complience with scientific python guide

.github/workflows/docs.yml

@@ -8,6 +8,7 @@ on:
     branches:
       - main
   pull_request:
+  workflow_dispatch:
 jobs:
   Docs:
     runs-on: ubuntu-22.04

.github/workflows/tests.yml

@@ -8,6 +8,9 @@ on:
     branches:
       - main
   pull_request:
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
 jobs:
   Tests:
     runs-on: ${{ matrix.os }}

.pre-commit-config.yaml

@@ -10,15 +10,16 @@ repos:
     rev: v4.0.0-alpha.8
     hooks:
       - id: prettier
+        files: \.ya?ml$
   - repo: https://github.com/fsfe/reuse-tool
-    rev: v2.1.0
+    rev: v3.0.1
     hooks:
       - id: reuse
   - repo: https://github.com/codespell-project/codespell
     rev: v2.2.6
     hooks:
       - id: codespell
-  - repo: https://github.com/asottile/blacken-docs
+  - repo: https://github.com/adamchainz/blacken-docs
     rev: "1.16.0"
     hooks:
       - id: blacken-docs
@@ -38,7 +39,7 @@ repos:
         exclude: ^contrib/
         additional_dependencies: [numpy, pandas]
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.9
+    rev: v0.1.14
     hooks:
       - id: ruff
         args: [--fix, --show-fixes]

contrib/print_flux.py

@@ -9,6 +9,7 @@
 from sys import argv
 
 import numpy as np
+
 from simweights import _fluxes
 
 E = np.logspace(2, 10, 9)

examples/additional_flux_params.py

@@ -6,10 +6,10 @@
 
 import pandas as pd
 import pylab as plt
+from numpy.typing import ArrayLike
 
 # start-box1
 import simweights
-from numpy.typing import ArrayLike
 
 # load the hdf5 file and make the weigher
 hdffile = pd.HDFStore("Level2_IC86.2016_NuMu.021217.N100.hdf5", "r")

examples/basic_genie.py

@@ -6,6 +6,7 @@
 
 import nuflux
 import pandas as pd
+
 import simweights
 
 simfile = pd.HDFStore("genie_reader_NuE_C_corr.hdf5")

examples/combined_plot.py

@@ -6,9 +6,10 @@
 
 import numpy as np
 import pylab as plt
-import simweights
 import tables
 
+import simweights
+
 # start-box1
 # load the Medium Energy file
 ME_file = tables.File("Level2_IC86.2016_corsika.021746.hdf5", "r")

examples/effective_area.py

@@ -6,9 +6,10 @@
 
 import numpy as np
 import pylab as plt
-import simweights
 import tables
 
+import simweights
+
 # start-example1
 # load hdf5 file
 f = tables.open_file("Level2_IC86.2016_NuMu.021217.N100.hdf5", "r")

examples/icetop_plot.py

@@ -8,9 +8,10 @@
 
 import numpy as np
 import pylab as plt
-import simweights
 import tables
 
+import simweights
+
 # —- Define which files you want to be part of the dataset ——
 # (This particular example is all low-energy protons)
 FILE_DIR = Path("/data/ana/CosmicRay/IceTop_level3/sim/IC86.2012/SIBYLL2.1/p/12360_v1s/h5files/")

examples/livetime.py

@@ -6,9 +6,10 @@
 
 import numpy as np
 import pylab as plt
-import simweights
 import tables
 
+import simweights
+
 # load hdf5 table
 f = tables.open_file("Level2_IC86.2016_corsika.021682.N100.hdf5", "r")
 wobj = simweights.CorsikaWeighter(f)

examples/nugen_nuflux.py

@@ -7,10 +7,10 @@
 import nuflux
 import pandas as pd
 import pylab as plt
+from numpy.typing import ArrayLike
 
 # start-box1
 import simweights
-from numpy.typing import ArrayLike
 
 # load the hdf5 file and make the weigher
 hdffile = pd.HDFStore("Level2_IC86.2016_NuMu.021217.hdf5", "r")

examples/nugen_plot.py

@@ -6,9 +6,10 @@
 
 import pandas as pd
 import pylab as plt
-import simweights
 from numpy.typing import ArrayLike
 
+import simweights
+
 # load the hdf5 file that we just created using pandas
 hdffile = pd.HDFStore("Level2_IC86.2016_NuMu.021217.hdf5", "r")
 

examples/triggered_corsika_plot.py

@@ -6,6 +6,7 @@
 
 import pandas as pd
 import pylab as plt
+
 import simweights
 
 # load the hdf5 file that we just created using pandas

examples/tutorial_corsika.py

@@ -8,9 +8,10 @@
 
 import matplotlib.pyplot as plt
 import numpy as np
-import simweights
 from icecube import dataio
 
+import simweights
+
 CORSIKA_DATASET_DIR = Path("/data/sim/IceCube/2016/filtered/level2/CORSIKA-in-ice/20789/")
 corsika_filelist = sorted(
     str(f) for f in CORSIKA_DATASET_DIR.glob("0000000-0000999/Level2_IC86.2016_corsika.020789.00000*.i3.zst")

examples/tutorial_nugen.py

@@ -9,9 +9,10 @@
 import matplotlib.pyplot as plt
 import nuflux
 import numpy as np
-import simweights
 from icecube import dataclasses, dataio, simclasses
 
+import simweights
+
 
 def get_most_energetic_muon(mmclist: simclasses.I3MMCTrackList) -> float:
     "Loop through the MMC track list and return the muon with the most energy."

examples/without_tableio.py

@@ -7,9 +7,10 @@
 from pathlib import Path
 
 import pylab as plt
-import simweights
 from icecube import dataio, simclasses
 
+import simweights
+
 FILE_DIR = Path("/data/sim/IceCube/2016/filtered/level2/CORSIKA-in-ice/21889/0000000-0000999")
 filelist = sorted(str(f) for f in FILE_DIR.glob("Level2_IC86.2016_corsika.021889.00000*.i3.zst"))
 

pyproject.toml

@@ -66,8 +66,9 @@ ignore-words-list = 'livetime'
 
 [tool.mypy]
 plugins = "numpy.typing.mypy_plugin"
-show_error_codes = true
+# show_error_codes = true
 warn_unreachable = true
+strict = true
 enable_error_code = ["ignore-without-code", "redundant-expr", "truthy-bool"]
 
 [tool.pylint.format]
@@ -77,6 +78,12 @@ max-line-length = "128"
 disable = "C0114,R0902,R0913"
 
 [tool.ruff]
+src = ["src"]
+line-length = 128
+target-version = "py38"
+namespace-packages = ["examples", "contrib", "docs"]
+
+[tool.ruff.lint]
 select = ["ALL"]
 fixable = ["I"]
 ignore = [
@@ -87,14 +94,11 @@ ignore = [
     "ISC001", # confilcts with ruff formatter
     "PLR0913",# Too many arguments in function definition
     ]
-line-length = 128
-target-version = "py38"
-namespace-packages = ["examples", "contrib", "docs"]
 
-[tool.ruff.pydocstyle]
+[tool.ruff.lint.pydocstyle]
 convention = "google"
 
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "contrib/*" = ["T201"]
 "tests/*" = [
     "D",      # pydocstyle

src/simweights/_generation_surface.py

@@ -5,7 +5,7 @@
 from __future__ import annotations
 
 from copy import deepcopy
-from typing import TYPE_CHECKING, NamedTuple, Sequence
+from typing import TYPE_CHECKING, Any, NamedTuple, Sequence
 
 import numpy as np
 
@@ -26,7 +26,7 @@ class SurfaceTuple(NamedTuple):
 
     pdgid: int | PDGCode
     nevents: float
-    dists: Sequence
+    dists: Sequence[Any]
 
 
 class GenerationSurface:

src/simweights/_utils.py

@@ -4,7 +4,6 @@
 
 from __future__ import annotations
 
-import numbers
 from typing import TYPE_CHECKING, Any, Union
 
 import numpy as np
@@ -15,10 +14,8 @@
 if TYPE_CHECKING:  # pragma: no cover
     from numpy.typing import ArrayLike, NDArray
 
-
-IntNumber = Union[int, np.integer]
 GeneratorType = Union[Generator, RandomState]
-SeedType = Union[GeneratorType, IntNumber, None]
+SeedType = Union[GeneratorType, int, None]
 
 
 class Column:
@@ -167,9 +164,9 @@ def check_random_state(seed: SeedType = None) -> GeneratorType:
         seed : {`numpy.random.Generator`, `numpy.random.RandomState`}
             Random number generator.
     """
-    if seed is None or isinstance(seed, (numbers.Integral, np.integer)):
+    if seed is None or isinstance(seed, (int, np.integer)):
         return np.random.default_rng(seed)
     if isinstance(seed, (RandomState, Generator)):
         return seed
-    mesg = f"{seed!r} cannot be used to seed a numpy.random.Generator instance"
+    mesg = f"{seed!r} cannot be used to seed a numpy.random.Generator instance"  # type: ignore[unreachable]
     raise ValueError(mesg)

tests/test_corsika_datasets.py

@@ -12,6 +12,7 @@
 import pandas as pd
 import tables
 import uproot
+
 from simweights import CorsikaWeighter, GaisserH4a
 from simweights._utils import constcol
 

tests/test_corsika_weighter.py

@@ -7,8 +7,9 @@
 import unittest
 
 import numpy as np
-import simweights
 from scipy.interpolate import interp1d
+
+import simweights
 from simweights import CorsikaWeighter
 
 info_dtype = [

tests/test_fluxes.py

@@ -9,6 +9,7 @@
 from pathlib import Path
 
 import numpy as np
+
 from simweights import _fluxes
 
 E = np.logspace(2, 10, 9)

tests/test_generation_surface.py

@@ -9,6 +9,7 @@
 
 import numpy as np
 from numpy.testing import assert_allclose
+
 from simweights import GenerationSurface, NaturalRateCylinder, PDGCode, PowerLaw, generation_surface
 from simweights._generation_surface import SurfaceTuple  # noqa: F401
 

tests/test_genie_datasets.py

@@ -13,6 +13,7 @@
 import pandas as pd
 import tables
 import uproot
+
 from simweights import GenieWeighter
 from simweights._utils import get_column, get_table
 

tests/test_genie_weighter.py

@@ -7,6 +7,7 @@
 import unittest
 
 import numpy as np
+
 import simweights
 
 info_dtype = [

tests/test_icetop_datasets.py

@@ -13,6 +13,7 @@
 import pandas as pd
 import tables
 import uproot
+
 from simweights import IceTopWeighter
 
 

tests/test_icetop_weighter.py

@@ -7,6 +7,7 @@
 import unittest
 
 import numpy as np
+
 import simweights
 
 info_dtype = [

tests/test_nugen_datasets.py

@@ -13,6 +13,7 @@
 import pandas as pd
 import tables
 import uproot
+
 from simweights import NuGenWeighter
 
 

tests/test_nugen_weighter.py

@@ -8,6 +8,7 @@
 
 import numpy as np
 import pandas as pd
+
 from simweights import CircleInjector, NaturalRateCylinder, NuGenWeighter, PowerLaw
 
 base_keys = [

tests/test_powerlaw.py

@@ -9,6 +9,7 @@
 import numpy as np
 from scipy import stats
 from scipy.integrate import quad
+
 from simweights import PowerLaw
 
 

tests/test_spatial.py

@@ -7,6 +7,7 @@
 import unittest
 
 import numpy as np
+
 from simweights import (
     CircleInjector,
     NaturalRateCylinder,

tests/test_util.py

@@ -11,6 +11,7 @@
 import numpy as np
 import uproot
 from numpy.testing import assert_array_equal
+
 from simweights import Hoerandel
 from simweights._utils import (
     Column,

tests/test_weighter.py

@@ -8,6 +8,7 @@
 from copy import copy
 
 import numpy as np
+
 from simweights import TIG1996, NaturalRateCylinder, PowerLaw, Weighter, generation_surface