Wire local-only data setup workflow

2026-06-15 14:38:47 +02:00
parent b5ca9370f1
commit d9c648bd54
21 changed files with 2442 additions and 110 deletions
@@ -0,0 +1,59 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+MODE="${1:---dry-run}"
+repo_root="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd -P)"
+cd "$repo_root"
+
+case "$MODE" in
+  --dry-run|--download-only|--build-test|--compare|--full-test) ;;
+  *)
+    echo "Usage: $0 [--dry-run|--download-only|--build-test|--compare|--full-test]" >&2
+    exit 1
+    ;;
+esac
+
+export PARTY2D_RAW_DATA_DIR="${PARTY2D_RAW_DATA_DIR:-$repo_root/_local/raw}"
+export PARTY2D_BUILD_DIR="${PARTY2D_BUILD_DIR:-$repo_root/_local/build}"
+export PARTY2D_GENERATED_INPUT_DIR="${PARTY2D_GENERATED_INPUT_DIR:-$repo_root/_local/generated-inputs}"
+export PARTY2D_REPORT_DIR="${PARTY2D_REPORT_DIR:-$repo_root/_local/reports}"
+export R_LIBS_USER="${R_LIBS_USER:-$repo_root/_local/R/library}"
+mkdir -p "$R_LIBS_USER"
+
+if [ "$MODE" = "--dry-run" ]; then
+  echo "Checking data-setup scripts only; no downloads and no rebuild."
+  command -v bash >/dev/null
+  command -v Rscript >/dev/null
+  command -v python3 >/dev/null
+  bash -n data-setup/check_raw_data.sh
+  python3 -m py_compile data-setup/download_sources.py
+  python3 -m py_compile data-setup/compare_generated_inputs.py
+  Rscript -e 'files <- list.files("data-setup/R", pattern="\\.R$", full.names=TRUE); invisible(lapply(files, parse)); cat("R setup scripts parse OK\n")'
+  echo "Data setup dry run passed."
+  exit 0
+fi
+
+if [ "$MODE" = "--download-only" ]; then
+  python3 data-setup/download_sources.py
+  exit 0
+fi
+
+if [ "$MODE" = "--compare" ]; then
+  python3 data-setup/compare_generated_inputs.py
+  exit 0
+fi
+
+if [ "$MODE" = "--full-test" ]; then
+  python3 data-setup/download_sources.py || true
+fi
+
+bash data-setup/check_raw_data.sh
+rm -rf "$PARTY2D_BUILD_DIR" "$PARTY2D_GENERATED_INPUT_DIR"
+mkdir -p "$PARTY2D_BUILD_DIR" "$PARTY2D_GENERATED_INPUT_DIR"
+Rscript data-setup/R/00_install_dependencies.R
+Rscript data-setup/R/02_build_model_inputs.R
+if [ "$MODE" = "--full-test" ]; then
+  python3 data-setup/compare_generated_inputs.py || true
+else
+  python3 data-setup/compare_generated_inputs.py
+fi