Wire local-only data setup workflow

This commit is contained in:
aseimel
2026-06-15 14:38:47 +02:00
parent b5ca9370f1
commit d9c648bd54
21 changed files with 2442 additions and 110 deletions
+14 -7
View File
@@ -17,27 +17,33 @@ export PARTY2D_RAW_DATA_DIR="${PARTY2D_RAW_DATA_DIR:-$repo_root/_local/raw}"
export TMPDIR="${TMPDIR:-$repo_root/_local/tmp}"
mkdir -p "$TMPDIR"
required_model_inputs=(
"data/text_data.csv"
"data/expert.csv"
"data/lr_data.csv"
"data/union_mapping.csv"
"data/party_families.csv"
)
if [ "$MODE" = "dry-run" ]; then
echo "Checking commands..."
command -v bash >/dev/null
command -v Rscript >/dev/null
command -v julia >/dev/null
echo "Checking key files..."
test -f Project.toml
test -f Manifest.toml
test -f models/stan_model_2dim_v6.stan
test -f data/text_data.csv
test -f data/expert.csv
test -f data/lr_data.csv
test -f data/model_data.csv
for input in "${required_model_inputs[@]}"; do
test -f "$input"
done
echo "Checking shell syntax..."
bash -n scripts/01_prepare_data.sh
bash -n scripts/02_fit_model.sh
bash -n scripts/03_extract_estimates.sh
bash -n scripts/04_enrich_estimates.sh
bash -n scripts/05_validate_estimates.sh
echo "Checking R syntax..."
Rscript -e 'files <- list.files("src/r", pattern="\\.R$", full.names=TRUE); invisible(lapply(files, parse))'
bash -n data-setup/run_data_setup.sh
bash -n data-setup/check_raw_data.sh
echo "Checking Julia project can instantiate without running model code..."
julia --project=. -e 'import Pkg; Pkg.instantiate(); println("Julia project OK")'
echo "Dry run passed. No model fitting was run."
@@ -54,3 +60,4 @@ fi
bash scripts/03_extract_estimates.sh
bash scripts/04_enrich_estimates.sh
bash scripts/05_validate_estimates.sh