julearn 0.3.3__tar.gz → 0.3.3.dev4__tar.gz

{julearn-0.3.3 → julearn-0.3.3.dev4}/.pre-commit-config.yaml

@@ -4,7 +4,7 @@ ci:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v4.4.0
     hooks:
       - id: check-ast
       - id: check-docstring-first
@@ -17,27 +17,27 @@ repos:
       - id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
   - repo: https://github.com/abravalheri/validate-pyproject
-    rev: v0.17
+    rev: v0.12.2
     hooks:
       - id: validate-pyproject
-  - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 24.4.2
+  - repo: https://github.com/psf/black
+    rev: 23.3.0
     hooks:
       - id: black
         exclude: ^(docs/|examples/)
         args: [--check]
-  - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.4
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.0.267
     hooks:
       - id: ruff
         exclude: ^(__init__.py)
-        args: [--output-format, grouped, --show-fixes]
+        args: [--format, grouped, --show-fixes]
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.6
+    rev: v2.2.4
     hooks:
       - id: codespell
         exclude: ^(.github/|docs/)
-        args: [--toml, pyproject.toml]
+        args: [--config, tox.ini]
   - repo: https://github.com/pre-commit/pygrep-hooks
     rev: v1.10.0
     hooks:

{julearn-0.3.3 → julearn-0.3.3.dev4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: julearn
-Version: 0.3.3
+Version: 0.3.3.dev4
 Summary: Juelich Machine Learning Library
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Sami Hamdan <s.hamdan@fz-juelich.de>
 Maintainer-email: Sami Hamdan <s.hamdan@fz-juelich.de>

{julearn-0.3.3 → julearn-0.3.3.dev4}/docs/changes/contributors.inc

@@ -4,4 +4,3 @@
 .. _Shammi More: https://www.fz-juelich.de/SharedDocs/Personen/INM/INM-7/EN/More_s.html?nn=654218
 .. _Leonard Sasse: https://github.com/LeSasse
 .. _Synchon Mandal: https://github.com/synchon
-.. _Dante Culaciati: https://github.com/Dante-010

{julearn-0.3.3 → julearn-0.3.3.dev4}/docs/index.rst

@@ -86,14 +86,14 @@ Indices and tables
 Indices and tables
 ==================
 
-If you use julearn in a scientific publication, please use the following
+If you use julearn in a scientific publication, please use the following 
 reference
 
-    Hamdan, Sami, Shammi More, Leonard Sasse, Vera Komeyer,
-    Kaustubh R. Patil, and Federico Raimondo. ‘Julearn:
-    An Easy-to-Use Library for Leakage-Free Evaluation and Inspection of
-    ML Models’. arXiv, 19 October 2023.
+    Hamdan, Sami, Shammi More, Leonard Sasse, Vera Komeyer, 
+    Kaustubh R. Patil, and Federico Raimondo. ‘Julearn: 
+    An Easy-to-Use Library for Leakage-Free Evaluation and Inspection of 
+    ML Models’. arXiv, 19 October 2023. 
     https://doi.org/10.48550/arXiv.2310.12568.
 
-Since julearn is also heavily reliant on scikit-learn, please also cite
+Since julearn is also heavily reliant on scikit-learn, please also cite 
 them: https://scikit-learn.org/stable/about.html#citing-scikit-learn

{julearn-0.3.3 → julearn-0.3.3.dev4}/docs/what_really_need_know/cross_validation.rst

@@ -16,7 +16,7 @@ Cross-validation - The fundamentals
 This means that in order to evaluate if a model is *successful* in learning,
 we need to evaluate if it is able to predict new data. Thus, we need to have
 separate data for learning and testing. At the same time, data is a valuable
-resource in machine learning and one wants to use it as efficiently as possible.
+resource in machine learning and one wants to use it as efficeint as possible.
 
 To solve this, we use *cross validation*. The core idea is that we want to
 train (also named *fit*) a model on a subset of our data and evaluate it on a

{julearn-0.3.3 → julearn-0.3.3.dev4}/docs/whats_new.rst

@@ -8,24 +8,6 @@ What's new
 
 .. towncrier release notes start
 
-Julearn 0.3.3 (2024-05-16)
---------------------------
-
-Bugfixes
-^^^^^^^^
-
-- Fix ``OptunaSearchCV`` issue
-  (https://github.com/optuna/optuna-integration/issues/118) with an internal
-  implementation until the issue is fixed in ``optuna-integration`` by `Fede
-  Raimondo`_ (:gh:`265`)
-
-
-Improved Documentation
-^^^^^^^^^^^^^^^^^^^^^^
-
-- Fixed a typo in cross validation by `Dante Culaciati`_ (:gh:`258`)
-
-
 Julearn 0.3.2 (2024-05-03)
 --------------------------
 

{julearn-0.3.3 → julearn-0.3.3.dev4}/examples/99_docs/run_hyperparameters_docs.py

@@ -253,7 +253,7 @@ pprint(model_tuned.best_params_)
 # hyperparameters values.
 #
 # Other searchers that ``julearn`` provides are the
-# :class:`~sklearn.model_selection.RandomizedSearchCV`,
+# :class:`~sklearn.model_selection.RandomizedSearchCV`, 
 # :class:`~skopt.BayesSearchCV` and
 # :class:`~optuna_integration.sklearn.OptunaSearchCV`.
 #
@@ -383,14 +383,14 @@ pprint(model_tuned.best_params_)
 # searcher. However, the optuna searcher behaviour is controlled by a
 # :class:`~optuna.study.Study` object. This object can be passed to the
 # searcher using the ``study`` parameter in the ``search_params`` dictionary.
-#
+# 
 # .. important::
 #    The optuna searcher requires that all the hyperparameters are specified
-#    as distributions, even the categorical ones.
+#    as distributions, even the categorical ones. 
 #
 # We first modify the pipeline creator so the ``select_k`` parameter is
 # specified as a distribution. We exemplarily use a categorical distribution
-# for the ``class_weight`` hyperparameter, trying the ``"balanced"`` and
+# for the ``class_weight`` hyperparameter, trying the ``"balanced"`` and 
 # ``None`` values.
 
 creator = PipelineCreator(problem_type="classification")
@@ -445,12 +445,12 @@ pprint(model_tuned.best_params_)
 # searcher, bayesian searcher and optuna searcher. The distributions are
 # either specified toolbox-specific method or  a tuple convention with the
 # following format: ``(low, high, distribution)`` where the distribution can
-# be either ``"log-uniform"`` or ``"uniform"`` or
+# be either ``"log-uniform"`` or ``"uniform"`` or 
 # ``(a, b, c, d, ..., "categorical")`` where ``a``, ``b``, ``c``, ``d``, etc.
 # are the possible categorical values for the hyperparameter.
 #
-# For example, we can specify the ``C`` and ``gamma`` hyperparameters of the
-# :class:`~sklearn.svm.SVC` as  log-uniform distributions, while keeping
+# For example, we can specify the ``C`` and ``gamma`` hyperparameters of the 
+# :class:`~sklearn.svm.SVC` as  log-uniform distributions, while keeping 
 # the ``with_mean`` parameter of the
 # :class:`~sklearn.preprocessing.StandardScaler` as a categorical parameter
 # with two options.
@@ -469,7 +469,7 @@ print(creator)
 # While this will work for any of the ``random``, ``bayes`` or ``optuna``
 # searcher options, it is important to note that both ``bayes`` and ``optuna``
 # searchers accept further parameters to specify distributions. For example,
-# the ``bayes`` searcher distributions are defined using the
+# the ``bayes`` searcher distributions are defined using the 
 # :class:`~skopt.space.space.Categorical`, :class:`~skopt.space.space.Integer`
 # and :class:`~skopt.space.space.Real`.
 #
@@ -493,7 +493,7 @@ print(creator)
 #
 #
 # For example, we can define a uniform distribution from 0.5 to 0.9 with a 0.05
-# step for the ``n_components`` of a :class:`~sklearn.decomposition.PCA`
+# step for the ``n_components`` of a :class:`~sklearn.decomposition.PCA` 
 # transformer, while keeping a log-uniform distribution for the ``C`` and
 # ``gamma`` hyperparameters of the :class:`~sklearn.svm.SVC` model.
 from optuna.distributions import FloatDistribution

{julearn-0.3.3 → julearn-0.3.3.dev4}/ignore_words.txt

@@ -5,4 +5,4 @@ fpr
 master
 whis
 jupyter
-arange
+arange

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.3.3'
-__version_tuple__ = version_tuple = (0, 3, 3)
+__version__ = version = '0.3.3.dev4'
+__version_tuple__ = version_tuple = (0, 3, 3, 'dev4')

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/conftest.py

@@ -286,7 +286,6 @@ def bayes_search_params(request: FixtureRequest) -> Optional[Dict]:
 
     return request.param
 
-
 @fixture(
     params=[
         {"kind": "optuna", "n_trials": 10, "cv": 3},
@@ -311,7 +310,6 @@ def optuna_search_params(request: FixtureRequest) -> Optional[Dict]:
 
     return request.param
 
-
 _tuning_params = {
     "zscore": {"with_mean": [True, False]},
     "pca": {"n_components": [0.2, 0.7]},

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/model_selection/__init__.py

@@ -21,3 +21,4 @@ from ._optuna_searcher import register_optuna_searcher
 
 register_bayes_searcher()
 register_optuna_searcher()
+

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/model_selection/_optuna_searcher.py

@@ -11,8 +11,7 @@ from .available_searchers import _recreate_reset_copy, register_searcher
 
 try:
     import optuna.distributions as optd
-
-    from ..external.optuna_searchcv import OptunaSearchCV
+    from optuna_integration.sklearn import OptunaSearchCV
 except ImportError:
     from sklearn.model_selection._search import BaseSearchCV
 
@@ -90,10 +89,8 @@ def _prepare_optuna_hyperparameters_distributions(
                     )
                     out[k] = optd.FloatDistribution(v[0], v[1], log=True)
             elif v[2] == "categorical":
-                logger.info(
-                    f"Hyperparameter {k} is categorical with 2 "
-                    f"options: [{v[0]} and {v[1]}]"
-                )
+                logger.info(f"Hyperparameter {k} is categorical with 2 "
+                            f"options: [{v[0]} and {v[1]}]")
                 out[k] = optd.CategoricalDistribution((v[0], v[1]))
             else:
                 out[k] = v

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/model_selection/tests/test_optuna_searcher.py

@@ -14,7 +14,6 @@ from julearn.model_selection._optuna_searcher import (
 
 optd = pytest.importorskip("optuna.distributions")
 
-
 @pytest.mark.parametrize(
     "params_to_tune,expected_types, expected_dist",
     [

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/model_selection/tests/test_skopt_searcher.py

@@ -14,7 +14,6 @@ from julearn.model_selection._skopt_searcher import (
 
 sksp = pytest.importorskip("skopt.space")
 
-
 @pytest.mark.parametrize(
     "params_to_tune,expected_types, expected_dist",
     [

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/pipeline/merger.py

@@ -89,7 +89,10 @@ def merge_pipelines(
         # TODO: Fix this comparison, as it always returns False.
         for s in pipelines[1:]:
             if isinstance(s, BaseSearchCV):
-                if s.estimator.named_steps[t_step_name] != t:  # type: ignore
+                if (
+                    s.estimator.named_steps[t_step_name]  # type: ignore
+                    != t
+                ):
                     different_steps.append(t_step_name)
                     break
             else:

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/pipeline/tests/test_merger.py

@@ -51,14 +51,10 @@ def test_merger_pipelines() -> None:
     assert "scaler" == named_steps[1]
     assert "rf" == named_steps[2]
     assert len(merged.param_distributions) == 3  # type: ignore
-    assert merged.param_distributions[-1][
-        "rf__max_features"
-    ] == [  # type: ignore
-        2,
-        3,
-        7,
-        42,
-    ]
+    assert (
+        merged.param_distributions[-1]["rf__max_features"]  # type: ignore
+        == [2, 3, 7, 42]
+    )
 
 
 def test_merger_errors() -> None:

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/pipeline/tests/test_pipeline_creator.py

@@ -285,12 +285,8 @@ def test_hyperparameter_tuning_optuna(
         The parameters for the search.
 
     """
-    # TODO: Wait till https://github.com/optuna/optuna-integration/issues/118
-    # is solved and go back to optuna_integration instead of our own
-    # implementation
-    # optuna_integration = pytest.importorskip("optuna_integration")
-    # OptunaSearchCV = optuna_integration.OptunaSearchCV
-    from julearn.external.optuna_searchcv import OptunaSearchCV
+    optuna_integration = pytest.importorskip("optuna_integration")
+    OptunaSearchCV = optuna_integration.OptunaSearchCV
 
     pipeline, param_grid = _hyperparam_tuning_base_test(
         X_types_iris,

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/tests/test_api.py

@@ -455,8 +455,9 @@ def test_tune_hyperparam_gridsearch(df_iris: pd.DataFrame) -> None:
     )
 
     assert len(actual.columns) == len(expected) + 5  # type: ignore
-    assert len(actual["test_accuracy"]) == len(  # type: ignore
-        expected["test_accuracy"]
+    assert (
+        len(actual["test_accuracy"])  # type: ignore
+        == len(expected["test_accuracy"])
     )
     assert all(
         a == b
@@ -539,8 +540,9 @@ def test_tune_hyperparam_gridsearch_groups(df_iris: pd.DataFrame) -> None:
     )
 
     assert len(actual.columns) == len(expected) + 5  # type: ignore
-    assert len(actual["test_accuracy"]) == len(  # type: ignore
-        expected["test_accuracy"]
+    assert (
+        len(actual["test_accuracy"])  # type: ignore
+        == len(expected["test_accuracy"])
     )
     assert all(
         a == b
@@ -628,8 +630,9 @@ def test_tune_hyperparam_randomsearch(df_iris: pd.DataFrame) -> None:
     )
 
     assert len(actual.columns) == len(expected) + 5  # type: ignore
-    assert len(actual["test_accuracy"]) == len(  # type: ignore
-        expected["test_accuracy"]
+    assert (
+        len(actual["test_accuracy"])  # type: ignore
+        == len(expected["test_accuracy"])
     )
     assert all(
         a == b
@@ -743,11 +746,13 @@ def test_tune_hyperparams_multiple_grid(df_iris: pd.DataFrame) -> None:
 
     assert len(actual1.columns) == len(expected) + 5  # type: ignore
     assert len(actual2.columns) == len(expected) + 5  # type: ignore
-    assert len(actual1["test_accuracy"]) == len(  # type: ignore
-        expected["test_accuracy"]
+    assert (
+        len(actual1["test_accuracy"])  # type: ignore
+        == len(expected["test_accuracy"])
     )
-    assert len(actual2["test_accuracy"]) == len(  # type: ignore
-        expected["test_accuracy"]
+    assert (
+        len(actual2["test_accuracy"])  # type: ignore
+        == len(expected["test_accuracy"])
     )
     assert all(
         a == b

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/transformers/cbpm.py

@@ -284,10 +284,8 @@ class CBPM(BaseEstimator, TransformerMixin):
         cols = (
             ["positive"]
             if self.used_corr_sign_ == "pos"
-            else (
-                ["negative"]
-                if self.used_corr_sign_ == "neg"
-                else ["positive", "negative"]
-            )
+            else ["negative"]
+            if self.used_corr_sign_ == "neg"
+            else ["positive", "negative"]
         )
         return np.array(cols, dtype=object)

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/transformers/dataframe/change_column_types.py

@@ -75,9 +75,9 @@ class ChangeColumnTypes(JuTransformer):
             if "__:type:__" in col:
                 name, old_type = col.split("__:type:__")
                 if old_type in self.X_types_renamer:
-                    to_rename[col] = (
-                        f"{name}__:type:__{self.X_types_renamer[old_type]}"
-                    )
+                    to_rename[
+                        col
+                    ] = f"{name}__:type:__{self.X_types_renamer[old_type]}"
         self._renamer = to_rename
         return self
 

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/transformers/tests/test_jucolumntransformers.py

@@ -156,9 +156,9 @@ def test_JuColumnTransformer_row_select():
     )
 
     mean_both = (
-        transformer_both.fit(X)
-        .column_transformer_.transformers_[0][1]
-        .mean_  # type: ignore
+        transformer_both.fit(
+            X
+        ).column_transformer_.transformers_[0][1].mean_  # type: ignore
     )
 
     assert_almost_equal(

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/utils/checks.py

@@ -1,5 +1,4 @@
 """Implement various checks for the input of the functions."""
-
 # Author: Federico Raimondo <f.raimondo@fz-juelich.de>
 # License: BSD 3 clause
 

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/utils/logging.py

@@ -222,7 +222,9 @@ def raise_error(
         raise klass(msg)
 
 
-def warn_with_log(msg: str, category: Type[Warning] = RuntimeWarning) -> None:
+def warn_with_log(
+    msg: str, category: Type[Warning] = RuntimeWarning
+) -> None:
     """Warn, but first log it.
 
     Parameters

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn/utils/testing.py

@@ -185,7 +185,7 @@ def do_scoring_test(
     scorers: List[str],
     groups: Optional[str] = None,
     X_types: Optional[Dict[str, List[str]]] = None,  # noqa: N803
-    cv: Union[int, BaseCrossValidator] = 5,
+    cv: Union[int, BaseCrossValidator]  = 5,
     sk_y: Optional[np.ndarray] = None,
     decimal: int = 5,
 ):

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: julearn
-Version: 0.3.3
+Version: 0.3.3.dev4
 Summary: Juelich Machine Learning Library
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Sami Hamdan <s.hamdan@fz-juelich.de>
 Maintainer-email: Sami Hamdan <s.hamdan@fz-juelich.de>

{julearn-0.3.3 → julearn-0.3.3.dev4}/julearn.egg-info/SOURCES.txt

@@ -143,7 +143,6 @@ julearn/base/column_types.py
 julearn/base/estimators.py
 julearn/base/tests/test_base_estimators.py
 julearn/base/tests/test_column_types.py
-julearn/external/optuna_searchcv.py
 julearn/inspect/__init__.py
 julearn/inspect/_cv.py
 julearn/inspect/_pipeline.py

{julearn-0.3.3 → julearn-0.3.3.dev4}/pyproject.toml

@@ -95,7 +95,7 @@ line-length = 79
 target-version = ["py38", "py39", "py310", "py311"]
 
 [tool.codespell]
-skip = "*/auto_examples/*,*.html,.git/,*.pyc,*/_build/*,*/api/generated/*.examples,julearn/external/*"
+skip = "*/auto_examples/*,*.html,.git/,*.pyc,*/_build/*,*/api/generated/*.examples"
 count = ""
 quiet-level = 3
 ignore-words = "ignore_words.txt"
@@ -104,14 +104,6 @@ builtin = "clear,rare,informal,names,usage,code"
 
 [tool.ruff]
 line-length = 79
-extend-exclude = [
-    "__init__.py",
-    "docs",
-    "examples",
-    "external",
-]
-
-[tool.ruff.lint]
 select = [
     # flake8-bugbear
     "B",
@@ -144,6 +136,11 @@ select = [
     # flake8-2020
     "YTT",
 ]
+extend-exclude = [
+    "__init__.py",
+    "docs",
+    "examples",
+]
 extend-ignore = [
     # Use of `functools.lru_cache` or `functools.cache` on methods can lead to
     # memory leaks. The cache may retain instance references, preventing garbage
@@ -166,7 +163,7 @@ extend-ignore = [
     "PGH003",
 ]
 
-[tool.ruff.lint.isort]
+[tool.ruff.isort]
 lines-after-imports = 2
 known-first-party = ["julearn"]
 known-third-party =[
@@ -181,7 +178,7 @@ known-third-party =[
     "pytest",
 ]
 
-[tool.ruff.lint.mccabe]
+[tool.ruff.mccabe]
 max-complexity = 20
 
 [tool.towncrier]
@@ -242,6 +239,5 @@ exclude = [
     ".tox",
     ".eggs",
     "examples/",  # Lots of problems due to bad stubs, avoid filling the example with # type:ignore
-    "julearn/external",  # External code, not to be checked
     "scratch/",  # place to prototype, not to be checked
 ]

{julearn-0.3.3 → julearn-0.3.3.dev4}/tox.ini

@@ -98,7 +98,6 @@ omit =
     */tests/*
     */utils/typing.py
     */viz/*
-    */external/*
 parallel = false
 
 [coverage:report]