Adapt code and requirements for latest sklearn

examples/example_1.py

@@ -60,7 +60,6 @@ def create_plot(scores):
         verbose=10,
         scoring=["r2", "neg_mean_squared_error"],
         return_estimator=True,
-        fit_params={"cleanup": True},
     )
 
     create_plot(scores)

examples/example_2.py

@@ -50,7 +50,6 @@
         verbose=10,
         scoring=["r2", "neg_mean_squared_error"],
         return_estimator=True,
-        fit_params={"cleanup": True},
     )
 
     log_scores(scores)

examples/example_3.py

@@ -61,7 +61,6 @@
         verbose=10,
         scoring=["r2", "neg_mean_squared_error"],
         return_estimator=True,
-        fit_params={"cleanup": True},
     )
 
     log_scores(scores)

examples/example_4.py

@@ -50,8 +50,8 @@
             elitist_ratio=0.2,
             random_state=random_state,
             n_jobs=1,
-            mutation=suprb.optimizer.solution.ga.mutation.BitFlips(mutation_rate=0.1),
-            crossover=suprb.optimizer.solution.ga.crossover.NPoint(crossover_rate=0.9, n=2),
+            mutation=suprb.optimizer.solution.ga.mutation.BitFlips(),
+            crossover=suprb.optimizer.solution.ga.crossover.NPoint(n=2),
             selection=suprb.optimizer.solution.ga.selection.Tournament(k=6),
             init=suprb.solution.initialization.RandomInit(
                 mixing=suprb.solution.mixing_model.ErrorExperienceHeuristic(),
@@ -71,7 +71,6 @@
         verbose=10,
         scoring=["r2", "neg_mean_squared_error"],
         return_estimator=True,
-        fit_params={"cleanup": True},
     )
 
     log_scores(scores)

requirements.txt

@@ -1,12 +1,5 @@
-numpy~=1.22.4
-scipy~=1.7.1
-matplotlib~=3.4.3
-scikit-learn~=1.0.1
-scikit-optimize~=0.9
-pandas~=1.3.4
-mlflow~=1.21.0
-hypothesis~=6.24.2
-joblib~=1.1.0
-tqdm~=4.62.3
-pytest~=6.2.5
-protobuf~=3.20.0
+matplotlib==3.10.3
+pandas==2.3.0
+pytest==8.4.1
+scikit-learn==1.7.0
+tqdm==4.67.1

suprb/base.py

@@ -51,7 +51,7 @@ def _more_str_attributes(self) -> dict:
         return {}
 
 
-class BaseRegressor(BaseEstimator, RegressorMixin, metaclass=ABCMeta):
+class BaseRegressor(RegressorMixin, BaseEstimator, metaclass=ABCMeta):
     """A base (composite) Regressor."""
 
     is_fitted_: bool

suprb/suprb.py

@@ -4,7 +4,8 @@
 import numpy as np
 from sklearn import clone
 from sklearn.utils import check_X_y
-from sklearn.utils.validation import check_is_fitted, check_array
+from sklearn.utils.validation import check_is_fitted, check_array, validate_data
+
 
 from .base import BaseRegressor
 from .exceptions import PopulationEmptyWarning
@@ -22,6 +23,18 @@
 
 
 class SupRB(BaseRegressor):
+    def __sklearn_tags__(self):
+        tags = super().__sklearn_tags__()
+        tags.target_tags.single_output = False
+        tags.non_deterministic = True
+        return tags
+
+    def _more_tags(self):
+        # additional or override tags
+        return {
+            # 'some_tag': True,
+        }
+
     """The multi-solution batch learning LCS developed by the Organic Computing group at Universität Augsburg.
 
     Parameters
@@ -150,8 +163,7 @@ def fit(self, X: np.ndarray, y: np.ndarray, cleanup=False):
         self.elitist_.complexity_ = 99999
 
         # Check that x and y have correct shape
-        X, y = check_X_y(X, y, dtype="float64", y_numeric=True)
-        y = check_array(y, ensure_2d=False, dtype="float64")
+        X, y = validate_data(self, X, y, ensure_2d=True)
 
         # Init sklearn interface
         self.n_features_in_ = X.shape[1]
@@ -273,11 +285,9 @@ def _compose_solution(self, X: np.ndarray, y: np.ndarray):
         # Optimize
         self.solution_composition_.optimize(X, y)
 
-    def predict(self, X: np.ndarray):
-        # Check is fit had been called
-        check_is_fitted(self, ["is_fitted_"])
-        # Input validation
-        X = check_array(X)
+    def predict(self, X):
+        check_is_fitted(self)
+        X = validate_data(self, X, ensure_2d=True, reset=False)
 
         if hasattr(self, "is_error_") and self.is_error_:
             return [0] * len(X)

tests/test_solution.py

@@ -1,6 +1,6 @@
 import unittest
 
-from sklearn.utils.estimator_checks import check_estimator
+from sklearn.utils.estimator_checks import check_estimator, _regression_dataset
 
 import suprb
 import suprb.logging.stdout
@@ -18,55 +18,69 @@ class TestSolution(unittest.TestCase):
 
     def test_check_ga(self):
         estimator = suprb.SupRB(
-            n_iter=1,
+            n_iter=4,
             rule_discovery=ES1xLambda(n_iter=4, lmbda=1, delay=2),
             solution_composition=GeneticAlgorithm(n_iter=2, population_size=2),
             logger=suprb.logging.stdout.StdoutLogger(),
             verbose=10,
         )
 
+        X, y = _regression_dataset()
+        estimator.fit(X, y)
+
         check_estimator(estimator)
 
     def test_check_saga1(self):
         estimator = suprb.SupRB(
-            n_iter=1,
+            n_iter=4,
             rule_discovery=ES1xLambda(n_iter=4, lmbda=1, delay=2),
             solution_composition=SelfAdaptingGeneticAlgorithm1(n_iter=2, population_size=2),
             logger=suprb.logging.stdout.StdoutLogger(),
             verbose=10,
         )
+        X, y = _regression_dataset()
+        estimator.fit(X, y)
 
         check_estimator(estimator)
 
     def test_check_saga2(self):
         estimator = suprb.SupRB(
-            n_iter=1,
+            n_iter=4,
             rule_discovery=ES1xLambda(n_iter=4, lmbda=1, delay=2),
             solution_composition=SelfAdaptingGeneticAlgorithm2(n_iter=2, population_size=2),
             logger=suprb.logging.stdout.StdoutLogger(),
             verbose=10,
         )
 
+        X, y = _regression_dataset()
+        estimator.fit(X, y)
+
         check_estimator(estimator)
 
     def test_check_saga3(self):
         estimator = suprb.SupRB(
-            n_iter=1,
+            n_iter=4,
             rule_discovery=ES1xLambda(n_iter=4, lmbda=1, delay=2),
             solution_composition=SelfAdaptingGeneticAlgorithm3(n_iter=2, population_size=2),
             logger=suprb.logging.stdout.StdoutLogger(),
             verbose=10,
         )
 
+        X, y = _regression_dataset()
+        estimator.fit(X, y)
+
         check_estimator(estimator)
 
     def test_check_sas(self):
         estimator = suprb.SupRB(
-            n_iter=1,
+            n_iter=4,
             rule_discovery=ES1xLambda(n_iter=4, lmbda=1, delay=2),
             solution_composition=SasGeneticAlgorithm(n_iter=2, initial_population_size=2),
             logger=suprb.logging.stdout.StdoutLogger(),
             verbose=10,
         )
 
+        X, y = _regression_dataset()
+        estimator.fit(X, y)
+
         check_estimator(estimator)

tests/test_suprb.py

@@ -1,7 +1,7 @@
 import unittest
 import numpy as np
 
-from sklearn.utils.estimator_checks import check_estimator
+from sklearn.utils.estimator_checks import check_estimator, _regression_dataset
 
 import suprb
 import suprb.logging.stdout
@@ -35,13 +35,16 @@ def test_check_estimator(self):
 
         # Low n_iter for speed. Still takes forever though.
         estimator = suprb.SupRB(
-            n_iter=1,
+            n_iter=4,
             rule_discovery=ES1xLambda(n_iter=4, lmbda=1, delay=2),
             solution_composition=suprb.optimizer.solution.ga.GeneticAlgorithm(n_iter=2, population_size=2),
             logger=suprb.logging.stdout.StdoutLogger(),
             verbose=10,
         )
 
+        X, y = _regression_dataset()
+        estimator.fit(X, y)
+
         check_estimator(estimator)
 
     def test_early_stopping(self):