Typing fixes and cleanup in estimators.py

CITATION.cff

@@ -0,0 +1,109 @@
+---
+cff-version: 1.2.0
+
+message: "If you use auto-sklearn in a scientific publication, we would appreciate a reference to the following paper"
+
+title: "auto-sklearn"
+date-released: "2015-07-02"
+
+url: "https://automl.github.io/auto-sklearn/master/"
+repository-code: "https://github.com/automl/auto-sklearn"
+
+version: "0.14.0"
+
+type: "software"
+keywords:
+  - "automated machine learning"
+  - "machine learning"
+
+license: "BSD-3-Clause"
+
+authors:
+  - family-names: "Feurer"
+    given-names: "Matthias"
+    orcid: "https://orcid.org/0000-0001-9611-8588"
+    affiliation: "University of Freiburg, Germany"
+
+  - family-names: "Eggensperger"
+    given-names: "Katharina" 
+    orcid: "https://orcid.org/0000-0002-0309-401X"
+    affiliation: "University of Freiburg, Germany"
+
+  - family-name: "Bergman"
+    given-names: "Edward"
+    affiliation: "University of Freiburg, Germany"
+
+  - family-name: "Rivera Valverde"
+    given-names: "Francisco"
+    affiliation: "University of Freiburg, Germany"
+
+  - family-names: "Jost"
+    given-names: "Springenberg"
+    orcid: "https://orcid.org/0000-0002-9392-1006"
+    affiliation: "University of Freiburg, Germany"
+
+  - family-names: "Manuel"
+    given-names: "Blum"
+    affiliation: "University of Freiburg, Germany"
+
+  - family-names: "Hutter"
+    given-names: "Frank"
+    affiliation: "University of Freiburg, Germany"
+
+preferred-citation:
+  type: "proceedings"
+  title: "Efficient and Robust Automated Machine Learning"
+  collection-title: "Advances in Nerual Infromation Processing Systems 28 (2015)"
+  year: 2015
+  pages: "2962--2970"
+  url: "https://papers.neurips.cc/paper/5872-efficient-and-robust-automated-machine-learning.pdf"
+
+  publisher:
+    name: "Curran Associates, Inc."
+
+  editors:
+
+    - family-names: "Cortes"
+      given-names: "C."
+
+    - family-names: "Lawrence"
+      given-names: "N."
+
+    - family-names: "Lee"
+      given-names: "D."
+
+    - family-names: "Sugiyama"
+      given-names: "M."
+
+    - family-names: "Garnett"
+      given-names: "R."
+
+  authors:
+
+    - family-names: "Feurer"
+      given-names: "Matthias" 
+      orcid: "https://orcid.org/0000-0001-9611-8588"
+      affiliation: "University of Freiburg, Germany"
+
+    - family-names: "Klein"
+      given-names: "Aaron"
+      affiliation: "University of Freiburg, Germany"
+
+    - family-names: "Eggensperger"
+      given-names: "Katharina" 
+      orcid: "https://orcid.org/0000-0002-0309-401X"
+      affiliation: "University of Freiburg, Germany"
+
+    - family-names: "Jost"
+      given-names: "Springenberg"
+      orcid: "https://orcid.org/0000-0002-9392-1006"
+      affiliation: "University of Freiburg, Germany"
+
+    - family-names: "Manuel"
+      given-names: "Blum"
+      affiliation: "University of Freiburg, Germany"
+
+    - family-names: "Hutter"
+      given-names: "Frank"
+      affiliation: "University of Freiburg, Germany"
+...

README.md

@@ -30,14 +30,14 @@ If you use auto-sklearn in scientific publications, we would appreciate citation
 *Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum and Frank Hutter*  
 Advances in Neural Information Processing Systems 28 (2015)  
 
-[Link](https://papers.nips.cc/paper/5872-efficient-and-robust-automated-machine-learning.pdf) to publication.
+[Link](https://papers.neurips.cc/paper/5872-efficient-and-robust-automated-machine-learning.pdf) to publication.
 ```
 @inproceedings{feurer-neurips15a,
-  title     = {Efficient and Robust Automated Machine Learning},
-  author    = {Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum and Frank Hutter},
-  booktitle = {Advances in Neural Information Processing Systems 28 (2015)},
-  pages     = {2962--2970},
-  year      = {2015}
+    title     = {Efficient and Robust Automated Machine Learning},
+    author    = {Feurer, Matthias and Klein, Aaron and Eggensperger, Katharina  Springenberg, Jost and Blum, Manuel and Hutter, Frank},
+    booktitle = {Advances in Neural Information Processing Systems 28 (2015)},
+    pages     = {2962--2970},
+    year      = {2015}
 }
 ```
 
@@ -49,11 +49,11 @@ arXiv:2007.04074 [cs.LG], 2020
 
 [Link](https://arxiv.org/abs/2007.04074) to publication.
 ```
-@inproceedings{feurer-arxiv20a,
-  title     = {Auto-Sklearn 2.0: The Next Generation},
-  author    = {Matthias Feurer, Katharina Eggensperger, Stefan Falkner, Marius Lindauer and Frank Hutter},
-  booktitle = {arXiv:2007.04074 [cs.LG]},
-  year      = {2020}
+@article{feurer-arxiv20a,
+    title     = {Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning},
+    author    = {Feurer, Matthias and Eggensperger, Katharina and Falkner, Stefan and Lindauer, Marius and Hutter, Frank},
+    booktitle = {arXiv:2007.04074 [cs.LG]},
+    year      = {2020}
 }
 ```
 

autosklearn/automl.py

@@ -31,7 +31,6 @@
 from smac.stats.stats import Stats
 import joblib
 import sklearn.utils
-from scipy.sparse import spmatrix
 from sklearn.utils import check_random_state
 from sklearn.utils.validation import check_is_fitted
 from sklearn.metrics._classification import type_of_target
@@ -486,10 +485,10 @@ def _supports_task_type(cls, task_type: str) -> bool:
     def fit(
         self,
         X: SUPPORTED_FEAT_TYPES,
-        y: Union[SUPPORTED_TARGET_TYPES, spmatrix],
+        y: SUPPORTED_TARGET_TYPES,
         task: Optional[int] = None,
         X_test: Optional[SUPPORTED_FEAT_TYPES] = None,
-        y_test: Optional[Union[SUPPORTED_TARGET_TYPES, spmatrix]] = None,
+        y_test: Optional[SUPPORTED_TARGET_TYPES] = None,
         feat_type: Optional[List[str]] = None,
         dataset_name: Optional[str] = None,
         only_return_configuration_space: bool = False,
@@ -587,6 +586,7 @@ def fit(
 
         # AutoSklearn does not handle sparse y for now
         y = convert_if_sparse(y)
+        y_test = convert_if_sparse(y_test) if y_test is not None else None
 
         # Get the task if it doesn't exist
         if task is None:
@@ -1012,7 +1012,7 @@ def _check_resampling_strategy(
                 'partial-cv',
                 'partial-cv-iterative-fit',
         ] and not is_split_object:
-            raise ValueError('Illegal resampling strategy: %s' % self._resampling_strategy)
+            raise ValueError(f'Illegal resampling strategy: {self._resampling_strategy}')
 
         elif is_split_object:
             TrainEvaluator.check_splitter_resampling_strategy(
@@ -1206,13 +1206,13 @@ def refit(self, X, y):
     def fit_pipeline(
         self,
         X: SUPPORTED_FEAT_TYPES,
-        y: Union[SUPPORTED_TARGET_TYPES, spmatrix],
+        y: SUPPORTED_TARGET_TYPES,
         is_classification: bool,
         config: Union[Configuration,  Dict[str, Union[str, float, int]]],
         task: Optional[int] = None,
         dataset_name: Optional[str] = None,
         X_test: Optional[SUPPORTED_FEAT_TYPES] = None,
-        y_test: Optional[Union[SUPPORTED_TARGET_TYPES, spmatrix]] = None,
+        y_test: Optional[SUPPORTED_TARGET_TYPES] = None,
         feat_type: Optional[List[str]] = None,
         **kwargs: Dict,
     ) -> Tuple[Optional[BasePipeline], RunInfo, RunValue]:
@@ -1263,6 +1263,7 @@ def fit_pipeline(
         """
         # AutoSklearn does not handle sparse y for now
         y = convert_if_sparse(y)
+        y_test = convert_if_sparse(y_test) if y_test is not None else None
 
         # Get the task if it doesn't exist
         if task is None:
@@ -1903,10 +1904,10 @@ def _supports_task_type(cls, task_type: str) -> bool:
     def fit(
         self,
         X: SUPPORTED_FEAT_TYPES,
-        y: Union[SUPPORTED_TARGET_TYPES, spmatrix],
+        y: SUPPORTED_TARGET_TYPES,
         X_test: Optional[SUPPORTED_FEAT_TYPES] = None,
-        y_test: Optional[Union[SUPPORTED_TARGET_TYPES, spmatrix]] = None,
-        feat_type: Optional[List[bool]] = None,
+        y_test: Optional[SUPPORTED_TARGET_TYPES] = None,
+        feat_type: Optional[List[str]] = None,
         dataset_name: Optional[str] = None,
         only_return_configuration_space: bool = False,
         load_models: bool = True,
@@ -1925,11 +1926,11 @@ def fit(
     def fit_pipeline(
         self,
         X: SUPPORTED_FEAT_TYPES,
-        y: Union[SUPPORTED_TARGET_TYPES, spmatrix],
+        y: SUPPORTED_TARGET_TYPES,
         config: Union[Configuration,  Dict[str, Union[str, float, int]]],
         dataset_name: Optional[str] = None,
         X_test: Optional[SUPPORTED_FEAT_TYPES] = None,
-        y_test: Optional[Union[SUPPORTED_TARGET_TYPES, spmatrix]] = None,
+        y_test: Optional[SUPPORTED_TARGET_TYPES] = None,
         feat_type: Optional[List[str]] = None,
         **kwargs,
     ) -> Tuple[Optional[BasePipeline], RunInfo, RunValue]:
@@ -1980,10 +1981,10 @@ def _supports_task_type(cls, task_type: str) -> bool:
     def fit(
         self,
         X: SUPPORTED_FEAT_TYPES,
-        y: Union[SUPPORTED_TARGET_TYPES, spmatrix],
+        y: SUPPORTED_TARGET_TYPES,
         X_test: Optional[SUPPORTED_FEAT_TYPES] = None,
-        y_test: Optional[Union[SUPPORTED_TARGET_TYPES, spmatrix]] = None,
-        feat_type: Optional[List[bool]] = None,
+        y_test: Optional[SUPPORTED_TARGET_TYPES] = None,
+        feat_type: Optional[List[str]] = None,
         dataset_name: Optional[str] = None,
         only_return_configuration_space: bool = False,
         load_models: bool = True,
@@ -2002,11 +2003,11 @@ def fit(
     def fit_pipeline(
         self,
         X: SUPPORTED_FEAT_TYPES,
-        y: Union[SUPPORTED_TARGET_TYPES, spmatrix],
+        y: SUPPORTED_TARGET_TYPES,
         config: Union[Configuration,  Dict[str, Union[str, float, int]]],
         dataset_name: Optional[str] = None,
         X_test: Optional[SUPPORTED_FEAT_TYPES] = None,
-        y_test: Optional[Union[SUPPORTED_TARGET_TYPES, spmatrix]] = None,
+        y_test: Optional[SUPPORTED_TARGET_TYPES] = None,
         feat_type: Optional[List[str]] = None,
         **kwargs: Dict,
     ) -> Tuple[Optional[BasePipeline], RunInfo, RunValue]:

autosklearn/data/validation.py

@@ -15,7 +15,7 @@
 
 
 def convert_if_sparse(
-    y: typing.Union[SUPPORTED_TARGET_TYPES, spmatrix]
+    y: SUPPORTED_TARGET_TYPES
 ) -> SUPPORTED_TARGET_TYPES:
     """If the labels `y` are sparse, it will convert it to its dense representation