Update pre-commit, store tagger scores as structured array (#177)

* update pre-commit

* run ruff

* update tagger to use structured array

* update tagger

* bug fixes

* update changelog

* revert line length

* Update puma/histogram.py

Co-authored-by: Dmitrii Kobylianskii <[email protected]>

---------

Co-authored-by: Dmitrii Kobylianskii <[email protected]>

.github/workflows/github_update_todo.py

@@ -13,7 +13,6 @@ def pylint_fixmes():
     list
         pylint_msgs with Todos
     """
-
     (pylint_stdout, _) = lint.py_run("puma/ --disable=all --enable=fixme ", True)
     pylint_stdout = pylint_stdout.read()
     pylint_files, pylint_msgs = [], []

.pre-commit-config.yaml

@@ -1,35 +1,24 @@
 repos:
-  - repo: https://github.com/pycqa/isort
-    rev: 5.12.0
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: "v0.0.254"
     hooks:
-      - id: isort
-        args: ["--profile", "black"]
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
 
   - repo: https://github.com/psf/black
-    rev: 23.1.0
+    rev: "23.1.0"
     hooks:
       - id: black
-        args: ["--preview"]
 
-  - repo: https://github.com/pycqa/flake8
-    rev: 5.0.4
-    hooks:
-      - id: flake8
-
-  - repo: https://github.com/terrencepreilly/darglint
-    rev: v1.8.1
-    hooks:
-      - id: darglint
+  #- repo: https://github.com/pre-commit/mirrors-mypy
+  #  rev: "v1.1.1"
+  #  hooks:
+  #    - id: mypy
+  #      args: [--ignore-missing-imports]
+  #      additional_dependencies: ["types-requests", "types-PyYAML"]
 
-  - repo: local
-    hooks:
-      - id: pylint
-        name: pylint
-        entry: pylint
-        language: system
-        types: [python]
-        args: [
-            "-rn", # Only display messages
-            "-sn", # Don't display the score
-            "--ignore-paths=.github/*,docs/*",
-          ]
+  #- repo: https://github.com/adrienverge/yamllint.git
+  #  rev: v1.17.0
+  #  hooks:
+  #    - id: yamllint
+  #      args: ["-d", "{extends: relaxed, rules: {line-length: disable}}"]

changelog.md

@@ -2,6 +2,7 @@
 
 ### [Latest]
 
+- Update pre-commit (using ruff) and store tagger scores as structured array [!177](https://github.com/umami-hep/puma/pull/177)
 - Remove dev image [!176](https://github.com/umami-hep/puma/pull/176)
 - Fix bug in ratio axis limits [!175](https://github.com/umami-hep/puma/pull/175)
 - Add `VarVsVar` plot [!172](https://github.com/umami-hep/puma/pull/172)

docs/source/conf.py

@@ -74,10 +74,7 @@
 commits = requests.get("https://api.github.com/repos/umami-hep/puma/commits/main")
 latest_commit_hash = commits.json()["sha"]
 
-if current_hash == latest_commit_hash:
-    version_match = "latest"
-else:
-    version_match = f"v{release}"
+version_match = "latest" if current_hash == latest_commit_hash else f"v{release}"
 
 html_theme = "pydata_sphinx_theme"
 html_theme_options = {

docs/source/dev_guidelines/development_guidelines.md

@@ -16,18 +16,15 @@ automatic formatting when you save a file.
 ## Linters
 
 In addition to the pure style-component of checking the code with `black`, we use
-`flake8` and `pylint` to check the code for bad coding practices. Make sure to run them before
-you commit your code.
-
-In addition to that, we require docstrings in the `numpy`-style, which are checked in
-the pipeline by `darglint`.
+`ruff` to check the code for bad coding practices and docstrings. Make sure to run 
+`ruff` before you commit your code.
 
 ## Pre-commit hook
 
-To check staged files for style and `flake8` conformity, you can use the `pre-commit`
-hook, which then won't allow you to commit your staged changes if `isort`, `black` or
-`flake8` fails.
-You might have to set it up by executing the following in the root of the repo:
+To check staged files for style conformity, you can use the `pre-commit`
+hook, which then won't allow you to commit your staged changes if `ruff` 
+or `black fails.
+You can set it up by executing the following in the root of the repo:
 
 ```bash
 pre-commit install

docs/sphinx_build_multiversion.py

@@ -50,7 +50,7 @@ def build_docs_version(version):
 
 def main():
     """main function that is executed when the script is called."""
-    with open("docs/source/_static/switcher.json", "r") as f:  # pylint: disable=W1514
+    with open("docs/source/_static/switcher.json") as f:
         version_switcher = json.load(f)
 
     # get currently active branch

examples/plot_fraction_scan.py

@@ -1,4 +1,4 @@
-"""Example of fraction scan plot"""
+"""Example of fraction scan plot."""
 
 import numpy as np
 
@@ -24,7 +24,7 @@
 
 
 def calc_effs(fc_value: float):
-    """Tagger efficiency for fixed working point
+    """Tagger efficiency for fixed working point.
 
     Parameters
     ----------

examples/plot_histogram_underoverflow.py

@@ -1,4 +1,4 @@
-"""Example script that demonstrates under/overflow bins"""
+"""Example script that demonstrates under/overflow bins."""
 import numpy as np
 
 from puma import Histogram, HistogramPlot

examples/plot_pie.py

@@ -1,4 +1,4 @@
-"""Example plotting script for the puma.PiePlot class"""
+"""Example plotting script for the puma.PiePlot class."""
 from ftag import Flavours
 
 from puma.pie import PiePlot

examples/plot_pt_vs_eff.py

@@ -7,7 +7,7 @@
 
 # define a small function to calculate discriminant
 def disc_fct(arr: np.ndarray, f_c: float = 0.018) -> np.ndarray:
-    """Tagger discriminant
+    """Tagger discriminant.
 
     Parameters
     ----------

examples/plot_rocs.py

@@ -13,7 +13,7 @@
 
 # define a small function to calculate discriminant
 def disc_fct(arr: np.ndarray, f_c: float = 0.018) -> np.ndarray:
-    """Tagger discriminant
+    """Tagger discriminant.
 
     Parameters
     ----------

examples/plot_weighted_histograms.py

@@ -1,4 +1,4 @@
-"""Example script for plotting weighted histograms"""
+"""Example script for plotting weighted histograms."""
 import numpy as np
 
 from puma import Histogram, HistogramPlot

puma/__init__.py

@@ -1,7 +1,6 @@
 """puma framework - Plotting UMami Api."""
 
 # flake8: noqa
-# pylint: skip-file
 
 __version__ = "0.2.4"
 

puma/histogram.py

@@ -12,15 +12,13 @@
 from puma.utils.histogram import hist_ratio, hist_w_unc
 
 
-class Histogram(
-    PlotLineObject
-):  # pylint: disable=too-few-public-methods,too-many-instance-attributes
+class Histogram(PlotLineObject):
     """
     Histogram class storing info about histogram and allows to calculate ratio w.r.t
     other histograms.
     """
 
-    def __init__(  # pylint: disable=too-many-arguments
+    def __init__(
         self,
         values: np.ndarray,
         weights: np.ndarray = None,
@@ -79,9 +77,8 @@ def __init__(  # pylint: disable=too-many-arguments
                 "Invalid type of histogram input data. Allowed values are "
                 "numpy.ndarray, list, pandas.core.series.Series"
             )
-        if weights is not None:
-            if len(values) != len(weights):
-                raise ValueError("`values` and `weights` are not of same length.")
+        if weights is not None and len(values) != len(weights):
+            raise ValueError("`values` and `weights` are not of same length.")
 
         self.values = values
         self.weights = weights
@@ -173,10 +170,10 @@ def divide(self, other):
         return (ratio, ratio_unc)
 
 
-class HistogramPlot(PlotBase):  # pylint: disable=too-many-instance-attributes
-    """Histogram plot class"""
+class HistogramPlot(PlotBase):
+    """Histogram plot class."""
 
-    def __init__(  # pylint: disable=too-many-arguments
+    def __init__(
         self,
         bins=40,
         bins_range: tuple = None,
@@ -188,7 +185,7 @@ def __init__(  # pylint: disable=too-many-arguments
         grid: bool = False,
         **kwargs,
     ) -> None:
-        """histogram plot properties
+        """histogram plot properties.
 
         Parameters
         ----------
@@ -292,7 +289,7 @@ def add(self, histogram: object, key: str = None, reference: bool = False):
             self.set_reference(key)
 
     def set_reference(self, key: str):
-        """Setting the reference histogram curves used in the ratios
+        """Setting the reference histogram curves used in the ratios.
 
         Parameters
         ----------
@@ -325,12 +322,11 @@ def plot(self, **kwargs):
         ValueError
             If specified bins type is not supported.
         """
-        if self.ylabel is not None:
-            if self.norm and "norm" not in self.ylabel.lower():
-                logger.warning(
-                    "You are plotting normalised distributions but 'norm' is not "
-                    "included in your y-label."
-                )
+        if self.ylabel is not None and self.norm and "norm" not in self.ylabel.lower():
+            logger.warning(
+                "You are plotting normalised distributions but 'norm' is not "
+                "included in your y-label."
+            )
         plt_handles = []
 
         # Calculate bins of stacked histograms to ensure all histograms fit in plot
@@ -422,7 +418,7 @@ def plot(self, **kwargs):
 
     def get_discrete_values(self, elem: object):
         """Get discrete values of a variable and adjust the
-        bins accordingly
+        bins accordingly.
 
         Parameters
         ----------
@@ -443,7 +439,6 @@ def get_discrete_values(self, elem: object):
             If the number of bins is set to 1 such that no values can be
             distinguished
         """
-
         if len(elem.bin_edges) > 1:
             if abs(elem.bin_edges[1] - elem.bin_edges[0]) <= 1:
                 indice = []
@@ -476,14 +471,14 @@ def get_discrete_values(self, elem: object):
                 )
         else:
             raise ValueError(
-                "Choose a binning with more than one bin in order to plot"
-                "only discrete values."
+                "Choose a binning with more than one bin in order to plot only discrete"
+                " values."
             )
 
         return bins
 
     def get_reference_histo(self, histo):
-        """Get reference histogram from list of references
+        """Get reference histogram from list of references.
 
         Parameters
         ----------
@@ -500,7 +495,6 @@ def get_reference_histo(self, histo):
         ValueError
             If no reference histo was found or multiple matches.
         """
-
         matches = 0
         reference_histo = None
 
@@ -516,8 +510,8 @@ def get_reference_histo(self, histo):
 
         if matches != 1:
             raise ValueError(
-                f"Found {matches} matching reference candidates, but only one match "
-                "is allowed."
+                f"Found {matches} matching reference candidates, but only one match is"
+                " allowed."
             )
 
         logger.debug(
@@ -583,7 +577,6 @@ def add_bin_width_to_ylabel(self):
         ValueError
             If plotting_done is False (therefore `bins` is not yet calculated)
         """
-
         if self.plotting_done is False:
             raise ValueError(
                 "`add_bin_width_to_ylabel` should be called after plotting, since bins "

puma/hlplots/__init__.py

@@ -1,6 +1,6 @@
 """High level plotting API within puma, to avoid code duplication."""
-# flake8: noqa
-# pylint: skip-file
 
 from puma.hlplots.results import Results
 from puma.hlplots.tagger import Tagger
+
+__all__ = ["Results", "Tagger"]