umami-preprocessing 0.3.0__tar.gz → 0.3.1__tar.gz

{umami_preprocessing-0.3.0/umami_preprocessing.egg-info → umami_preprocessing-0.3.1}/PKG-INFO

@@ -1,36 +1,34 @@
 Metadata-Version: 2.4
 Name: umami-preprocessing
-Version: 0.3.0
+Version: 0.3.1
 Summary: ATLAS Flavour Tagging Preprocessing - Umami PreProcessing (UPP)
 Author: Alexander Froch
-License: MIT
+License-Expression: Apache-2.0
 Project-URL: Homepage, https://github.com/umami-hep/umami-preprocessing
 Project-URL: Issue Tracker, https://github.com/umami-hep/umami-preprocessing/issues
-Requires-Python: <3.12,>=3.10
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Physics
+Requires-Python: <3.15,>=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: atlas-ftag-tools==0.3.1
+Requires-Dist: atlas-ftag-tools==0.3.3
 Requires-Dist: dotmap>=1.3.30
 Requires-Dist: numpy>=2.2.6
-Requires-Dist: puma-hep==0.5.1
+Requires-Dist: puma-hep==0.5.3
 Requires-Dist: pyyaml-include==1.3
 Requires-Dist: PyYAML>=6.0.2
 Requires-Dist: rich>=14.1.0
 Requires-Dist: scipy>=1.15.3
-Provides-Extra: dev
-Requires-Dist: coverage>=7.10.6; extra == "dev"
-Requires-Dist: ipykernel>=6.30.1; extra == "dev"
-Requires-Dist: mypy>=1.18.1; extra == "dev"
-Requires-Dist: pre-commit>=4.3.0; extra == "dev"
-Requires-Dist: pydoclint>=0.7.3; extra == "dev"
-Requires-Dist: pytest_notebook>=0.10.0; extra == "dev"
-Requires-Dist: pytest-cov>=7.0.0; extra == "dev"
-Requires-Dist: pytest-randomly>=4.0.1; extra == "dev"
-Requires-Dist: pytest>=8.4.2; extra == "dev"
-Requires-Dist: ruff>=0.13.0; extra == "dev"
 Dynamic: license-file
 
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 [![codecov](https://codecov.io/gh/umami-hep/umami-preprocessing/graph/badge.svg?token=K8MJI20UZO)](https://codecov.io/gh/umami-hep/umami-preprocessing)
 [![PyPI version](https://badge.fury.io/py/umami-preprocessing.svg)](https://badge.fury.io/py/umami-preprocessing)
 [![docs](https://img.shields.io/badge/info-documentation-informational)](https://umami-hep.github.io/umami-preprocessing//)

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/README.md

@@ -1,4 +1,5 @@
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 [![codecov](https://codecov.io/gh/umami-hep/umami-preprocessing/graph/badge.svg?token=K8MJI20UZO)](https://codecov.io/gh/umami-hep/umami-preprocessing)
 [![PyPI version](https://badge.fury.io/py/umami-preprocessing.svg)](https://badge.fury.io/py/umami-preprocessing)
 [![docs](https://img.shields.io/badge/info-documentation-informational)](https://umami-hep.github.io/umami-preprocessing//)

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/pyproject.toml

@@ -3,29 +3,39 @@ name = "umami-preprocessing"
 description = "ATLAS Flavour Tagging Preprocessing - Umami PreProcessing (UPP)"
 authors = [{name="Alexander Froch"}]
 dynamic = ["version"]
-license = {text = "MIT"}
+license = "Apache-2.0"
+license-files = ["LICENSE"]
 readme = "README.md"
-requires-python = ">=3.10,<3.12"
+requires-python = ">=3.11,<3.15"
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: Science/Research",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3.14",
+  "Topic :: Scientific/Engineering :: Physics",
+]
 
 dependencies = [
-  "atlas-ftag-tools==0.3.1",
+  "atlas-ftag-tools==0.3.3",
   "dotmap>=1.3.30",
   "numpy>=2.2.6",
-  "puma-hep==0.5.1",
+  "puma-hep==0.5.3",
   "pyyaml-include==1.3",
   "PyYAML>=6.0.2",
   "rich>=14.1.0",
   "scipy>=1.15.3",
 ]
 
-[project.optional-dependencies]
+[dependency-groups]
 dev = [
   "coverage>=7.10.6",
   "ipykernel>=6.30.1",
   "mypy>=1.18.1",
   "pre-commit>=4.3.0",
   "pydoclint>=0.7.3",
-  "pytest_notebook>=0.10.0",
   "pytest-cov>=7.0.0",
   "pytest-randomly>=4.0.1",
   "pytest>=8.4.2",
@@ -48,10 +58,11 @@ include-package-data = true
 version = {attr = "upp.__version__"}
 
 [build-system]
-requires = ["setuptools>=62"]
+requires = ["setuptools>=77"]
 build-backend = "setuptools.build_meta"
 
 [tool.ruff]
+target-version = "py311"
 lint.select = ["I", "E", "W", "F", "B", "UP", "ARG", "SIM", "TID", "RUF", "D2", "D3", "D4"]
 lint.ignore = ["RUF005"]
 line-length = 100

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1/umami_preprocessing.egg-info}/PKG-INFO

@@ -1,36 +1,34 @@
 Metadata-Version: 2.4
 Name: umami-preprocessing
-Version: 0.3.0
+Version: 0.3.1
 Summary: ATLAS Flavour Tagging Preprocessing - Umami PreProcessing (UPP)
 Author: Alexander Froch
-License: MIT
+License-Expression: Apache-2.0
 Project-URL: Homepage, https://github.com/umami-hep/umami-preprocessing
 Project-URL: Issue Tracker, https://github.com/umami-hep/umami-preprocessing/issues
-Requires-Python: <3.12,>=3.10
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Physics
+Requires-Python: <3.15,>=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: atlas-ftag-tools==0.3.1
+Requires-Dist: atlas-ftag-tools==0.3.3
 Requires-Dist: dotmap>=1.3.30
 Requires-Dist: numpy>=2.2.6
-Requires-Dist: puma-hep==0.5.1
+Requires-Dist: puma-hep==0.5.3
 Requires-Dist: pyyaml-include==1.3
 Requires-Dist: PyYAML>=6.0.2
 Requires-Dist: rich>=14.1.0
 Requires-Dist: scipy>=1.15.3
-Provides-Extra: dev
-Requires-Dist: coverage>=7.10.6; extra == "dev"
-Requires-Dist: ipykernel>=6.30.1; extra == "dev"
-Requires-Dist: mypy>=1.18.1; extra == "dev"
-Requires-Dist: pre-commit>=4.3.0; extra == "dev"
-Requires-Dist: pydoclint>=0.7.3; extra == "dev"
-Requires-Dist: pytest_notebook>=0.10.0; extra == "dev"
-Requires-Dist: pytest-cov>=7.0.0; extra == "dev"
-Requires-Dist: pytest-randomly>=4.0.1; extra == "dev"
-Requires-Dist: pytest>=8.4.2; extra == "dev"
-Requires-Dist: ruff>=0.13.0; extra == "dev"
 Dynamic: license-file
 
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 [![codecov](https://codecov.io/gh/umami-hep/umami-preprocessing/graph/badge.svg?token=K8MJI20UZO)](https://codecov.io/gh/umami-hep/umami-preprocessing)
 [![PyPI version](https://badge.fury.io/py/umami-preprocessing.svg)](https://badge.fury.io/py/umami-preprocessing)
 [![docs](https://img.shields.io/badge/info-documentation-informational)](https://umami-hep.github.io/umami-preprocessing//)

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/umami_preprocessing.egg-info/SOURCES.txt

@@ -12,6 +12,7 @@ upp/__init__.py
 upp/main.py
 upp/classes/__init__.py
 upp/classes/components.py
+upp/classes/plotting_config.py
 upp/classes/preprocessing_config.py
 upp/classes/region.py
 upp/classes/resampling_config.py

umami_preprocessing-0.3.1/umami_preprocessing.egg-info/requires.txt

@@ -0,0 +1,8 @@
+atlas-ftag-tools==0.3.3
+dotmap>=1.3.30
+numpy>=2.2.6
+puma-hep==0.5.3
+pyyaml-include==1.3
+PyYAML>=6.0.2
+rich>=14.1.0
+scipy>=1.15.3

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/upp/__init__.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-__version__ = "v0.3.0"
+__version__ = "v0.3.1"
 
 from . import classes, stages, utils
 from .main import run_pp

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/upp/classes/__init__.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 from upp.classes.components import Component, Components
+from upp.classes.plotting_config import PlottingConfig
 from upp.classes.preprocessing_config import PreprocessingConfig
 from upp.classes.region import Region
 from upp.classes.resampling_config import ResamplingConfig
@@ -11,6 +12,7 @@ from upp.classes.variable_config import VariableConfig
 __all__ = [
     "Component",
     "Components",
+    "PlottingConfig",
     "PreprocessingConfig",
     "Region",
     "ResamplingConfig",

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/upp/classes/components.py

@@ -86,6 +86,9 @@ class Component:
         if fname is None:
             fname = self.sample.path
 
+        if "vds_dir" not in kwargs and self.sample.vds_dir is not None:
+            kwargs["vds_dir"] = self.sample.vds_dir
+
         self.reader = H5Reader(
             fname=fname,
             batch_size=batch_size,
@@ -106,7 +109,8 @@ class Component:
             Name of the group in which the jets are stored, by default "jets"
         """
         dtypes = self.reader.dtypes(variables.combined())
-        shapes = self.reader.shapes(self.num_jets, variables.keys())
+        # num_jets == -1 ("write all") -> 0 leading dim so the writer grows dynamically
+        shapes = self.reader.shapes(max(self.num_jets, 0), variables.keys())
         self.writer = H5Writer(self.out_path, dtypes, shapes, jets_name=jets_name)
         log.debug(f"Setup component writer at: {self.out_path}")
 
@@ -209,6 +213,10 @@ class Component:
         ValueError
             If more jets are requsted than available
         """
+        # num_req < 0 means "use all available jets" - nothing to check
+        if num_req < 0:
+            return
+
         # Check if num_jets jets are aviailable after the cuts and sampling fraction
         num_est = (
             None if self.num_jets_estimate_available <= 0 else self.num_jets_estimate_available
@@ -313,9 +321,9 @@ class Components:
         component_list = []
         for component in config.config["components"]:
             # Ensure equal_jets flag is correctly set
-            assert (
-                "equal_jets" not in component
-            ), "equal_jets flag should be set in the sample config"
+            assert "equal_jets" not in component, (
+                "equal_jets flag should be set in the sample config"
+            )
 
             # Get the region cuts
             region_cuts = (
@@ -337,6 +345,7 @@ class Components:
                 ntuple_dir=config.ntuple_dir,
                 name=component["sample"]["name"],
                 skip_checks=config.skip_checks,
+                vds_dir=config.vds_dir,
             )
 
             # Create the Component instances for the different flavours
@@ -360,8 +369,8 @@ class Components:
                 )
         components = cls(component_list)
 
-        # Check the flavour ratios
-        if config.sampl_cfg and config.sampl_cfg.method is not None:
+        # Check the flavour ratios (not meaningful when resampling is skipped)
+        if not config.skip_resampling:
             components.check_flavour_ratios()
 
         return components

umami_preprocessing-0.3.1/upp/classes/plotting_config.py

@@ -0,0 +1,121 @@
+from __future__ import annotations
+
+from dataclasses import dataclass, field
+
+
+def _default_variable_labels() -> dict[str, str]:
+    return {
+        "pt": "Jet $p_\\mathrm{T}$ [GeV]",
+        "eta": "Jet $|\\eta|$",
+        "mass": "Jet Mass [GeV]",
+    }
+
+
+def _default_sample_labels() -> dict[str, str]:
+    return {
+        "ttbar": "$t\\bar{t}$",
+        "zprime": "$Z'$",
+    }
+
+
+@dataclass
+class PlottingConfig:
+    r"""
+    Options for the preprocessing resampling distribution plots.
+
+    These options are specified in the config file under the `plotting:` key.
+    Any omitted option uses the default defined by this class.
+
+    Attributes
+    ----------
+    num_jets_plotting : int | None, optional
+        Number of jets loaded for plotting. If not set, use the global
+        `num_jets_estimate_plotting` value. By default None.
+    variable_labels : dict[str, str], optional
+        Display labels for plotted variables. Keys are matched case-insensitively
+        against variable names, with the longest matching key taking precedence.
+        User-provided labels are merged with the default pT, eta, and mass labels.
+    sample_labels : dict[str, str], optional
+        Display labels for input samples. User-provided labels are merged with the
+        default ttbar and zprime labels.
+    ylabel : str, optional
+        Label for the y-axis. The `{jets_name}` placeholder is replaced with the
+        configured jet dataset name. By default "Normalised Number of {jets_name}".
+    atlas_first_tag : str, optional
+        First ATLAS plot label. By default "Simulation Internal".
+    atlas_second_tag : str, optional
+        Second ATLAS plot label. By default "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$".
+    show_num_jets : bool, optional
+        Decide, if the number of jets is shown in the ATLAS second tag
+    output_formats : list[str], optional
+        File formats in which each plot is saved. By default `["pdf", "png"]`.
+    linestyles : list[str], optional
+        Linestyles used to distinguish input samples. By default
+        `["-", "--", "-.", ":"]`.
+    bins : int, optional
+        Number of histogram bins. By default 50.
+    norm : bool, optional
+        Normalise each histogram before plotting. By default True.
+    underoverflow : bool, optional
+        Include underflow and overflow values in the edge bins. By default True.
+    y_scale : float, optional
+        Scale factor applied to the automatically determined y-axis range.
+        By default 1.5.
+    figsize : list[float], optional
+        Figure width and height. By default `[6, 4]`.
+    logy : bool, optional
+        Use a logarithmic y-axis. By default True.
+    legend_location : str, optional
+        Location of the flavour legend. By default "upper right".
+    linestyle_legend_location : str, optional
+        Location of the sample-linestyle legend. By default "upper center".
+    linestyle_legend_anchor : list[float], optional
+        Anchor position of the sample-linestyle legend. By default `[0.55, 1]`.
+    output_directory : str, optional
+        Plot directory relative to the preprocessing output directory.
+        By default "plots".
+    """
+
+    num_jets_plotting: int | None = None
+    variable_labels: dict[str, str] = field(default_factory=_default_variable_labels)
+    sample_labels: dict[str, str] = field(default_factory=_default_sample_labels)
+    ylabel: str = "Normalised Number of {jets_name}"
+    atlas_first_tag: str = "Simulation Internal"
+    atlas_second_tag: str = "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$"
+    show_num_jets: bool = True
+    output_formats: list[str] = field(default_factory=lambda: ["pdf", "png"])
+    linestyles: list[str] = field(default_factory=lambda: ["-", "--", "-.", ":"])
+    bins: int = 50
+    norm: bool = True
+    underoverflow: bool = True
+    y_scale: float = 1.5
+    figsize: list[float] = field(default_factory=lambda: [6, 4])
+    logy: bool = True
+    legend_location: str = "upper right"
+    linestyle_legend_location: str = "upper center"
+    linestyle_legend_anchor: list[float] = field(default_factory=lambda: [0.55, 1])
+    output_directory: str = "plots"
+
+    def __post_init__(self) -> None:
+        self.variable_labels = {**_default_variable_labels(), **self.variable_labels}
+        self.sample_labels = {**_default_sample_labels(), **self.sample_labels}
+        if self.num_jets_plotting is not None and self.num_jets_plotting <= 0:
+            raise ValueError("plotting.num_jets_plotting must be a positive integer or None")
+        if not self.output_formats:
+            raise ValueError("plotting.output_formats must contain at least one format")
+        if not self.linestyles:
+            raise ValueError("plotting.linestyles must contain at least one linestyle")
+
+    def variable_label(self, variable: str) -> str:
+        """Return the configured display label for a variable."""
+        variable_lower = variable.lower()
+        for name, label in sorted(
+            self.variable_labels.items(), key=lambda item: len(item[0]), reverse=True
+        ):
+            if name.lower() in variable_lower:
+                return label
+        return variable
+
+    def sample_label(self, sample: str) -> str:
+        """Return the configured display label for a sample."""
+        return self.sample_labels.get(sample, sample)

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/upp/classes/preprocessing_config.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import dataclasses
 import functools
 import logging as log
+import subprocess
 from copy import copy
 from dataclasses import dataclass
 from pathlib import Path
@@ -19,6 +20,7 @@ from yamlinclude import YamlIncludeConstructor
 
 from upp import __version__
 from upp.classes.components import Components
+from upp.classes.plotting_config import PlottingConfig
 from upp.classes.resampling_config import ResamplingConfig
 from upp.classes.reweight_config import ReweightConfig
 from upp.classes.variable_config import VariableConfig
@@ -119,6 +121,9 @@ class PreprocessingConfig:
         Skip checks for the input files. This is used for grid submission
     skip_config_copy : bool, optional
         Decide, if the config copying is skipped or not. By default False
+    vds_dir : Path | None, optional
+        Directory name for creation of virtual datasets. By default None
+        If none is given, virtual datasets is created next to input ntuples
     """
 
     config_path: Path
@@ -142,6 +147,7 @@ class PreprocessingConfig:
     num_jets_per_output_file: int | None = None
     skip_checks: bool = False
     skip_config_copy: bool = False
+    vds_dir: Path | None = None
 
     def __post_init__(self):
         # postprocess paths
@@ -158,6 +164,9 @@ class PreprocessingConfig:
         for field in dataclasses.fields(self):
             if field.type == "Path" and field.name != "out_fname" and field.name != "base_dir":
                 setattr(self, field.name, self.get_path(Path(getattr(self, field.name))))
+        # vds_dir is optional (Path | None), so the loop above skips it; resolve it here
+        if self.vds_dir is not None:
+            self.vds_dir = self.get_path(Path(self.vds_dir))
         if not self.ntuple_dir.exists() and not self.skip_checks:
             raise FileNotFoundError(f"Path {self.ntuple_dir} does not exist")
         self.components_dir = self.components_dir / self.split
@@ -202,7 +211,7 @@ class PreprocessingConfig:
         self.variables = VariableConfig(
             self.config["variables"], self.jets_name, self.is_test, selectors
         )
-        if self.sampl_cfg is not None:
+        if self.sampl_cfg is not None and self.sampl_cfg.variables:
             self.variables = self.variables.add_jet_vars(
                 list(self.config["resampling"]["variables"].keys()), "labels"
             )
@@ -217,8 +226,19 @@ class PreprocessingConfig:
             if "reweighting" in self.config
             else None
         )
+        self.plotting = PlottingConfig(**self.config.get("plotting", {}))
+        if self.plotting.num_jets_plotting is None:
+            self.plotting.num_jets_plotting = self.num_jets_estimate_plotting
+
         # reproducibility
-        self.git_hash = get_git_hash(Path(__file__).parent)
+        try:
+            self.git_hash = get_git_hash(Path(__file__).parent)
+        except (OSError, subprocess.CalledProcessError):
+            log.warning(
+                "Could not determine the git hash (is git installed and on PATH?); "
+                "using the UPP version for reproducibility metadata instead."
+            )
+            self.git_hash = None
         if self.git_hash is None:
             self.git_hash = __version__
         self.config["upp_hash"] = self.git_hash
@@ -255,12 +275,36 @@ class PreprocessingConfig:
     def is_test(self):
         return self.split == "test"
 
+    @property
+    def skip_resampling(self) -> bool:
+        """Return whether resampling is disabled (no block, or method none).
+
+        Returns
+        -------
+        bool
+            ``True`` if resampling should be skipped.
+        """
+        return self.sampl_cfg is None or self.sampl_cfg.method in (None, "none")
+
+    @property
+    def resampling_method(self) -> str:
+        """Resampling method recorded in the output metadata ("none" if skipped).
+
+        Returns
+        -------
+        str
+            The resampling method (e.g. ``"pdf"``/``"countup"``), or ``"none"``.
+        """
+        if self.skip_resampling:
+            return "none"
+        return self.sampl_cfg.method
+
     @functools.cached_property
     def global_cuts(self):
         cuts_list = self.config["global_cuts"].get("common", [])
         cuts_list += self.config["global_cuts"][self.split]
         if not self.is_test and self.config.get("resampling", None) is not None:
-            for resampling_var, cfg in self.config["resampling"]["variables"].items():
+            for resampling_var, cfg in self.config["resampling"].get("variables", {}).items():
                 cuts_list.append([resampling_var, ">", cfg["bins"][0][0]])
                 cuts_list.append([resampling_var, "<", cfg["bins"][-1][1]])
         return Cuts.from_list(cuts_list)

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/upp/classes/resampling_config.py

@@ -1,14 +1,15 @@
 from __future__ import annotations
 
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 
 import numpy as np
 
 
 @dataclass
 class ResamplingConfig:
-    variables: dict
-    target: str
+    # variables/target are only needed for pdf/countup resampling; optional when skipping
+    variables: dict = field(default_factory=dict)
+    target: str | None = None
     sampling_fraction: float = 1.0
     method: str | None = None
     upscale_pdf: int | None = None

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/upp/main.py

@@ -1,12 +1,14 @@
 """
-Preprocessing pipeline for jet taggging.
+Preprocessing pipeline for jet tagging.
 
 By default all stages for the training split are run.
 To run with only specific stages enabled, include the flag for the required stages.
 To run without certain stages, include the corresponding negative flag.
 
-Note that all stages are required to run the pipeline. If you want to disable resampling,
-you need to set method: none in your config file.
+To disable resampling, omit the `resampling` block or set `method: none`. The jets passing
+the cuts are then written directly, capped at each component's `num_jets` (use `num_jets: -1`
+to keep all of them). The `--no-resample` flag only skips the resampling *stage* (e.g. to
+re-run later stages); it does not disable resampling.
 """
 
 from __future__ import annotations
@@ -129,7 +131,11 @@ def parse_args(args: Any) -> argparse.Namespace:
         "--reweight", "--rw", action="store_true", default=False, help="Run the reweighting stage"
     )
     parser.add_argument(
-        "--rw-merge", "--rwm", action="store_true", default=False, help="Run the reweighting stage"
+        "--rw-merge",
+        "--rwm",
+        action="store_true",
+        default=False,
+        help="Run the reweighting merge stage",
     )
     parser.add_argument(
         "--rw-merge-idx",
@@ -137,7 +143,7 @@ def parse_args(args: Any) -> argparse.Namespace:
         type=str,
         default=None,
         help=(
-            "Commar seperated pair of indices representing the range of output "
+            "Comma-separated pair of indices representing the range of output "
             "files to create, e.g '0,10' will create files 0 to 9"
         ),
     )
@@ -149,7 +155,7 @@ def parse_args(args: Any) -> argparse.Namespace:
     parser.add_argument(
         "--skip-sample-check",
         action="store_true",
-        help="Skip the inital input sample check",
+        help="Skip the initial input sample check",
     )
     parser.add_argument(
         "--grid", action="store_true", help="Use when running the split stage on the grid. "
@@ -231,7 +237,7 @@ def run_pp(args: argparse.Namespace) -> None:
                 verbose=True,
             )
 
-        if args.split == "train":
+        if args.split == "train" and not config.skip_resampling:
             create_histograms(
                 config=config,
                 component_to_run=args.component,

{umami_preprocessing-0.3.0 → umami_preprocessing-0.3.1}/upp/stages/hist.py

@@ -41,8 +41,9 @@ def bin_jets(array: dict, bins: list) -> tuple[np.ndarray, np.ndarray]:
             bin in which this observation falls.  The representation depends on the
             `expand_binnumbers` argument.  See `Notes` for details.
     """
+    sample = s2u(array).astype(np.float64, copy=False)
     hist, _, out_bins = binned_statistic_dd(
-        sample=s2u(array),
+        sample=sample,
         values=None,
         statistic="count",
         bins=bins,
@@ -145,6 +146,9 @@ def create_histograms(
     """
     # Setup the logger and load the variables used for resampling
     setup_logger()
+    if config.skip_resampling:
+        log.info("Resampling is disabled - skipping histogram/PDF creation.")
+        return
     sampl_vars = config.sampl_cfg.vars
 
     title = " Writing PDFs "