); do
    case "$1" in
        --gpus)
            [[ $# -ge 2 ]] || {
                echo "ERROR: --gpus requires a value." >&2
                exit 2
            }
            GPU_CSV="$2"
            shift 2
            ;;
        --runs-root)
            [[ $# -ge 2 ]] || {
                echo "ERROR: --runs-root requires a value." >&2
                exit 2
            }
            RUNS_ROOT="$2"
            shift 2
            ;;
        --log-root)
            [[ $# -ge 2 ]] || {
                echo "ERROR: --log-root requires a value." >&2
                exit 2
            }
            LOG_ROOT="$2"
            shift 2
            ;;
        --python)
            [[ $# -ge 2 ]] || {
                echo "ERROR: --python requires a value." >&2
                exit 2
            }
            PYTHON_BIN="$2"
            shift 2
            ;;
        --num-workers)
            [[ $# -ge 2 ]] || {
                echo "ERROR: --num-workers requires a value." >&2
                exit 2
            }
            NUM_WORKERS="$2"
            shift 2
            ;;
        --num-workers-auc)
            [[ $# -ge 2 ]] || {
                echo "ERROR: --num-workers-auc requires a value." >&2
                exit 2
            }
            NUM_WORKERS_AUC="$2"
            shift 2
            ;;
        --force)
            FORCE=1
            shift
            ;;
        --dry-run)
            DRY_RUN=1
            shift
            ;;
        -h|--help)
            usage
            exit 0
            ;;
        *)
            echo "ERROR: unknown argument: $1" >&2
            usage >&2
            exit 2
            ;;
    esac
done

[[ -n "$GPU_CSV" ]] || {
    echo "ERROR: --gpus must not be empty." >&2
    exit 2
}
[[ "$NUM_WORKERS" =~ ^[0-9]+$ ]] || {
    echo "ERROR: --num-workers must be a non-negative integer." >&2
    exit 2
}
[[ "$NUM_WORKERS_AUC" =~ ^[1-9][0-9]*$ ]] || {
    echo "ERROR: --num-workers-auc must be a positive integer." >&2
    exit 2
}
[[ -d "$RUNS_ROOT" ]] || {
    echo "ERROR: runs root does not exist: $RUNS_ROOT" >&2
    exit 2
}
[[ -f "$SCRIPT_DIR/evaluate_auc.py" ]] || {
    echo "ERROR: missing evaluator: $SCRIPT_DIR/evaluate_auc.py" >&2
    exit 2
}
[[ -f "$SCRIPT_DIR/evaluate_auc_v2.py" ]] || {
    echo "ERROR: missing evaluator: $SCRIPT_DIR/evaluate_auc_v2.py" >&2
    exit 2
}
command -v "$PYTHON_BIN" >/dev/null 2>&1 || {
    echo "ERROR: Python executable not found: $PYTHON_BIN" >&2
    exit 2
}

RUNS_ROOT="$(cd -- "$RUNS_ROOT" && pwd)"
if [[ "$LOG_ROOT" != /* ]]; then
    LOG_ROOT="$SCRIPT_DIR/$LOG_ROOT"
fi

IFS=',' read -r -a GPU_IDS <<< "$GPU_CSV"
declare -A SEEN_GPUS=()
for gpu in "${GPU_IDS[@]}"; do
    [[ -n "$gpu" && "$gpu" =~ ^[A-Za-z0-9._:-]+$ ]] || {
        echo "ERROR: invalid GPU id: $gpu" >&2
        exit 2
    }
    [[ -z "${SEEN_GPUS[$gpu]+x}" ]] || {
        echo "ERROR: duplicate GPU id: $gpu" >&2
        exit 2
    }
    SEEN_GPUS["$gpu"]=1
done

declare -a JOB_RUN_DIRS=()
declare -a JOB_EVALUATORS=()
declare -a JOB_REPORTS=()
declare -a JOB_LOG_FILES=()

add_job() {
    local run_dir="$1"
    local evaluator="$2"
    local report_name="$3"
    local relative_run="${run_dir#"$RUNS_ROOT"/}"
    local evaluator_name="${evaluator%.py}"

    JOB_RUN_DIRS+=("$run_dir")
    JOB_EVALUATORS+=("$evaluator")
    JOB_REPORTS+=("$report_name")
    JOB_LOG_FILES+=("$LOG_ROOT/$relative_run/$evaluator_name.log")
}

run_count=0
incomplete_run_count=0
skipped_token_count=0
skipped_landmark_count=0

while IFS= read -r -d '' config_path; do
    run_dir="${config_path%/train_config.json}"
    ((run_count += 1))

    if [[ ! -f "$run_dir/best_model.pt" ]]; then
        echo "[SKIP] Incomplete run without best_model.pt: $run_dir"
        ((incomplete_run_count += 1))
        continue
    fi

    if ((!FORCE)) && [[ -s "$run_dir/$TOKEN_REPORT" ]]; then
        ((skipped_token_count += 1))
    else
        add_job "$run_dir" "evaluate_auc.py" "$TOKEN_REPORT"
    fi

    if ((!FORCE)) && [[ -s "$run_dir/$LANDMARK_REPORT" ]]; then
        ((skipped_landmark_count += 1))
    else
        add_job "$run_dir" "evaluate_auc_v2.py" "$LANDMARK_REPORT"
    fi
done < <(find "$RUNS_ROOT" -type f -name "train_config.json" -print0)

if ((!DRY_RUN)); then
    mkdir -p "$LOG_ROOT"
fi

print_command() {
    printf '%q ' "$@"
    printf '\n'
}

run_job() {
    local job_index="$1"
    local gpu="$2"
    local run_dir="${JOB_RUN_DIRS[$job_index]}"
    local evaluator="${JOB_EVALUATORS[$job_index]}"
    local report_name="${JOB_REPORTS[$job_index]}"
    local log_file="${JOB_LOG_FILES[$job_index]}"
    local -a command=(
        "$PYTHON_BIN"
        -u
        "$SCRIPT_DIR/$evaluator"
        --run_path "$run_dir"
        --output_path "$run_dir"
        --device cuda
        --num_workers "$NUM_WORKERS"
        --num_workers_auc "$NUM_WORKERS_AUC"
    )

    echo "[$(date '+%F %T')] START evaluator=$evaluator gpu=$gpu"
    echo "  run=$run_dir"
    echo "  report=$report_name"

    if ((DRY_RUN)); then
        printf '  CUDA_VISIBLE_DEVICES=%q ' "$gpu"
        print_command "${command[@]}"
        return 0
    fi

    mkdir -p "$(dirname -- "$log_file")"
    if CUDA_VISIBLE_DEVICES="$gpu" PYTHONUNBUFFERED=1 \
        "${command[@]}" >"$log_file" 2>&1; then
        if [[ -s "$run_dir/$report_name" ]]; then
            echo "[$(date '+%F %T')] DONE  evaluator=$evaluator gpu=$gpu"
            return 0
        fi

        echo "[$(date '+%F %T')] FAIL  evaluator=$evaluator gpu=$gpu" >&2
        echo "  Evaluator exited successfully but did not create: $run_dir/$report_name" >&2
        echo "  See: $log_file" >&2
        return 1
    else
        local exit_code=$?
        echo "[$(date '+%F %T')] FAIL  evaluator=$evaluator gpu=$gpu exit=$exit_code" >&2
        echo "  See: $log_file" >&2
        return "$exit_code"
    fi
}

worker() {
    local slot="$1"
    local gpu="${GPU_IDS[$slot]}"
    local job_index
    local failed=0

    for ((job_index = slot; job_index < ${#JOB_RUN_DIRS[@]}; job_index += ${#GPU_IDS[@]})); do
        run_job "$job_index" "$gpu" || failed=1
    done
    return "$failed"
}

force_label="no"
if ((FORCE)); then
    force_label="yes"
fi

echo "Runs root: $RUNS_ROOT"
echo "GPUs: ${GPU_IDS[*]}"
echo "Force recompute: $force_label"
echo "Runs discovered: $run_count"
echo "Incomplete runs skipped: $incomplete_run_count"
echo "Existing token reports skipped: $skipped_token_count"
echo "Existing landmark reports skipped: $skipped_landmark_count"
echo "Scheduled evaluation tasks: ${#JOB_RUN_DIRS[@]}"
echo "Log root: $LOG_ROOT"
echo

if ((${#JOB_RUN_DIRS[@]} == 0)); then
    echo "No AUC evaluation tasks are scheduled."
    exit 0
fi

declare -a WORKER_PIDS=()
for ((slot = 0; slot < ${#GPU_IDS[@]}; slot++)); do
    worker "$slot" &
    WORKER_PIDS+=("$!")
done

overall_status=0
for pid in "${WORKER_PIDS[@]}"; do
    wait "$pid" || overall_status=1
done

if ((overall_status != 0)); then
    echo "One or more evaluation tasks failed. Inspect logs under: $LOG_ROOT" >&2
    exit 1
fi

if ((DRY_RUN)); then
    echo "Dry run completed successfully."
else
    echo "All scheduled AUC evaluations completed successfully."
fi