julearn 0.3.5.dev16__tar.gz → 0.3.5.dev25__tar.gz

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: julearn
-Version: 0.3.5.dev16
+Version: 0.3.5.dev25
 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>
@@ -56,6 +56,7 @@ Requires-Dist: optuna<3.7,>=3.6.0; extra == "optuna"
 Requires-Dist: optuna_integration<4.1,>=3.6.0; extra == "optuna"
 Provides-Extra: all
 Requires-Dist: julearn[optuna,skopt,viz]; extra == "all"
+Dynamic: license-file
 
 # julearn
 
@@ -67,6 +68,7 @@ Requires-Dist: julearn[optuna,skopt,viz]; extra == "all"
 ![Codecov](https://img.shields.io/codecov/c/github/juaml/julearn?style=flat-square)
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/charliermarsh/ruff)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)
+![JuRSE Code Pick](https://img.shields.io/badge/JuRSE_Code_Pick-May_2025-blue?link=https://www.fz-juelich.de/en/rse/jurse-community/jurse-code-of-the-month/may-2025)
 
 ## About
 
@@ -113,6 +115,6 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 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. https://doi.org/10.48550/arXiv.2310.12568.
+> Sami Hamdan,Shammi More,Leonard Sasse,Vera Komeyer,Kaustubh R. Patil,Federico Raimondo,for the Alzheimer’s Disease Neuroimaging Initiative,Julearn: an easy-to-use library for leakage-free evaluation and inspection of ML models,Gigabyte,2024 https://doi.org/10.46471/gigabyte.113
 
 Since julearn is also heavily reliant on scikit-learn, please also cite them: https://scikit-learn.org/stable/about.html#citing-scikit-learn

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/README.md

@@ -8,6 +8,7 @@
 ![Codecov](https://img.shields.io/codecov/c/github/juaml/julearn?style=flat-square)
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/charliermarsh/ruff)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)
+![JuRSE Code Pick](https://img.shields.io/badge/JuRSE_Code_Pick-May_2025-blue?link=https://www.fz-juelich.de/en/rse/jurse-community/jurse-code-of-the-month/may-2025)
 
 ## About
 
@@ -54,6 +55,6 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 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. https://doi.org/10.48550/arXiv.2310.12568.
+> Sami Hamdan,Shammi More,Leonard Sasse,Vera Komeyer,Kaustubh R. Patil,Federico Raimondo,for the Alzheimer’s Disease Neuroimaging Initiative,Julearn: an easy-to-use library for leakage-free evaluation and inspection of ML models,Gigabyte,2024 https://doi.org/10.46471/gigabyte.113
 
 Since julearn is also heavily reliant on scikit-learn, please also cite them: https://scikit-learn.org/stable/about.html#citing-scikit-learn

julearn-0.3.5.dev25/docs/changes/newsfragments/279.doc

@@ -0,0 +1 @@
+Update citation in README by `Synchon Mandal`_

julearn-0.3.5.dev25/docs/changes/newsfragments/283.doc

@@ -0,0 +1 @@
+Add JuRSE Code Pick shield in README by `Synchon Mandal`_

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/examples/00_starting/plot_stratified_kfold_reg.py

@@ -75,7 +75,7 @@ sns.displot(data_df, x="target", bins=20)
 # distributed. We can see that the data is skewed towards the lower end of
 # the target variable. We can also see that there are some outliers in the
 # data. In any case, even with a low number of splits, some groups will not be
-# represented in each fold. Lets continue with 40 bins which gives a good
+# represented in each fold. Let's continue with 40 bins which gives a good
 # granularity.
 
 cv_stratified = ContinuousStratifiedKFold(n_bins=40, n_splits=5, shuffle=False)

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/examples/00_starting/run_combine_pandas.py

@@ -122,7 +122,7 @@ df_fmri = df_fmri.reset_index()
 
 ###############################################################################
 # Reshaping data frames (more complex)
-# Lets suppose that our prediction target is now the *age* and we want to use
+# Let's suppose that our prediction target is now the *age* and we want to use
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 # as features the frontal and parietal value during each event. For this
 # purpose, we need to convert the event values into columns. There are two

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/examples/00_starting/run_grouped_cv.py

@@ -40,7 +40,7 @@ configure_logging(level="INFO")
 df_fmri = load_dataset("fmri")
 
 ###############################################################################
-# First, lets get some information on what the dataset has:
+# First, let's get some information on what the dataset has:
 
 print(df_fmri.head())
 
@@ -49,7 +49,7 @@ print(df_fmri.head())
 # were several subjects, timepoints, events and signal extracted from several
 # brain regions.
 #
-# Lets check how many kinds of each we have.
+# Let's check how many kinds of each we have.
 print(df_fmri["event"].unique())
 print(df_fmri["region"].unique())
 print(sorted(df_fmri["timepoint"].unique()))
@@ -58,7 +58,7 @@ print(df_fmri["subject"].unique())
 ###############################################################################
 # We have data from parietal and frontal regions during 2 types of events
 # (*cue* and *stim*) during 18 timepoints and for 14 subjects.
-# Lets see how many samples we have for each condition
+# Let's see how many samples we have for each condition
 
 print(df_fmri.groupby(["subject", "timepoint", "event", "region"]).count())
 print(
@@ -72,7 +72,7 @@ print(
 ###############################################################################
 # We have exactly one value per condition.
 #
-# Lets try to build a model, that uses parietal and frontal signal to predicts
+# Let's try to build a model, that uses parietal and frontal signal to predicts
 # whether the event was a *cue* or a *stim*.
 #
 # First we define our X and y variables.

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/examples/02_inspection/plot_groupcv_inspect_svm.py

@@ -42,7 +42,7 @@ configure_logging(level="INFO")
 df_fmri = load_dataset("fmri")
 
 ###############################################################################
-# First, lets get some information on what the dataset has:
+# First, let's get some information on what the dataset has:
 
 print(df_fmri.head())
 
@@ -51,7 +51,7 @@ print(df_fmri.head())
 # were several subjects, timepoints, events and signal extracted from several
 # brain regions.
 #
-# Lets check how many kinds of each we have.
+# Let's check how many kinds of each we have.
 
 print(df_fmri["event"].unique())
 print(df_fmri["region"].unique())
@@ -61,7 +61,7 @@ print(df_fmri["subject"].unique())
 ###############################################################################
 # We have data from parietal and frontal regions during 2 types of events
 # (*cue* and *stim*) during 18 timepoints and for 14 subjects.
-# Lets see how many samples we have for each condition
+# Let's see how many samples we have for each condition
 
 print(df_fmri.groupby(["subject", "timepoint", "event", "region"]).count())
 print(
@@ -75,7 +75,7 @@ print(
 ###############################################################################
 # We have exactly one value per condition.
 #
-# Lets try to build a model, that uses parietal and frontal signal to predicts
+# Let's try to build a model, that uses parietal and frontal signal to predicts
 # whether the event was a *cue* or a *stim*.
 #
 # First we define our X and y variables.

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/examples/03_complex_models/run_hyperparameter_multiple_grids.py

@@ -47,7 +47,7 @@ df_fmri = df_fmri.reset_index()
 df_fmri.head()
 
 ###############################################################################
-# Lets do a first attempt and use a linear SVM with the default parameters.
+# Let's do a first attempt and use a linear SVM with the default parameters.
 
 X = ["frontal", "parietal"]
 y = "event"

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/examples/03_complex_models/run_hyperparameter_tuning.py

@@ -84,7 +84,7 @@ scores, estimator = run_cross_validation(
 print(scores["test_score"].mean())
 
 ###############################################################################
-# This did not change much, lets explore other kernels too.
+# This did not change much, let's explore other kernels too.
 
 creator = PipelineCreator(problem_type="classification")
 creator.add("zscore")

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/examples/99_docs/run_cv_splitters_docs.py

@@ -182,7 +182,7 @@ fig.suptitle(
 )
 
 ###############################################################################
-# Now lets see how K-fold would have split this data.
+# Now let's see how K-fold would have split this data.
 cv = KFold(n_splits=3, shuffle=True, random_state=42)
 
 fig, axis = plt.subplots(1, 2, figsize=(20, 4))

julearn-0.3.5.dev25/julearn/_version.py

@@ -0,0 +1,21 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+else:
+    VERSION_TUPLE = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+
+__version__ = version = '0.3.5.dev25'
+__version_tuple__ = version_tuple = (0, 3, 5, 'dev25')

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/base/column_types.py

@@ -30,7 +30,7 @@ def change_column_type(column: str, new_type: str):
         The new column name with the type changed.
 
     """
-    return "__:type:__".join(column.split("__:type:__")[0:1] + [new_type])
+    return "__:type:__".join([*column.split("__:type:__")[0:1], new_type])
 
 
 def get_column_type(column):

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/base/estimators.py

@@ -492,7 +492,7 @@ class WrapModel(JuBaseEstimator):
 
         """
         model_params = list(self.model.get_params(True).keys())
-        kwargs = cast(Dict[str, Any], kwargs)
+        kwargs = cast("Dict[str, Any]", kwargs)
         for param, val in kwargs.items():
             if param in model_params:
                 self.model.set_params(**{param: val})

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/conftest.py

@@ -90,7 +90,7 @@ def df_typed_iris() -> pd.DataFrame:
 
     """
     df = load_dataset("iris")
-    df = typing.cast(pd.DataFrame, df)
+    df = typing.cast("pd.DataFrame", df)
 
     rename = {
         "sepal_length": "sepal_length__:type:__continuous",
@@ -113,7 +113,7 @@ def df_iris() -> pd.DataFrame:
 
     """
     df = load_dataset("iris")
-    df = typing.cast(pd.DataFrame, df)
+    df = typing.cast("pd.DataFrame", df)
 
     return df.copy()
 
@@ -129,7 +129,7 @@ def df_binary() -> pd.DataFrame:
 
     """
     df_iris = load_dataset("iris")
-    df_iris = typing.cast(pd.DataFrame, df_iris)
+    df_iris = typing.cast("pd.DataFrame", df_iris)
     df_binary = df_iris[df_iris["species"].isin(["setosa", "virginica"])]
 
     return df_binary
@@ -148,7 +148,7 @@ def X_iris() -> pd.DataFrame:
 
     """
     df = load_dataset("iris")
-    df = typing.cast(pd.DataFrame, df)
+    df = typing.cast("pd.DataFrame", df)
     features = ["sepal_length", "sepal_width", "petal_length", "petal_width"]
     return df.loc[:, features]
 
@@ -166,7 +166,7 @@ def y_iris() -> pd.Series:
 
     """
     df = load_dataset("iris")
-    df = typing.cast(pd.DataFrame, df)
+    df = typing.cast("pd.DataFrame", df)
 
     return df.loc[:, "species"].astype("category").cat.codes
 

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/inspect/tests/test_preprocess.py

@@ -79,7 +79,7 @@ def test_preprocess_sklearn(
 
     """
     X = list(X_iris.columns)
-    X = cast(List[str], X)
+    X = cast("List[str]", X)
     pipeline.fit(X_iris, y=y_iris)
 
     X_train = X_iris.copy()
@@ -111,7 +111,7 @@ def test_preprocess_sklearn_nodataframe(
 
     """
     X = list(X_iris.columns)
-    X = cast(List[str], X)
+    X = cast("List[str]", X)
     pipeline = Pipeline([("scaler", StandardScaler()), ("svm", SVC())])
     pipeline.fit(X_iris, y=y_iris)
 

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/pipeline/pipeline_creator.py

@@ -255,7 +255,7 @@ class PipelineCreator:
                     "TargetPipelineCreator can only be added to the target."
                 )
             step = step.to_pipeline()  # type: ignore
-            step = typing.cast(JuTargetPipeline, step)
+            step = typing.cast("JuTargetPipeline", step)
         # Validate the step
         self._validate_step(step, apply_to)
 
@@ -609,7 +609,7 @@ class PipelineCreator:
             params_to_tune.update(step_params_to_tune)
             pipeline_steps.append((model_name, model_estimator))
         pipeline = Pipeline(pipeline_steps).set_output(transform="pandas")
-        pipeline = typing.cast(Pipeline, pipeline)  # damn typing..
+        pipeline = typing.cast("Pipeline", pipeline)  # damn typing..
         # Deal with the Hyperparameter tuning
         out = _prepare_hyperparameter_tuning(
             params_to_tune, search_params, pipeline

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/scoring/available_scorers.py

@@ -161,7 +161,7 @@ def check_scoring(
             wrap_score,
         )
     if isinstance(scoring, list):
-        scorer_names = typing.cast(List[str], scoring)
+        scorer_names = typing.cast("List[str]", scoring)
         scoring_dict = {
             score: _extend_scorer(get_scorer(score), wrap_score)
             for score in scorer_names

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/stats/corrected_ttest.py

@@ -168,8 +168,8 @@ def corrected_ttest(
         n_train = i_scores["n_train"].values
         n_test = i_scores["n_test"].values
 
-        n_train = typing.cast(np.ndarray, n_train)
-        n_test = typing.cast(np.ndarray, n_test)
+        n_train = typing.cast("np.ndarray", n_train)
+        n_test = typing.cast("np.ndarray", n_test)
 
         if np.unique(n_train).size > 1:
             warn_with_log(

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/tests/test_prepare.py

@@ -240,7 +240,7 @@ def test_prepare_input_data_erors() -> None:
         )
 
     # Missing column in dataframe
-    X = columns[:5] + ["wrong"]
+    X = [*columns[:5], "wrong"]
     y = columns[6]
     groups = columns[7]
     with pytest.raises(ValueError, match=r"missing: \['wrong'\]"):

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/transformers/target/ju_transformed_target_model.py

@@ -116,7 +116,7 @@ class JuTransformedTargetModel(JuBaseEstimator):
         """
         if not hasattr(self, "model_"):
             raise_error("Model not fitted yet.")
-        self.model_ = typing.cast(ModelLike, self.model_)
+        self.model_ = typing.cast("ModelLike", self.model_)
         # TODO: Check if we can inverse the y transformations
         # Raise warning if not possible
         y_pred = self.model_.predict(X)
@@ -150,7 +150,7 @@ class JuTransformedTargetModel(JuBaseEstimator):
         """
         if not hasattr(self, "model_"):
             raise_error("Model not fitted yet.")
-        self.model_ = typing.cast(ModelLike, self.model_)
+        self.model_ = typing.cast("ModelLike", self.model_)
         y_trans = self.transform_target(X, y)
         return self.model_.score(X, y_trans)
 
@@ -173,7 +173,7 @@ class JuTransformedTargetModel(JuBaseEstimator):
         """
         if not hasattr(self, "model_"):
             raise_error("Model not fitted yet.")
-        self.model_ = typing.cast(ModelLike, self.model_)
+        self.model_ = typing.cast("ModelLike", self.model_)
         return self.model_.predict_proba(X)  # type: ignore
 
     @available_if(_wrapped_model_has("decision_function"))
@@ -194,7 +194,7 @@ class JuTransformedTargetModel(JuBaseEstimator):
         """
         if not hasattr(self, "model_"):
             raise_error("Model not fitted yet.")
-        self.model_ = typing.cast(ModelLike, self.model_)
+        self.model_ = typing.cast("ModelLike", self.model_)
         return self.model_.decision_function(X)  # type: ignore
 
     def transform_target(
@@ -233,5 +233,5 @@ class JuTransformedTargetModel(JuBaseEstimator):
         """Get the classes of the model."""
         if not hasattr(self, "model_"):
             raise_error("Model not fitted yet.")
-        self.model_ = typing.cast(ModelLike, self.model_)
+        self.model_ = typing.cast("ModelLike", self.model_)
         return self.model_.classes_

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn/transformers/target/target_confound_remover.py

@@ -99,7 +99,7 @@ class TargetConfoundRemover(JuTargetTransformer):
         y_pred = self.model_confounds_.predict(  # type: ignore
             X_confounds.values
         )
-        y_pred = typing.cast(pd.Series, y_pred)
+        y_pred = typing.cast("pd.Series", y_pred)
         residuals = y - y_pred
         if self.threshold is not None:
             residuals[np.abs(residuals) < self.threshold] = 0

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: julearn
-Version: 0.3.5.dev16
+Version: 0.3.5.dev25
 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>
@@ -56,6 +56,7 @@ Requires-Dist: optuna<3.7,>=3.6.0; extra == "optuna"
 Requires-Dist: optuna_integration<4.1,>=3.6.0; extra == "optuna"
 Provides-Extra: all
 Requires-Dist: julearn[optuna,skopt,viz]; extra == "all"
+Dynamic: license-file
 
 # julearn
 
@@ -67,6 +68,7 @@ Requires-Dist: julearn[optuna,skopt,viz]; extra == "all"
 ![Codecov](https://img.shields.io/codecov/c/github/juaml/julearn?style=flat-square)
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/charliermarsh/ruff)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)
+![JuRSE Code Pick](https://img.shields.io/badge/JuRSE_Code_Pick-May_2025-blue?link=https://www.fz-juelich.de/en/rse/jurse-community/jurse-code-of-the-month/may-2025)
 
 ## About
 
@@ -113,6 +115,6 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
 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. https://doi.org/10.48550/arXiv.2310.12568.
+> Sami Hamdan,Shammi More,Leonard Sasse,Vera Komeyer,Kaustubh R. Patil,Federico Raimondo,for the Alzheimer’s Disease Neuroimaging Initiative,Julearn: an easy-to-use library for leakage-free evaluation and inspection of ML models,Gigabyte,2024 https://doi.org/10.46471/gigabyte.113
 
 Since julearn is also heavily reliant on scikit-learn, please also cite them: https://scikit-learn.org/stable/about.html#citing-scikit-learn

{julearn-0.3.5.dev16 → julearn-0.3.5.dev25}/julearn.egg-info/SOURCES.txt

@@ -56,6 +56,8 @@ docs/changes/contributors.inc
 docs/changes/newsfragments/.gitignore
 docs/changes/newsfragments/277.enh
 docs/changes/newsfragments/278.doc
+docs/changes/newsfragments/279.doc
+docs/changes/newsfragments/283.doc
 docs/images/corrected_ttest.png
 docs/images/final_estimator.png
 docs/images/iris_X.png

julearn-0.3.5.dev16/julearn/_version.py

@@ -1,16 +0,0 @@
-# file generated by setuptools_scm
-# don't change, don't track in version control
-TYPE_CHECKING = False
-if TYPE_CHECKING:
-    from typing import Tuple, Union
-    VERSION_TUPLE = Tuple[Union[int, str], ...]
-else:
-    VERSION_TUPLE = object
-
-version: str
-__version__: str
-__version_tuple__: VERSION_TUPLE
-version_tuple: VERSION_TUPLE
-
-__version__ = version = '0.3.5.dev16'
-__version_tuple__ = version_tuple = (0, 3, 5, 'dev16')