Merge branch 'main' into remove-legacy-model_selection

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.4.0
     hooks:
       - id: check-added-large-files
         args: ["--maxkb=1000"]
@@ -12,37 +12,46 @@ repos:
       - id: end-of-file-fixer
         exclude: "^docs/source/examples/"
       - id: fix-encoding-pragma
+        args:
+          - --remove
       - id: requirements-txt-fixer
       - id: trailing-whitespace
 
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.10.1
+    hooks:
+      - id: pyupgrade
+        args:
+          - --py38-plus
+
   - repo: https://github.com/pycqa/isort
     rev: 5.12.0
     hooks:
       - id: isort
         name: isort
 
   - repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 23.7.0
     hooks:
       - id: black
         language_version: python3
         # args: [--line-length 79]
 
   - repo: https://github.com/pycqa/flake8
-    rev: 4.0.1
+    rev: 6.1.0
     hooks:
       - id: flake8
         exclude: docs/conf.py
         additional_dependencies: [flake8-bugbear, flake8-print]
 
   - repo: https://github.com/mgedmin/check-manifest
-    rev: "0.47"
+    rev: "0.49"
     hooks:
       - id: check-manifest
         stages: [manual]
 
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.2.2
+    rev: 1.7.0
     hooks:
       - id: nbqa-black
         args: [--nbqa-mutate, --nbqa-dont-skip-bad-cells]
@@ -55,15 +64,15 @@ repos:
         additional_dependencies: [flake8==3.8.3]
 
   - repo: https://github.com/pycqa/pydocstyle
-    rev: 6.1.1
+    rev: 6.3.0
     hooks:
       - id: pydocstyle
         args: ["--config=setup.cfg"]
 
   # We use the Python version instead of the original version which seems to require Docker
   # https://github.com/koalaman/shellcheck-precommit
   - repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: v0.8.0.4
+    rev: v0.9.0.5
     hooks:
       - id: shellcheck
         name: shellcheck

build_tools/changelog.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """RestructuredText changelog generator."""
 
 import os
@@ -140,7 +139,6 @@ def render_changelog(prs, assigned):  # noqa
 
 
 if __name__ == "__main__":
-
     categories = [
         {"title": "Enhancements", "labels": ["feature", "enhancement"]},
         {"title": "Fixes", "labels": ["bug", "fix", "bugfix"]},

docs/conf.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 #
 # This file is execfile()d with the current directory set to its containing dir.
 #

examples/parametric/bagging.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # LEGACY MODULE - TODO: remove or refactor
 from sklearn.tree import DecisionTreeRegressor
 

examples/parametric/hyperparameters.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # LEGACY MODULE - TODO: remove or refactor
 from sklearn.datasets.base import load_diabetes
 from sklearn.ensemble import RandomForestRegressor

examples/parametric/simple.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # LEGACY MODULE - TODO: remove or refactor
 from sklearn.datasets.base import load_diabetes
 from sklearn.ensemble import RandomForestRegressor

examples/parametric/workflow.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # LEGACY MODULE - TODO: remove or refactor
 from sklearn.ensemble import RandomForestRegressor
 from sklearn.linear_model import LinearRegression

extension_templates/regression.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Extension template for regressors."""
 # todo: write an informative docstring for the file or module, remove the above
 # todo: add an appropriate copyright notice for your estimator
@@ -55,8 +54,8 @@ def __init__(self, paramname, paramname2="paramname2default"):
         self.paramname = paramname
         self.paramname2 = "paramname2default"
 
-        # todo: change "ClassName" to the name of the class
-        super(ClassName, self).__init__()
+        # leave this as is
+        super().__init__()
 
         # todo: optional, parameter checking logic (if applicable) should happen here
         # if writes derived values to self, should *not* overwrite self.parama etc

skpro/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """skpro."""
 
 __version__ = "2.0.0"

skpro/base/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Base module with base classes BaseObject, BaseEstimator."""
 # copyright: skpro developers, BSD-3-Clause License (see LICENSE file)
 

skpro/base/_base.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Base class and template for regressors and transformers."""
 from skbase.base import BaseEstimator as _BaseEstimator
 from skbase.base import BaseMetaEstimator as _BaseMetaEstimator

skpro/base/old_base.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # LEGACY MODULE - TODO: remove or refactor
 import abc
 import functools

skpro/benchmarking/__init__.py

@@ -1,2 +1 @@
-# -*- coding: utf-8 -*-
 """Benchmarking and evaluation."""

skpro/benchmarking/evaluate.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # copyright: skpro developers, BSD-3-Clause License (see LICENSE file)
 """Utility for benchmark evaluation of probabilistic regression models."""
 # based on the sktime utility of the same name
@@ -18,7 +17,6 @@
 
 
 def _split(X, y, train, test):
-
     # split data according to cv
     X_train, X_test = X.iloc[train], X.iloc[test]
 

skpro/benchmarking/tests/__init__.py

@@ -1,2 +1 @@
-# -*- coding: utf-8 -*-
 """Tests for benchmarking and evaluation."""

skpro/benchmarking/tests/test_evaluate.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Tests for evaluate utility."""
 # copyright: skpro developers, BSD-3-Clause License (see LICENSE file)
 # based on the sktime tests of the same name

skpro/datatypes/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Module exports: data type definitions, checks, validation, fixtures, converters."""
 # this module has been adapted from sktime
 # it is largely copy-pasting the Proba and Table parts

skpro/datatypes/_check.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # copyright: skpro developers, BSD-3-Clause License (see LICENSE file)
 """Machine type checkers for scitypes.
 
@@ -41,7 +40,7 @@
 
 def _check_scitype_valid(scitype: str = None):
     """Check validity of scitype."""
-    valid_scitypes = list(set([x[1] for x in check_dict.keys()]))
+    valid_scitypes = list({x[1] for x in check_dict.keys()})
 
     if not isinstance(scitype, str):
         raise TypeError(f"scitype should be a str but found {type(scitype)}")

skpro/datatypes/_common.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # copyright: skpro developers, BSD-3-Clause License (see LICENSE file)
 """Common private utilities for checkers and converters."""
 

skpro/datatypes/_convert.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # copyright: skpro developers, BSD-3-Clause License (see LICENSE file)
 """Machine type converters for scitypes.
 
@@ -281,8 +280,8 @@ def _conversions_defined(scitype: str):
                                      0 if conversion from i to j is not defined
     """
     pairs = [(x[0], x[1]) for x in list(convert_dict.keys()) if x[2] == scitype]
-    cols0 = set([x[0] for x in list(convert_dict.keys()) if x[2] == scitype])
-    cols1 = set([x[1] for x in list(convert_dict.keys()) if x[2] == scitype])
+    cols0 = {x[0] for x in list(convert_dict.keys()) if x[2] == scitype}
+    cols1 = {x[1] for x in list(convert_dict.keys()) if x[2] == scitype}
     cols = sorted(list(cols0.union(cols1)))
 
     mat = np.zeros((len(cols), len(cols)), dtype=int)

skpro/datatypes/_convert_utils/__init__.py

@@ -1,2 +1 @@
-# -*- coding: utf-8 -*-
 """Conversion auxiliary utilities."""

skpro/datatypes/_convert_utils/_coerce.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Conercion utilities for mtypes."""
 
 __author__ = ["fkiraly"]
@@ -7,7 +6,6 @@
 
 
 def _is_nullable_numeric(dtype):
-
     return dtype in ["Int64", "Float64", "boolean"]
 
 

skpro/datatypes/_convert_utils/_convert.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Conversion utilities for mtypes."""
 
 __author__ = ["fkiraly"]
@@ -64,7 +63,7 @@ def _extend_conversions(mtype, anchor_mtype, convert_dict, mtype_universe=None):
     scitype = list(keys)[0][2]
 
     if mtype_universe is None:
-        mtype_universe = set([x[1] for x in list(keys)])
+        mtype_universe = {x[1] for x in list(keys)}
         mtype_universe = mtype_universe.union([x[0] for x in list(keys)])
 
     for tp in set(mtype_universe).difference([mtype, anchor_mtype]):

skpro/datatypes/_examples.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # copyright: skpro developers, BSD-3-Clause License (see LICENSE file)
 """Example fixtures for mtypes/scitypes.
 

skpro/datatypes/_proba/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Type checkers, converters and mtype inference for probabilistic return types."""
 
 from skpro.datatypes._proba._check import check_dict as check_dict_Proba

skpro/datatypes/_proba/_check.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Machine type checkers for Series scitype.
 
 Exports checkers for Series scitype:
@@ -48,7 +47,6 @@
 
 
 def check_pred_quantiles_proba(obj, return_metadata=False, var_name="obj"):
-
     metadata = dict()
 
     # check if the input is a dataframe
@@ -103,7 +101,6 @@ def check_pred_quantiles_proba(obj, return_metadata=False, var_name="obj"):
 
 
 def check_pred_interval_proba(obj, return_metadata=False, var_name="obj"):
-
     metadata = dict()
 
     # check if the input is a dataframe

skpro/datatypes/_proba/_convert.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Machine type converters for Series scitype.
 
 Exports conversion and mtype dictionary for Series scitype:
@@ -44,7 +43,6 @@
 
 
 def convert_identity(obj, store=None):
-
     return obj
 
 
@@ -109,7 +107,6 @@ def convert_pred_interval_to_quantiles(y_pred, inplace=False):
 
 
 def convert_interval_to_quantiles(obj: pd.DataFrame, store=None) -> pd.DataFrame:
-
     return convert_pred_interval_to_quantiles(y_pred=obj)
 
 
@@ -169,7 +166,6 @@ def convert_pred_quantiles_to_interval(y_pred, inplace=False):
 
 
 def convert_quantiles_to_interval(obj: pd.DataFrame, store=None) -> pd.DataFrame:
-
     return convert_pred_quantiles_to_interval(y_pred=obj)
 
 

skpro/datatypes/_proba/_examples.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Example generation for testing.
 
 Exports dict of examples, useful for testing as fixtures.

skpro/datatypes/_registry.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 # copyright: skpro developers, BSD-3-Clause License (see LICENSE file)
 """Registry of mtypes and scitypes.
 

skpro/datatypes/_table/__init__.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Module exports: Series type checkers, converters and mtype inference."""
 
 from skpro.datatypes._table._check import check_dict as check_dict_Table

skpro/datatypes/_table/_check.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 """Machine type checkers for Table scitype.
 
 Exports checkers for Table scitype:
@@ -49,7 +48,6 @@
 
 
 def check_pddataframe_table(obj, return_metadata=False, var_name="obj"):
-
     metadata = dict()
 
     if not isinstance(obj, pd.DataFrame):
@@ -79,7 +77,6 @@ def check_pddataframe_table(obj, return_metadata=False, var_name="obj"):
 
 
 def check_pdseries_table(obj, return_metadata=False, var_name="obj"):
-
     metadata = dict()
 
     if not isinstance(obj, pd.Series):
@@ -112,7 +109,6 @@ def check_pdseries_table(obj, return_metadata=False, var_name="obj"):
 
 
 def check_numpy1d_table(obj, return_metadata=False, var_name="obj"):
-
     metadata = dict()
 
     if not isinstance(obj, np.ndarray):
@@ -142,7 +138,6 @@ def check_numpy1d_table(obj, return_metadata=False, var_name="obj"):
 
 
 def check_numpy2d_table(obj, return_metadata=False, var_name="obj"):
-
     metadata = dict()
 
     if not isinstance(obj, np.ndarray):
@@ -171,7 +166,6 @@ def check_numpy2d_table(obj, return_metadata=False, var_name="obj"):
 
 
 def check_list_of_dict_table(obj, return_metadata=False, var_name="obj"):
-
     metadata = dict()
 
     if not isinstance(obj, list):