Expose dataset/conversion scripts as uv entry points

scripts/ is now a proper package (scripts/__init__.py, added to the wheel's
packages), with each script registered under [project.scripts] using its
bare dashed name (e.g. `uv run migrate-geant-steps`). Tests now import these
modules normally instead of loading them by file path.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

README.md

@@ -34,7 +34,7 @@ The model is developed in two phases:
 
 ## Data
 
-Input: parquet files produced by [miniCaloSim](https://gitlab.etp.kit.edu/lbogner/minicalosim), or converted from a ROOT file via `scripts/steps_to_parquet.py`. Each row is one Geant4 step. Train/val split is by `event_id` (not row shuffle) to avoid leaking correlated steps from the same shower.
+Input: parquet files produced by [miniCaloSim](https://gitlab.etp.kit.edu/lbogner/minicalosim), or converted from a ROOT file via `uv run steps-to-parquet`. Each row is one Geant4 step. Train/val split is by `event_id` (not row shuffle) to avoid leaking correlated steps from the same shower.
 
 ## Project structure
 
@@ -55,9 +55,13 @@ giant/
 │   ├── validate.py         # step-level marginal + KL-divergence validation
 │   ├── analysis.py         # notebook diagnostics: marginals, correlations, constraint checks
 │   └── cli.py              # `giant train` / `giant predict` Typer app
-├── scripts/
-│   ├── train.py              # argparse training entry point
-│   └── steps_to_parquet.py   # ROOT → parquet conversion (uproot/awkward/polars)
+├── scripts/                            # also exposed as uv entry points, e.g. `uv run steps-to-parquet`
+│   ├── steps_to_parquet.py             # ROOT → parquet conversion (uproot/awkward/polars)
+│   ├── steps_to_parquet_parallel.py    # fan out steps_to_parquet.py over several ROOT files
+│   ├── migrate_geant_steps.py          # one-time move into the raw/processed/pools/derived layout
+│   ├── bump_dataset_version.py         # cut a new raw gen or parquet schema, with a logged reason
+│   ├── create_root_files.py            # generate new ROOT shards via a minicalosim executable
+│   └── hparam_scan.py                  # hyperparameter grid scan over `giant train` runs
 └── tests/
 ```
 

pyproject.toml

@@ -37,13 +37,18 @@ analysis = [
 
 [project.scripts]
 giant = "giant.cli:app"
+steps-to-parquet = "scripts.steps_to_parquet:main"
+steps-to-parquet-parallel = "scripts.steps_to_parquet_parallel:main"
+migrate-geant-steps = "scripts.migrate_geant_steps:main"
+bump-dataset-version = "scripts.bump_dataset_version:main"
+create-root-files = "scripts.create_root_files:main"
 
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
 
 [tool.hatch.build.targets.wheel]
-packages = ["giant"]
+packages = ["giant", "scripts"]
 
 [tool.uv]
 conflicts = [

tests/test_bump_dataset_version.py

@@ -1,13 +1,4 @@
-import importlib.util
-from pathlib import Path
-
-# scripts/ is not an installed package — load the module straight from its path.
-_SPEC = importlib.util.spec_from_file_location(
-    "bump_dataset_version",
-    Path(__file__).resolve().parents[1] / "scripts" / "bump_dataset_version.py",
-)
-bump_dataset_version = importlib.util.module_from_spec(_SPEC)
-_SPEC.loader.exec_module(bump_dataset_version)
+from scripts import bump_dataset_version
 
 plan_bump_gen = bump_dataset_version.plan_bump_gen
 plan_bump_schema = bump_dataset_version.plan_bump_schema

tests/test_create_root_files.py

@@ -1,17 +1,10 @@
-import importlib.util
 import json
 import stat
 from pathlib import Path
 
 import pytest
 
-# scripts/ is not an installed package — load the module straight from its path.
-_SPEC = importlib.util.spec_from_file_location(
-    "create_root_files",
-    Path(__file__).resolve().parents[1] / "scripts" / "create_root_files.py",
-)
-create_root_files = importlib.util.module_from_spec(_SPEC)
-_SPEC.loader.exec_module(create_root_files)
+from scripts import create_root_files
 
 parse_detector_spec = create_root_files.parse_detector_spec
 next_shard_index = create_root_files.next_shard_index

tests/test_steps_to_parquet.py

@@ -1,15 +1,6 @@
-import importlib.util
-from pathlib import Path
-
 import polars as pl
 
-# scripts/ is not an installed package — load the module straight from its path.
-_SPEC = importlib.util.spec_from_file_location(
-    "steps_to_parquet",
-    Path(__file__).resolve().parents[1] / "scripts" / "steps_to_parquet.py",
-)
-steps_to_parquet = importlib.util.module_from_spec(_SPEC)
-_SPEC.loader.exec_module(steps_to_parquet)
+from scripts import steps_to_parquet
 
 
 def _frame() -> pl.DataFrame:

tests/test_steps_to_parquet_parallel.py

@@ -1,14 +1,7 @@
-import importlib.util
 import json
 from pathlib import Path
 
-# scripts/ is not an installed package — load the module straight from its path.
-_SPEC = importlib.util.spec_from_file_location(
-    "steps_to_parquet_parallel",
-    Path(__file__).resolve().parents[1] / "scripts" / "steps_to_parquet_parallel.py",
-)
-steps_to_parquet_parallel = importlib.util.module_from_spec(_SPEC)
-_SPEC.loader.exec_module(steps_to_parquet_parallel)
+from scripts import steps_to_parquet_parallel
 
 run_parallel = steps_to_parquet_parallel.run_parallel
 resolve_destination = steps_to_parquet_parallel.resolve_destination