atlas-ftag-tools 0.2.10__py3-none-any.whl → 0.2.12__py3-none-any.whl

ftag/mock.py

@@ -106,11 +106,11 @@ def get_mock_scores(labels: np.ndarray, is_xbb: bool = False) -> np.ndarray:
     for i in range(n_classes):
         tmp_means = []
         tmp_means = [
-            0 if j != i else mean_scale_list[np.random.randint(0, len(mean_scale_list))]
+            0 if j != i else mean_scale_list[rng.integers(0, len(mean_scale_list))]
             for j in range(n_classes)
         ]
         means.append(tmp_means)
-        scales.append(mean_scale_list[np.random.randint(0, len(mean_scale_list))])
+        scales.append(mean_scale_list[rng.integers(0, len(mean_scale_list))])
 
     # Map the labels to the means
     label_mapping = dict(zip(label_dict.values(), means))

ftag/utils/__init__.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
-from ftag.utils.logging import logger, set_log_level
-from ftag.utils.metrics import (
+from .logging import logger, set_log_level
+from .metrics import (
     calculate_efficiency,
     calculate_efficiency_error,
     calculate_rejection,

ftag/vds.py

@@ -2,6 +2,9 @@ from __future__ import annotations
 
 import argparse
 import glob
+import os
+import re
+import sys
 from pathlib import Path
 
 import h5py
@@ -13,6 +16,8 @@ def parse_args(args):
     )
     parser.add_argument("pattern", type=Path, help="quotes-enclosed glob pattern of files to merge")
     parser.add_argument("output", type=Path, help="path to output virtual file")
+    parser.add_argument("--use_regex", help="if provided pattern is a regex", action="store_true")
+    parser.add_argument("--regex_path", type=str, required="--regex" in sys.argv, default=None)
     return parser.parse_args(args)
 
 
@@ -43,13 +48,36 @@ def get_virtual_layout(fnames: list[str], group: str):
     return layout
 
 
+def glob_re(pattern, regex_path):
+    return list(filter(re.compile(pattern).match, os.listdir(regex_path)))
+
+
+def regex_files_from_dir(reg_matched_fnames, regex_path):
+    parent_dir = regex_path or str(Path.cwd())
+    full_paths = [parent_dir + "/" + fname for fname in reg_matched_fnames]
+    paths_to_glob = [fname + "/*.h5" if Path(fname).is_dir() else fname for fname in full_paths]
+    nested_fnames = [glob.glob(fname) for fname in paths_to_glob]
+    return sum(nested_fnames, [])
+
+
 def create_virtual_file(
-    pattern: Path | str, out_fname: Path | None = None, overwrite: bool = False
+    pattern: Path | str,
+    out_fname: Path | None = None,
+    use_regex: bool = False,
+    regex_path: str | None = None,
+    overwrite: bool = False,
 ):
     # get list of filenames
-    fnames = glob.glob(str(pattern))
+    pattern_str = str(pattern)
+    if use_regex:
+        reg_matched_fnames = glob_re(pattern_str, regex_path)
+        print("reg matched fnames: ", reg_matched_fnames)
+        fnames = regex_files_from_dir(reg_matched_fnames, regex_path)
+    else:
+        fnames = glob.glob(pattern_str)
     if not fnames:
         raise FileNotFoundError(f"No files matched pattern {pattern}")
+    print("Files to merge to vds: ", fnames)
 
     # infer output path if not given
     if out_fname is None:
@@ -94,8 +122,15 @@ def create_virtual_file(
 
 def main(args=None) -> None:
     args = parse_args(args)
-    print(f"Globbing {args.pattern}...")
-    create_virtual_file(args.pattern, args.output, overwrite=True)
+    matching_mode = "Applying regex to" if args.use_regex else "Globbing"
+    print(f"{matching_mode} {args.pattern}...")
+    create_virtual_file(
+        args.pattern,
+        args.output,
+        use_regex=args.use_regex,
+        regex_path=args.regex_path,
+        overwrite=True,
+    )
     with h5py.File(args.output) as f:
         key = next(iter(f.keys()))
         num = len(f[key])

atlas_ftag_tools-0.2.10.dist-info/METADATA

@@ -1,151 +0,0 @@
-Metadata-Version: 2.4
-Name: atlas-ftag-tools
-Version: 0.2.10
-Summary: ATLAS Flavour Tagging Tools
-Author: Sam Van Stroud, Philipp Gadow
-License: MIT
-Project-URL: Homepage, https://github.com/umami-hep/atlas-ftag-tools/
-Requires-Python: <3.12,>=3.8
-Description-Content-Type: text/markdown
-Requires-Dist: h5py>=3.0
-Requires-Dist: numpy>=2.2.3
-Requires-Dist: PyYAML>=5.1
-Requires-Dist: scipy>=1.15.2
-Provides-Extra: dev
-Requires-Dist: ruff==0.6.2; extra == "dev"
-Requires-Dist: mypy==1.11.2; extra == "dev"
-Requires-Dist: pre-commit==3.1.1; extra == "dev"
-Requires-Dist: pytest==7.2.2; extra == "dev"
-Requires-Dist: pytest-cov==4.0.0; extra == "dev"
-Requires-Dist: pytest_notebook==0.10.0; extra == "dev"
-Requires-Dist: ipykernel==6.21.3; extra == "dev"
-
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
-[![PyPI version](https://badge.fury.io/py/atlas-ftag-tools.svg)](https://badge.fury.io/py/atlas-ftag-tools)
-[![codecov](https://codecov.io/gh/umami-hep/atlas-ftag-tools/branch/main/graph/badge.svg?token=MBHLIYYQ7I)](https://codecov.io/gh/umami-hep/atlas-ftag-tools)
-
-# ATLAS FTAG Python Tools
-
-This is a collection of Python tools for working with files produced with the FTAG [ntuple dumper](https://gitlab.cern.ch/atlas-flavor-tagging-tools/training-dataset-dumper/).
-The code is intended to be used a [library](https://iscinumpy.dev/post/app-vs-library/) for other projects.
-Please see the [example notebook](ftag/example.ipynb) for usage.
-
-# Quickstart 
-
-## Installation
-
-If you want to use this package without modification, you can install from [pypi](https://pypi.org/project/atlas-ftag-tools/) using `pip`.
-
-```bash
-pip install atlas-ftag-tools
-```
-
-To additionally install the development dependencies (for formatting and linting) use
-```bash
-pip install atlas-ftag-tools[dev]
-```
-
-## Development
-
-If you plan on making changes to teh code, instead clone the repository and install the package from source in editable mode with
-
-```bash
-python -m pip install -e .
-```
-
-Include development dependencies with
-
-```bash
-python -m pip install -e ".[dev]"
-```
-
-You can set up and run pre-commit hooks with
-
-```bash
-pre-commit install
-pre-commmit run --all-files
-```
-
-To run the tests you can use the `pytest` or `coverage` command, for example
-
-```bash
-coverage run --source ftag -m pytest --show-capture=stdout
-```
-
-Running `coverage report` will display the test coverage.
-
-
-# Usage
-
-Please see the [example notebook](ftag/example.ipynb) for full usage.
-Additional functionality is also documented below.
-
-## Calculate WPs
-
-This package contains a script to calculate tagger working points (WPs).
-The script is `working_points.py` and can be run after installing this package with
-
-```
-wps \
-    --ttbar "path/to/ttbar/*.h5" \
-    --tagger GN2v01 \
-    --fc 0.1
-```
-
-Both the `--tagger` and `--fc` options accept a list if you want to get the WPs for multiple taggers.
-If you are doing c-tagging or xbb-tagging, dedicated fx arguments are available ()you can find them all with `-h`.
-
-If you want to use the `ttbar` WPs get the efficiencies and rejections for the `zprime` sample, you can add `--zprime "path/to/zprime/*.h5"` to the command.
-Note that a default selection of $p_T > 250 ~GeV$ to jets in the `zprime` sample.
-
-If instead of defining the working points for a series of signal efficiencies, you wish to calculate a WP corresponding to a specific background rejection, the `--rejection` option can be given along with the desired background.
-
-By default the working points are printed to the terminal, but you can save the results to a YAML file with the `--outfile` option.
-
-See `wps --help` for more options and information.
-
-## Calculate efficiency at discriminant cut 
-
-The same script can be used to calculate the efficiency and rejection values at a given discriminant cut value.
-The script `working_points.py` can be run after intalling this package as follows
-
-```
-wps \
-    --ttbar "path/to/ttbar/*.h5" \
-    --tagger GN2v01 \
-    --fx 0.1
-    --disc_cuts 1.0 1.5
-```
-The `--tagger`, `--fx`, and `--outfile` follow the same procedure as in the 'Calculate WPs' script as described above.
-
-## H5 Utils
-
-### Create virtual file
-
-This package contains a script to easily merge a set of H5 files.
-A virtual file is a fast and lightweight way to wrap a set of files.
-See the [h5py documentation](https://docs.h5py.org/en/stable/vds.html) for more information on virtual datasets.
-
-The script is `vds.py` and can be run after installing this package with
-
-```
-vds <pattern> <output path>
-```
-
-The `<pattern>` argument should be a quotes enclosed [glob pattern](https://en.wikipedia.org/wiki/Glob_(programming)), for example `"dsid/path/*.h5"`
-
-See `vds --help` for more options and information.
-
-
-### [h5move](ftag/hdf5/h5move.py)
-
-A script to move/rename datasets inside an h5file.
-Useful for correcting discrepancies between group names.
-See [h5move.py](ftag/hdf5/h5move.py) for more info.
-
-
-### [h5split](ftag/hdf5/h5split.py)
-
-A script to split a large h5 file into several smaller files.
-Useful if output files are too large for EOS/grid storage.
-See [h5split.py](ftag/hdf5/h5split.py) for more info.

atlas_ftag_tools-0.2.10.dist-info/RECORD

@@ -1,30 +0,0 @@
-ftag/__init__.py,sha256=v9emuK48Hhd-_TCiirfCNMsZSzk52frz1zEOgk9PViQ,787
-ftag/cli_utils.py,sha256=w3TtQmUHSyAKChS3ewvOtcSDAUJAZGIIomaNi8f446U,298
-ftag/cuts.py,sha256=9_ooLZHaO3SnIQBNxwbaPZn-qptGdKnB27FdKQGTiTY,2933
-ftag/flavours.py,sha256=ShH4M2UjQZpZ_NlCctTm2q1tJbzYxjmGteioQ2GcqEU,114
-ftag/flavours.yaml,sha256=5Lo9KWe-2KzmGMbc7o_X9gzwUyTl0Q5uVHYExduZ6T4,9502
-ftag/fraction_optimization.py,sha256=IlMEJe5fD0soX40f-LO4dYAYld2gMqgZRuBLctoPn9A,5566
-ftag/git_check.py,sha256=Y-XqM80CVXZ5ZKrDdZcYOJt3X64uU6W3OP6Z0D7AZU0,1663
-ftag/labeller.py,sha256=IXUgU9UBir39PxVWRKs5r5fqI66Tv0x7nJD3-RYpbrg,2780
-ftag/labels.py,sha256=2nmcmrZD8mWQPxJsGiOgcLDhSVgWfS_cEzqsBV-Qy8o,4198
-ftag/mock.py,sha256=P2D7nNKAz2jRBbmfpHTDj9sBVU9r7HGd0rpWZOJYZ90,5980
-ftag/region.py,sha256=ANv0dGI2W6NJqD9fp7EfqAUReH4FOjc1gwl_Qn8llcM,360
-ftag/sample.py,sha256=3N0FrRcu9l1sX8ohuGOHuMYGD0See6gMO4--7NzR2tE,2538
-ftag/track_selector.py,sha256=fJNk_kIBQriBqV4CPT_3ReJbOUnavDDzO-u3EQlRuyk,2654
-ftag/transform.py,sha256=uEGGJSnqoKOzLYQv650XdK_kDNw4Aw-5dc60z9Dp_y0,3963
-ftag/vds.py,sha256=nRViQZQIORB95nC7NZsW3KsSoGkLzEdOsuCViH5h8-U,3296
-ftag/working_points.py,sha256=RJws2jPMEDQDspCbXUZBifS1CCBmlMJ5ax0eMyDzCRA,15949
-ftag/hdf5/__init__.py,sha256=LFDNxVOCp58SvLHwQhdT68Q-KBMS_i6jBrbXoRpHzbM,354
-ftag/hdf5/h5move.py,sha256=oYpRu0IDCIJIQ2ML52HBAdoyDxmKkHTeM9JdbPEgKfI,947
-ftag/hdf5/h5reader.py,sha256=i31pDAqmOSaxdeRhc4iSBlld8xJ0pmp4rNd7CugNzw0,13706
-ftag/hdf5/h5split.py,sha256=4Wy6Xc3J58MdD9aBaSZHf5ZcVFnJSkWsm42R5Pgo-R4,2448
-ftag/hdf5/h5utils.py,sha256=-4zKTMtNCrDZr_9Ww7uzfsB7M7muBKpmm_1IkKJnHOI,3222
-ftag/hdf5/h5writer.py,sha256=9FkClV__UbBqmFsq_h2jwiZnbWVm8QFRL_4mDZZBbTs,5316
-ftag/utils/__init__.py,sha256=C0PgaA6Nk5WVpFqKhBhrHgj2mwsKJbSxoO6Cl67RsaI,544
-ftag/utils/logging.py,sha256=54NaQiC9Bh4vSznSqzoPfR-7tj1PXfmoH7yKgv_ZHZk,3192
-ftag/utils/metrics.py,sha256=zQI4nPeRDSyzqKpdOPmu0GU560xSWoW1wgL13rrja-I,12664
-atlas_ftag_tools-0.2.10.dist-info/METADATA,sha256=VUhrtQML6_bUKlmZNFlUXxTTt5YBzNYupTrdlaF5IAw,5190
-atlas_ftag_tools-0.2.10.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-atlas_ftag_tools-0.2.10.dist-info/entry_points.txt,sha256=b46bVP_O8Mg6aSdPmyjGgVkaXSdyXZMeKAsofh2IDeA,133
-atlas_ftag_tools-0.2.10.dist-info/top_level.txt,sha256=qiYQuKcAvMim-31FwkT3MTQu7WQm0s58tPAia5KKWqs,5
-atlas_ftag_tools-0.2.10.dist-info/RECORD,,