lars
7df1945384
CI / Sync project version with tag (pull_request) Has been skipped
CI / Lint (ruff check) (pull_request) Successful in 1m6s
CI / Format (ruff format) (pull_request) Successful in 1m11s
CI / Type check (ty) (pull_request) Successful in 1m12s
CI / Tests (pull_request) Successful in 4m16s
CI / Bump version, tag, and update changelog on merge to master (pull_request) Has been skipped
CI / Publish package to Gitea package registry (pull_request) Has been skipped
giant.pipeline.run_setup_stage (used by both giant train and dwarf warm-cache) previously opened and fully read each parquet file 4-6 separate times via pandas, with per-row Python loops padding the secondary list columns on every chunk of the normalizer-fitting pass. - giant/data/loader.py: pandas -> polars throughout; ragged sec_*_list padding is now a single vectorized polars expression instead of a per-row Python loop (including a .iloc[i] loop for directions). - giant/data/scan.py (new): a fused metadata scan answering the event index, pdg/material vocab, process counts, and pooled-pdg counts in one pass per file instead of one pass per section. Frequency-ranking ties are now an explicit (-count, first_seen) contract instead of an accident of pandas' value_counts iteration order. - giant/pipeline.py: run_setup_stage restructured to consult the cache for every section first, then issue one combined scan request for whatever's missing. - giant/geometry.py: ported the one remaining pandas groupby to polars. - pyproject.toml: polars promoted to a core dependency, pandas moved to dev (only test fixtures still use it). - giant/tools/profile_setup_scan.py (new): synthetic-data benchmark for this scan, mirroring profile_analysis_costs.py's pattern. Also fixes a real deadlock this surfaced: DataLoader worker subprocesses fork() on Linux, and polars' native thread pool doesn't survive a fork — a worker touching polars after the parent already had hangs instantly. giant/pipeline.py's train/val DataLoaders now use multiprocessing_context="spawn" whenever num_workers>0. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01DdT32YWNEwnVLZUHsgdeSC
110 lines
2.2 KiB
TOML
110 lines
2.2 KiB
TOML
[project]
|
|
name = "giant"
|
|
version = "0.3.16"
|
|
description = "Geant4 step-function surrogate via conditional flow matching"
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
dependencies = [
|
|
"numpy>=1.26,<3",
|
|
"polars>=1.0,<2",
|
|
"pyarrow>=16,<25",
|
|
"tqdm>=4.60,<5",
|
|
"typer>=0.12,<1",
|
|
"pyyaml>=6,<7",
|
|
"particle>=1.0,<2",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
cpu = [
|
|
"torch>=2.3,<2.4",
|
|
]
|
|
cuda = [
|
|
"torch>=2.3,<2.4",
|
|
]
|
|
dev = [
|
|
"pytest>=8,<10",
|
|
"pytest-cov>=5,<8",
|
|
"ruff>=0.15,<1",
|
|
"ty>=0.0.50,<0.1",
|
|
"bump-my-version>=1.2,<2",
|
|
"git-cliff>=2,<3",
|
|
# Only used by test fixtures (writing small parquet files) — not a
|
|
# runtime dependency of giant itself since the pandas -> polars
|
|
# data-loading rewrite.
|
|
"pandas>=2.2,<4",
|
|
"giant[convert,analysis,geometry,wandb]",
|
|
]
|
|
geometry = [
|
|
"scikit-learn>=1.4,<2",
|
|
]
|
|
wandb = [
|
|
"wandb>=0.16,<1",
|
|
]
|
|
convert = [
|
|
"uproot>=5.3,<6",
|
|
"awkward>=2.6,<3",
|
|
"polars>=1.0,<2",
|
|
]
|
|
analysis = [
|
|
"matplotlib>=3.8,<4",
|
|
"polars>=1.0,<2",
|
|
"ipykernel>=7.3.0",
|
|
# KIT matplotlib theme, published from git.larsbogner.de. Only the local
|
|
# `giant analyze render` step imports it; compute workers never do.
|
|
"plotstyle>=1.0.0",
|
|
]
|
|
|
|
[project.scripts]
|
|
giant = "giant.cli:app"
|
|
dwarf = "giant.tools.dwarf:app"
|
|
|
|
[tool.ruff]
|
|
line-length = 120
|
|
|
|
[tool.coverage.run]
|
|
source = ["giant"]
|
|
omit = ["*/legacy/*"]
|
|
|
|
[tool.coverage.report]
|
|
exclude_also = [
|
|
"if TYPE_CHECKING:",
|
|
"raise NotImplementedError",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["giant"]
|
|
|
|
[tool.uv]
|
|
conflicts = [
|
|
[
|
|
{ extra = "cpu" },
|
|
{ extra = "cuda" },
|
|
],
|
|
]
|
|
|
|
[tool.uv.sources]
|
|
torch = [
|
|
{ index = "pytorch-cpu", extra = "cpu" },
|
|
{ index = "pytorch-cu118", extra = "cuda" },
|
|
]
|
|
plotstyle = { index = "larsbogner" }
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-cpu"
|
|
url = "https://download.pytorch.org/whl/cpu"
|
|
explicit = true
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-cu118"
|
|
url = "https://download.pytorch.org/whl/cu118"
|
|
explicit = true
|
|
|
|
[[tool.uv.index]]
|
|
name = "larsbogner"
|
|
url = "https://git.larsbogner.de/api/packages/lars/pypi/simple/"
|
|
explicit = true
|