Merge pull request #211 from mandjevant/2025Update

Sklearn 1.5 & 1.6 support. Various improvements

Author: mandjevant

.github/workflows/tests.yml

@@ -10,7 +10,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest]
-        python-version: ['3.9', '3.10', '3.11']
+        python-version: ['3.11', '3.12', '3.13']
 
     steps:
     - uses: actions/checkout@v2

.gitignore

@@ -36,3 +36,4 @@ nosetests.xml
 
 .idea
 notebooks/.ipynb_checkpoints
+/venv

hpsklearn/components/__init__.py

@@ -147,7 +147,9 @@
     lightgbm_regression
 
 from .feature_extraction import \
-    tfidf
+    tfidf_vectorizer, \
+    hashing_vectorizer, \
+    count_vectorizer
 
 from .decomposition import pca
 
@@ -253,7 +255,11 @@ def any_text_preprocessing(name):
     """
     Generic pre-processing appropriate for text data
     """
-    return hp.choice(name, [[tfidf(name + '.tfidf')]])
+    return hp.choice(name, [
+        [tfidf_vectorizer(name + ".tfidf")],
+        [hashing_vectorizer(name + ".hashing")],
+        [count_vectorizer(name + ".count")],
+    ])
 
 
 # Legacy any pre-processing as proposed in #137
@@ -423,7 +429,9 @@ def all_preprocessing(name):
         [polynomial_features(name + ".polynomial_features")],
         [spline_transformer(name + ".spline_transformer")],
         [k_bins_discretizer(name + ".k_bins_discretizer")],
-        [tfidf(name + ".tfidf")],
+        [tfidf_vectorizer(name + ".tfidf")],
+        [hashing_vectorizer(name + ".hashing")],
+        [count_vectorizer(name + ".count")],
         [pca(name + ".pca")],
         [ts_lagselector(name + ".ts_lagselector")],
         [colkmeans(name + ".colkmeans")],

hpsklearn/components/cluster/_kmeans.py

@@ -44,7 +44,8 @@ def _kmeans_hp_space(
         n_clusters: typing.Union[int, Apply] = None,
         init: typing.Union[str, callable, npt.ArrayLike, Apply] = None,
         verbose: int = 0,
-        random_state=None
+        random_state=None,
+        **kwargs
 ):
     """
     Hyper parameter search space for
@@ -55,7 +56,8 @@ def _kmeans_hp_space(
         n_clusters=_kmeans_n_clusters(name_func("n_clusters")) if n_clusters is None else n_clusters,
         init=_kmeans_init(name_func("init")) if init is None else init,
         verbose=verbose,
-        random_state=_kmeans_random_state(name_func("random_state")) if random_state is None else random_state
+        random_state=_kmeans_random_state(name_func("random_state")) if random_state is None else random_state,
+        **kwargs
     )
     return hp_space
 

hpsklearn/components/compose/_target.py

@@ -13,7 +13,8 @@ def transformed_target_regressor(name: str,
                                  transformer: object = None,
                                  func: callable = None,
                                  inverse_func: callable = None,
-                                 check_inverse: bool = True):
+                                 check_inverse: bool = True,
+                                 **kwargs):
     """
     Return a pyll graph with hyperparameters that will construct
     a sklearn.compose.TransformedTargetRegressor model.
@@ -36,6 +37,7 @@ def _name(msg):
         transformer=transformer,
         func=func,
         inverse_func=inverse_func,
-        check_inverse=check_inverse
+        check_inverse=check_inverse,
+        **kwargs
     )
     return scope.sklearn_TransformedTargetRegressor(**hp_space)

hpsklearn/components/covariance/_elliptic_envelope.py

@@ -16,7 +16,8 @@ def elliptic_envelope(name: str,
                       assume_centered: bool = False,
                       support_fraction: typing.Union[float, Apply] = None,
                       contamination: typing.Union[float, Apply] = 0.1,
-                      random_state=None):
+                      random_state=None,
+                      **kwargs):
     """
     Return a pyll graph with hyperparameters that will construct
     a sklearn.covariance.EllipticEnvelope model.
@@ -39,6 +40,7 @@ def _name(msg):
         support_fraction=hp.uniform(_name("support_fraction"), 0.05, 0.95)
         if support_fraction is None else support_fraction,
         contamination=hp.uniform(_name("contamination"), 0.0, 0.3) if contamination is None else contamination,
-        random_state=hp.randint(_name("random_state"), 5) if random_state is None else random_state
+        random_state=hp.randint(_name("random_state"), 5) if random_state is None else random_state,
+        **kwargs
     )
     return scope.sklearn_EllipticEnvelope(**hp_space)

hpsklearn/components/cross_decomposition/_pls.py

@@ -51,7 +51,8 @@ def _pls_hp_space(
         scale: bool = True,
         max_iter: typing.Union[int, Apply] = None,
         tol: typing.Union[float, Apply] = None,
-        copy: bool = True
+        copy: bool = True,
+        **kwargs
 ):
     """
     Hyper parameter search space for
@@ -64,7 +65,8 @@ def _pls_hp_space(
         scale=scale,
         max_iter=_pls_max_iter(name_func("max_iter")) if max_iter is None else max_iter,
         tol=_pls_tol(name_func("tol")) if tol is None else tol,
-        copy=copy
+        copy=copy,
+        **kwargs
     )
     return hp_space
 

hpsklearn/components/discriminant_analysis.py

@@ -30,7 +30,8 @@ def _discriminant_analysis_hp_space(
         name_func,
         priors: npt.ArrayLike = None,
         store_covariance: bool = False,
-        tol: float = None
+        tol: float = None,
+        **kwargs
 ):
     """
     Common hyper parameter search space
@@ -40,7 +41,8 @@ def _discriminant_analysis_hp_space(
     hp_space = dict(
         priors=priors,
         store_covariance=store_covariance,
-        tol=_discriminant_analysis_tol(name_func("tol")) if tol is None else tol
+        tol=_discriminant_analysis_tol(name_func("tol")) if tol is None else tol,
+        **kwargs
     )
     return hp_space
 

hpsklearn/components/dummy.py

@@ -26,7 +26,8 @@ def sklearn_DummyRegressor(*args, **kwargs):
 def dummy_classifier(name: str,
                      strategy: typing.Union[str, Apply] = None,
                      random_state=None,
-                     constant: typing.Union[int, str, npt.ArrayLike] = None):
+                     constant: typing.Union[int, str, npt.ArrayLike] = None,
+                     **kwargs):
     """
     Return a pyll graph with hyperparameters that will construct
     a sklearn.dummy.DummyClassifier model.
@@ -45,7 +46,8 @@ def _name(msg):
         strategy=hp.choice(_name("strategy"), ["stratified", "most_frequent", "prior", "uniform"])
         if strategy is None else strategy,
         random_state=hp.randint(_name("random_state"), 5) if random_state is None else random_state,
-        constant=constant
+        constant=constant,
+        **kwargs
     )
     return scope.sklearn_DummyClassifier(**hp_space)
 
@@ -60,7 +62,8 @@ def _name(msg):
 def dummy_regressor(name: str,
                     strategy: typing.Union[str, Apply] = None,
                     constant: typing.Union[int, str, npt.ArrayLike] = None,
-                    quantile: float = None):
+                    quantile: float = None,
+                    **kwargs):
     """
     Return a pyll graph with hyperparameters that will construct
     a sklearn.dummy.DummyRegressor model.
@@ -78,6 +81,7 @@ def _name(msg):
     hp_space = dict(
         strategy=hp.choice(_name("strategy"), ["mean", "median"]) if strategy is None else strategy,
         constant=constant,
-        quantile=quantile
+        quantile=quantile,
+        **kwargs
     )
     return scope.sklearn_DummyRegressor(**hp_space)

hpsklearn/components/ensemble/_bagging.py

@@ -93,6 +93,7 @@ def _bagging_hp_space(
         n_jobs: int = 1,
         random_state=None,
         verbose: int = False,
+        **kwargs,
 ):
     """
     Hyper parameter search space for
@@ -112,6 +113,7 @@ def _bagging_hp_space(
         n_jobs=n_jobs,
         random_state=_bagging_random_state(name_func("random_state")) if random_state is None else random_state,
         verbose=verbose,
+        **kwargs
     )
     return hp_space