data-manipulation-utilities 0.2.8.dev714__tar.gz → 0.2.8.dev725__tar.gz

{data_manipulation_utilities-0.2.8.dev714/src/data_manipulation_utilities.egg-info → data_manipulation_utilities-0.2.8.dev725}/PKG-INFO

@@ -1,7 +1,36 @@
-Metadata-Version: 2.4
-Name: data_manipulation_utilities
-Version: 0.2.8.dev714
+Metadata-Version: 2.3
+Name: data-manipulation-utilities
+Version: 0.2.8.dev725
 Summary: Project storing utilities needed to reduce boilerplate code when analyzing data
+Requires-Python: >=3.10,<3.13
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Provides-Extra: dev
+Provides-Extra: fit
+Provides-Extra: ml
+Requires-Dist: PyYAML
+Requires-Dist: awkward
+Requires-Dist: awkward-pandas
+Requires-Dist: dask[dataframe,distributed]
+Requires-Dist: hist[plot]
+Requires-Dist: joblib ; extra == "ml"
+Requires-Dist: logzero
+Requires-Dist: matplotlib
+Requires-Dist: mplhep
+Requires-Dist: numpy
+Requires-Dist: omegaconf
+Requires-Dist: optuna ; extra == "ml"
+Requires-Dist: pandas
+Requires-Dist: pytest ; extra == "dev"
+Requires-Dist: scikit-learn ; extra == "ml"
+Requires-Dist: scipy
+Requires-Dist: tensorflow
+Requires-Dist: toml
+Requires-Dist: tqdm
+Requires-Dist: uproot
+Requires-Dist: zfit (==0.26.0) ; extra == "fit"
 Description-Content-Type: text/markdown
 
 [TOC]
@@ -1793,3 +1822,4 @@ lxplus:
 ```
 
 and should be placed in `$HOME/.config/dmu/ssh/servers.yaml`
+

data_manipulation_utilities-0.2.8.dev725/pyproject.toml

@@ -0,0 +1,82 @@
+[tool.poetry]
+name           = 'data-manipulation-utilities'
+description    = 'Project storing utilities needed to reduce boilerplate code when analyzing data'
+version        = "0.2.8.dev725"
+readme         = 'README.md'
+package-mode   = true 
+packages       = [
+{include='dmu',      from='src'},
+{include='dmu_data', from='src'}]
+
+[[tool.poetry.include]]
+path = "src/dmu_data/**/*.yaml"
+format = "wheel"
+
+[[tool.poetry.include]]
+path = "src/dmu_data/**/*.toml"
+format = "wheel"
+
+[[tool.poetry.include]]
+path = "src/dmu_data/**/*.json"
+format = "wheel"
+
+[[tool.poetry.include]]
+path = "src/dmu_data/**/*.txt"
+format = "wheel"
+
+[tool.poetry.dependencies]
+python         = '>=3.10, <3.13'
+logzero        = '*'
+PyYAML         = '*'
+scipy          = '*'
+awkward        = '*'
+tqdm           = '*'
+omegaconf      = '*'
+toml           = '*'
+uproot         = '*'
+numpy          = '*'
+matplotlib     = '*'
+mplhep         = '*'
+pandas         = '*'
+tensorflow     = '*'
+awkward-pandas = '*'
+dask           = {version='*',      extras  =['dataframe','distributed']}
+hist           = {version='*',      extras  =['plot']}
+zfit           = {version='0.26.0', optional=true}
+scikit-learn   = {version='*',      optional=true}
+joblib         = {version='*',      optional=true}
+optuna         = {version='*',      optional=true}
+pytest         = {version='*',      optional=true}
+
+[tool.poetry.extras]
+fit  = ['zfit']
+ml   = ['scikit-learn', 'joblib', 'optuna']
+dev  = ['pytest']
+
+[build-system]
+requires      = [
+    'poetry-core>=1.0.0',
+    'poetry-dynamic-versioning>=1.0.0'
+]
+build-backend = 'poetry_dynamic_versioning.backend'
+
+[tool.poetry-dynamic-versioning]
+enable       = false
+vcs          = 'git'
+style        = 'pep440'
+pattern      = 'default-unprefixed'
+format-jinja = """
+{%- if distance == 0 -%}
+{{ base }}
+{%- else -%}
+{{ serialize_pep440(bump_version(base), dev=distance) }}
+{%- endif -%}
+"""
+
+[tool.poetry.scripts]
+transform_text       ='dmu_scripts.text.transform_text:main'
+coned                ='dmu_scripts.ssh.coned:main'
+check_truth          ='dmu_scripts.physics.check_truth:main'
+print_trees          ='dmu_scripts.rfile.print_trees:main'
+compare_root_files   ='dmu_scripts.rfile.compare_root_files:main'
+compare_classifiers  ='dmu_scripts.ml.compare_classifiers:main'

{data_manipulation_utilities-0.2.8.dev714 → data_manipulation_utilities-0.2.8.dev725}/src/dmu/plotting/plotter.py

@@ -5,12 +5,12 @@ Module containing plotter class
 import os
 import json
 import math
-from typing import Union
 
 import numpy
 import matplotlib.pyplot as plt
 
-from ROOT                  import RDataFrame
+from ROOT                  import RDataFrame, RDF
+from omegaconf             import DictConfig
 from dmu.logging.log_store import LogStore
 
 log = LogStore.add_logger('dmu:plotting:Plotter')
@@ -20,16 +20,28 @@ class Plotter:
     Base class of Plotter1D and Plotter2D
     '''
     #-------------------------------------
-    def __init__(self, d_rdf=None, cfg=None):
-        if not isinstance(  cfg, dict):
+    def __init__(
+            self,
+            d_rdf: dict|None            =None,
+            cfg  : dict|DictConfig|None =None):
+        '''
+        Parameters
+        --------------
+        d_rdf: Dictionary where
+            key  : Identifier of dataset
+            value: ROOT dataframe representing dataset
+
+        cfg  : Dictionary or DictConfig instance holding configuration
+        '''
+        if not isinstance(  cfg, (dict,DictConfig)):
             raise ValueError('Config dictionary not passed')
 
         if not isinstance(d_rdf, dict):
             raise ValueError('Dataframe dictionary not passed')
 
         self._d_cfg = cfg
-        self._d_rdf : dict[str, RDataFrame]    = { name : self._preprocess_rdf(rdf) for name, rdf in d_rdf.items()}
-        self._d_wgt : Union[dict[str, Union[numpy.ndarray, None]], None]
+        self._d_rdf : dict[str, RDF.RNode]    = { name : self._preprocess_rdf(rdf) for name, rdf in d_rdf.items()}
+        self._d_wgt : dict[str, numpy.ndarray|None] | None
 
         self._title : str = ''
     #-------------------------------------
@@ -68,9 +80,9 @@ class Plotter:
 
         return minx, maxx
     #-------------------------------------
-    def _preprocess_rdf(self, rdf : RDataFrame) -> RDataFrame:
+    def _preprocess_rdf(self, rdf : RDF.RNode) -> RDF.RNode:
         '''
-        rdf (RDataFrame): ROOT dataframe
+        rdf (RDF.RNode): ROOT dataframe
 
         returns preprocessed dataframe
         '''
@@ -146,7 +158,7 @@ class Plotter:
 
         return rdf
     # --------------------------------------------
-    def _print_weights(self, arr_wgt : Union[numpy.ndarray, None], var : str, sample : str) -> None:
+    def _print_weights(self, arr_wgt : numpy.ndarray|None, var : str, sample : str) -> None:
         if arr_wgt is None:
             log.debug(f'Not using weights for {sample}:{var}')
             return
@@ -171,7 +183,7 @@ class Plotter:
 
         return fig_size
     #-------------------------------------
-    def _get_weights(self, var) -> Union[dict[str, Union[numpy.ndarray, None]], None]:
+    def _get_weights(self, var) -> dict[str, numpy.ndarray|None]| None:
         d_cfg = self._d_cfg['plots'][var]
         if 'weights' not in d_cfg:
             return None
@@ -186,7 +198,7 @@ class Plotter:
 
         return d_weight
     # --------------------------------------------
-    def _read_weights(self, name : str, rdf : RDataFrame) -> numpy.ndarray:
+    def _read_weights(self, name : str, rdf : RDF.RNode) -> numpy.ndarray:
         v_col = rdf.GetColumnNames()
         l_col = [ col.c_str() for col in v_col ]
 

data_manipulation_utilities-0.2.8.dev714/.github/workflows/publish.yaml

@@ -1,87 +0,0 @@
-name: Publish Python 🐍 distribution 📦 to PyPI and TestPyPI
-on: push
-jobs:
-  build:
-    name   : Build distribution
-    runs-on: ubuntu-latest
-    strategy:
-      max-parallel: 5
-    steps:
-    - uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-    - name: Set up micromamba
-      uses: mamba-org/setup-micromamba@v1
-      with:
-        micromamba-version: 'latest'
-        environment-name: myenv
-        create-args: >-
-          python=3.12
-          gxx
-          root
-        channels: conda-forge
-        init-shell: bash
-    - name: Define output directory 
-      run: |
-        ANADIR=$PWD/output
-        echo  "ANADIR=$PWD/output" >> "$GITHUB_ENV"
-    
-        mkdir -p $ANADIR
-    #-----------
-    - name: Cache dependencies installed with poetry 
-      uses: actions/cache@v4
-      with:
-        path: |
-          ~/.cache/pypoetry
-          ~/.cache/pip
-        key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock', '**/pyproject.toml') }}
-        restore-keys: |
-          ${{ runner.os }}-poetry-
-    #-----------
-    - name: Install pypa/build
-      run: >-
-        micromamba run -n myenv  python3 -m
-        pip install
-        poetry
-        build
-        setuptools_scm
-    #-----------
-    - name: Install project dependencies
-      run: |
-        micromamba run -n myenv poetry install --extras 'fit ml dev'
-    - name: Install project itself 
-      run: |
-        micromamba run -n myenv pip install --no-deps .
-    #-----------
-    - name: Test
-      run: |
-        micromamba run -n myenv pytest tests
-    #-----------
-    - name: Build a binary wheel and a source tarball
-      run:  micromamba run -n myenv python3 -m build
-    #-----------
-    - name: Store the distribution packages
-      uses: actions/upload-artifact@v4
-      with:
-        name: python-package-distributions
-        path: dist/
-  #--------------------
-  publish-to-pypi:
-    name: >-
-      Publish Python 🐍 distribution 📦 to PyPI
-    needs:
-    - build
-    runs-on: ubuntu-latest
-    environment:
-      name: pypi
-      url: https://pypi.org/p/data-manipulation-utilities
-    permissions:
-      id-token: write  # IMPORTANT: mandatory for trusted publishing
-    steps:
-    - name: Download all the dists
-      uses: actions/download-artifact@v4
-      with:
-        name: python-package-distributions
-        path: dist/
-    - name: Publish distribution 📦 to PyPI
-      uses: pypa/gh-action-pypi-publish@release/v1

data_manipulation_utilities-0.2.8.dev714/.gitignore

@@ -1,186 +0,0 @@
-# Created by https://www.toptal.com/developers/gitignore/api/python
-# Edit at https://www.toptal.com/developers/gitignore?templates=python
-
-### Python ###
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-
-### Python Patch ###
-# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
-poetry.toml
-
-# ruff
-.ruff_cache/
-
-# LSP config files
-pyrightconfig.json
-
-# End of https://www.toptal.com/developers/gitignore/api/python
-
-*.swp
-*.png
-*.pkl
-*.root
-
-tests/*/*/*.json
-src/dmu_data/tests/*.tex
-
-!doc/images/*.png

data_manipulation_utilities-0.2.8.dev714/.pylintrc

@@ -1,8 +0,0 @@
-[MESSAGES CONTROL]
-disable=logging-fstring-interpolation, too-few-public-methods, line-too-long, no-name-in-module, too-many-locals, wrong-import-order
-
-[TYPECHECK]
-ignored-modules = ROOT, zfit
-
-[MASTER]
-ingnore=build