Remove restriction for scikit-learn dependency

pyproject.toml

@@ -37,7 +37,7 @@ dependencies = [
     "qiskit-ibm-runtime>=0.18.0",
     "qiskit-machine-learning>=0.7.0",
     "scipy>=1.8.0",
-    "scikit-learn>=1.2.0,<1.4.2",
+    "scikit-learn>=1.2.0",
     "tqdm>=4.1.0",
 ]
 requires-python = ">=3.9,<3.13"

src/squlearn/kernel/qgpr.py

@@ -1,13 +1,24 @@
 """Quantum Gaussian Process Regression"""
 
 import warnings
+from packaging import version
 
 import numpy as np
 from typing import Optional, Union
 from scipy.linalg import cholesky, cho_solve
 from sklearn.base import BaseEstimator, RegressorMixin
 from sklearn.preprocessing._data import _handle_zeros_in_scale
 
+from sklearn import __version__
+
+if version.parse(__version__) >= version.parse("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+
+    def validate_data(self, *args, **kwargs):
+        return self._validate_data(*args, **kwargs)
+
+
 from .lowlevel_kernel.kernel_matrix_base import KernelMatrixBase
 from .lowlevel_kernel.regularization import regularize_full_kernel
 
@@ -123,7 +134,8 @@ def fit(self, X, y):
             Returns an instance of self.
         """
 
-        X, y = self._validate_data(
+        X, y = validate_data(
+            self,
             X,
             y,
             multi_output=True,
@@ -201,7 +213,7 @@ def predict(self, X: np.ndarray, return_std=False, return_cov=False):
                 Only returned when `return_cov` is True.
         """
 
-        X = self._validate_data(X, ensure_2d=True, dtype="numeric", reset=False)
+        X = validate_data(self, X, ensure_2d=True, dtype="numeric", reset=False)
 
         if self.K_train is None:
             raise ValueError("There is no training data. Please call the fit method first.")

src/squlearn/kernel/qkrr.py

@@ -1,9 +1,20 @@
 """Quantum Kernel Ridge Regression"""
 
+from packaging import version
+
 import scipy
 import numpy as np
 from typing import Optional, Union
 from sklearn.base import BaseEstimator, RegressorMixin
+from sklearn import __version__
+
+if version.parse(__version__) >= version.parse("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+
+    def validate_data(self, *args, **kwargs):
+        return self._validate_data(*args, **kwargs)
+
 
 from .lowlevel_kernel.kernel_matrix_base import KernelMatrixBase
 from .lowlevel_kernel.regularization import thresholding_regularization, tikhonov_regularization
@@ -122,8 +133,8 @@ def fit(self, X, y):
             Returns an instance of self.
         """
 
-        X, y = self._validate_data(
-            X, y, accept_sparse=("csr", "csc"), multi_output=True, y_numeric=True
+        X, y = validate_data(
+            self, X, y, accept_sparse=("csr", "csc"), multi_output=True, y_numeric=True
         )
 
         self.X_train = X
@@ -172,7 +183,7 @@ def predict(self, X: np.ndarray) -> np.ndarray:
         if self.k_train is None:
             raise ValueError("The fit() method has to be called beforehand.")
 
-        X = self._validate_data(X, accept_sparse=("csr", "csc"), reset=False)
+        X = validate_data(self, X, accept_sparse=("csr", "csc"), reset=False)
 
         if isinstance(self._quantum_kernel, str):
             if self._quantum_kernel == "precomputed":

src/squlearn/qnn/base_qnn.py

@@ -3,12 +3,22 @@
 from __future__ import annotations
 
 from abc import abstractmethod, ABC
+from packaging import version
 from typing import Callable, Union
 from warnings import warn
 
 import numpy as np
 from sklearn.base import BaseEstimator
 from sklearn.utils import column_or_1d
+from sklearn import __version__
+
+if version.parse(__version__) >= version.parse("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+
+    def validate_data(self, *args, **kwargs):
+        return self._validate_data(*args, **kwargs)
+
 
 from ..observables.observable_base import ObservableBase
 from ..encoding_circuit.encoding_circuit_base import EncodingCircuitBase
@@ -339,7 +349,8 @@ def _initialize_lowlevel_qnn(self):
         )
 
     def _validate_input(self, X, y, incremental, reset):
-        X, y = self._validate_data(
+        X, y = validate_data(
+            self,
             X,
             y,
             accept_sparse=["csr", "csc"],

src/squlearn/qnn/qnnc.py

@@ -1,11 +1,22 @@
 """QNNClassifier Implemenation"""
 
+from packaging import version
 from typing import Callable, Union
 import sys
 
 import numpy as np
 from sklearn.base import ClassifierMixin
 from sklearn.preprocessing import LabelBinarizer
+from sklearn import __version__
+
+if version.parse(__version__) >= version.parse("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+
+    def validate_data(self, *args, **kwargs):
+        return self._validate_data(*args, **kwargs)
+
+
 from tqdm import tqdm
 
 from .base_qnn import BaseQNN
@@ -155,7 +166,7 @@ def predict(self, X: np.ndarray) -> np.ndarray:
         Returns:
             np.ndarray : The predicted values.
         """
-        X = self._validate_data(X, accept_sparse=["csr", "csc"], reset=False)
+        X = validate_data(self, X, accept_sparse=["csr", "csc"], reset=False)
 
         if not self._is_fitted and not self.pretrained:
             raise RuntimeError("The model is not fitted.")

src/squlearn/qnn/qnnr.py

@@ -1,11 +1,22 @@
 """QNNRegressor Implemenation"""
 
+from packaging import version
 from typing import Callable, Union
 from warnings import warn
 import sys
 
 import numpy as np
 from sklearn.base import RegressorMixin
+from sklearn import __version__
+
+if version.parse(__version__) >= version.parse("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+
+    def validate_data(self, *args, **kwargs):
+        return self._validate_data(*args, **kwargs)
+
+
 from tqdm import tqdm
 
 from .base_qnn import BaseQNN
@@ -205,7 +216,7 @@ def predict(self, X: np.ndarray) -> np.ndarray:
         Returns:
             np.ndarray : The predicted values.
         """
-        X = self._validate_data(X, accept_sparse=["csr", "csc"], reset=False)
+        X = validate_data(self, X, accept_sparse=["csr", "csc"], reset=False)
 
         if not self._is_fitted and not self.pretrained:
             warn("The model is not fitted.")

src/squlearn/qrc/base_qrc.py

@@ -1,9 +1,20 @@
 import numpy as np
 from typing import Union, List
 from abc import abstractmethod, ABC
+from packaging import version
 
 from sklearn.base import BaseEstimator
 from sklearn.utils import column_or_1d
+from sklearn import __version__
+
+if version.parse(__version__) >= version.parse("1.6"):
+    from sklearn.utils.validation import validate_data
+else:
+
+    def validate_data(self, *args, **kwargs):
+        return self._validate_data(*args, **kwargs)
+
+
 from qiskit.quantum_info.random import random_pauli_list
 
 from ..observables.observable_base import ObservableBase
@@ -118,7 +129,7 @@ def predict(self, X) -> np.ndarray:
         Returns:
             np.ndarray : The predicted values.
         """
-        X = self._validate_data(X, accept_sparse=["csr", "csc"], reset=False)
+        X = validate_data(self, X, accept_sparse=["csr", "csc"], reset=False)
         X_qnn = self._qnn.evaluate(X, self.param_ini, self.param_op_ini, "f")["f"]
         return self._ml_model.predict(X_qnn)
 
@@ -278,7 +289,8 @@ def set_params(self, **params) -> "BaseQRC":
         return self
 
     def _validate_input(self, X, y, incremental, reset):
-        X, y = self._validate_data(
+        X, y = validate_data(
+            self,
             X,
             y,
             accept_sparse=["csr", "csc"],