skfolio 0.6.0__py3-none-any.whl → 0.8.0__py3-none-any.whl

skfolio/optimization/cluster/_nco.py

@@ -2,7 +2,7 @@
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 # Implementation derived from:
 # Riskfolio-Lib, Copyright (c) 2020-2023, Dany Cajas, Licensed under BSD 3 clause.
 # scikit-learn, Copyright (c) 2007-2010 David Cournapeau, Fabian Pedregosa, Olivier
@@ -18,6 +18,7 @@ import sklearn.base as skb
 import sklearn.model_selection as sks
 import sklearn.utils.metadata_routing as skm
 import sklearn.utils.parallel as skp
+import sklearn.utils.validation as skv
 
 import skfolio.typing as skt
 from skfolio.cluster import HierarchicalClustering
@@ -311,9 +312,9 @@ class NestedClustersOptimization(BaseOptimization):
                 w[cluster_ids] = fitted_inner_estimator.weights_
             inner_weights.append(w)
         inner_weights = np.array(inner_weights)
-        assert not any(
-            fitted_inner_estimators
-        ), "fitted_inner_estimator iterator must be empty"
+        assert not any(fitted_inner_estimators), (
+            "fitted_inner_estimator iterator must be empty"
+        )
 
         # Outer cluster weights
         # To train the outer-estimator using the most data as possible, we use
@@ -355,10 +356,10 @@ class NestedClustersOptimization(BaseOptimization):
         # We validate and convert to numpy array only after inner-estimator fitting to
         # keep the assets names in case they are used in the estimator.
         if y is not None:
-            X, y = self._validate_data(X, y)
+            X, y = skv.validate_data(self, X, y)
             y_pred = y[test_indices]
         else:
-            X = self._validate_data(X)
+            X = skv.validate_data(self, X)
             y_pred = None
 
         X_pred = []
@@ -379,9 +380,9 @@ class NestedClustersOptimization(BaseOptimization):
             X_pred.append(np.asarray(pred))
         X_pred = np.array(X_pred).T
         if cv_predictions is None:
-            assert not any(
-                fitted_inner_estimators
-            ), "fitted_inner_estimator iterator must be empty"
+            assert not any(fitted_inner_estimators), (
+                "fitted_inner_estimator iterator must be empty"
+            )
         else:
             assert not any(cv_predictions), "cv_predictions iterator must be empty"
 

skfolio/optimization/cluster/hierarchical/__init__.py

@@ -1,3 +1,5 @@
+"""Hierarchical Optimization module."""
+
 from skfolio.optimization.cluster.hierarchical._base import (
     BaseHierarchicalOptimization,
 )
@@ -8,6 +10,6 @@ from skfolio.optimization.cluster.hierarchical._hrp import HierarchicalRiskParit
 
 __all__ = [
     "BaseHierarchicalOptimization",
-    "HierarchicalRiskParity",
     "HierarchicalEqualRiskContribution",
+    "HierarchicalRiskParity",
 ]

skfolio/optimization/cluster/hierarchical/_base.py

@@ -2,7 +2,7 @@
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 # Implementation derived from:
 # Riskfolio-Lib, Copyright (c) 2020-2023, Dany Cajas, Licensed under BSD 3 clause.
 # scikit-learn, Copyright (c) 2007-2010 David Cournapeau, Fabian Pedregosa, Olivier
@@ -349,7 +349,6 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
         max_weights : ndarray of shape (n_assets,)
             The weight upper bound 1D array.
         """
-
         if self.min_weights is None:
             min_weights = np.zeros(n_assets)
         else:

skfolio/optimization/cluster/hierarchical/_herc.py

@@ -2,7 +2,7 @@
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 # Weight constraints is a novel implementation, see docstring for more details.
 
 import numpy as np
@@ -10,6 +10,7 @@ import numpy.typing as npt
 import pandas as pd
 import scipy.cluster.hierarchy as sch
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 import skfolio.typing as skt
 from skfolio.cluster import HierarchicalClustering
@@ -346,7 +347,7 @@ class HierarchicalEqualRiskContribution(BaseHierarchicalOptimization):
         if self.risk_measure in [ExtraRiskMeasure.SKEW, ExtraRiskMeasure.KURTOSIS]:
             # Because Skew and Kurtosis can take negative values
             raise ValueError(
-                f"risk_measure {self.risk_measure} currently not supported" f"in HERC"
+                f"risk_measure {self.risk_measure} currently not supported in HERC"
             )
 
         self.prior_estimator_ = check_estimator(
@@ -391,7 +392,7 @@ class HierarchicalEqualRiskContribution(BaseHierarchicalOptimization):
         labels = self.hierarchical_clustering_estimator_.labels_
         linkage_matrix = self.hierarchical_clustering_estimator_.linkage_matrix_
 
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         n_assets = X.shape[1]
 
         min_weights, max_weights = self._convert_weights_bounds(n_assets=n_assets)

skfolio/optimization/cluster/hierarchical/_hrp.py

@@ -2,7 +2,7 @@
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 # The risk measure generalization and constraint features are derived
 # from Riskfolio-Lib, Copyright (c) 2020-2023, Dany Cajas, Licensed under BSD 3 clause.
 
@@ -11,6 +11,7 @@ import numpy.typing as npt
 import pandas as pd
 import scipy.cluster.hierarchy as sch
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 import skfolio.typing as skt
 from skfolio.cluster import HierarchicalClustering
@@ -298,7 +299,7 @@ class HierarchicalRiskParity(BaseHierarchicalOptimization):
         if self.risk_measure in [ExtraRiskMeasure.SKEW, ExtraRiskMeasure.KURTOSIS]:
             # Because Skew and Kurtosis can take negative values
             raise ValueError(
-                f"risk_measure {self.risk_measure} currently not supported" f"in HRP"
+                f"risk_measure {self.risk_measure} currently not supported in HRP"
             )
 
         self.prior_estimator_ = check_estimator(
@@ -339,7 +340,7 @@ class HierarchicalRiskParity(BaseHierarchicalOptimization):
             X=distance, y=None, **routed_params.hierarchical_clustering_estimator.fit
         )
 
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         n_assets = X.shape[1]
 
         min_weights, max_weights = self._convert_weights_bounds(n_assets=n_assets)

skfolio/optimization/convex/__init__.py

@@ -1,3 +1,5 @@
+"""Convex Optimization module."""
+
 from skfolio.optimization.convex._base import ConvexOptimization, ObjectiveFunction
 from skfolio.optimization.convex._distributionally_robust import (
     DistributionallyRobustCVaR,
@@ -7,10 +9,10 @@ from skfolio.optimization.convex._mean_risk import MeanRisk
 from skfolio.optimization.convex._risk_budgeting import RiskBudgeting
 
 __all__ = [
-    "ObjectiveFunction",
     "ConvexOptimization",
-    "MeanRisk",
-    "RiskBudgeting",
     "DistributionallyRobustCVaR",
     "MaximumDiversification",
+    "MeanRisk",
+    "ObjectiveFunction",
+    "RiskBudgeting",
 ]

skfolio/optimization/convex/_base.py

@@ -2,7 +2,7 @@
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 # The optimization features are derived
 # from Riskfolio-Lib, Copyright (c) 2020-2023, Dany Cajas, Licensed under BSD 3 clause.
 
@@ -144,7 +144,7 @@ class ConvexOptimization(BaseOptimization, ABC):
         all weights). `None` means no budget constraints.
         The default value is `1.0` (fully invested portfolio).
 
-        Examples:
+        For example:
 
              * `budget = 1` --> fully invested portfolio.
              * `budget = 0` --> market neutral portfolio.
@@ -329,7 +329,7 @@ class ConvexOptimization(BaseOptimization, ABC):
         `groups` if the input `X` of the `fit` method is a DataFrame with these
         assets names in columns.
 
-        Examples:
+        For example:
 
             * "SPX >= 0.10" --> SPX weight must be greater than 10% (note that you can also use `min_weights`)
             * "SX5E + TLT >= 0.2" --> the sum of SX5E and TLT weights must be greater than 20%
@@ -343,7 +343,7 @@ class ConvexOptimization(BaseOptimization, ABC):
         (asset name/asset groups) and the input `X` of the `fit` method must be a
         DataFrame with the assets names in columns.
 
-        Examples:
+        For example:
 
             * groups = {"SX5E": ["Equity", "Europe"], "SPX": ["Equity", "US"], "TLT": ["Bond", "US"]}
             * groups = [["Equity", "Equity", "Bond"], ["Europe", "US", "US"]]
@@ -657,7 +657,7 @@ class ConvexOptimization(BaseOptimization, ABC):
         )
 
     def _clear_models_cache(self):
-        """CLear the cache of CVX models"""
+        """CLear the cache of CVX models."""
         self._cvx_cache = {}
 
     def _get_weight_constraints(
@@ -989,7 +989,7 @@ class ConvexOptimization(BaseOptimization, ABC):
             self._scale_constraints = cp.Constant(self.scale_constraints)
 
     def _get_custom_objective(self, w: cp.Variable) -> cp.Expression:
-        """Returns the CVXPY expression evaluated by calling the `add_objective`
+        """Return the CVXPY expression evaluated by calling the `add_objective`
         function if provided, otherwise returns the CVXPY constant `0`.
 
         Parameters
@@ -1010,7 +1010,7 @@ class ConvexOptimization(BaseOptimization, ABC):
         )
 
     def _get_custom_constraints(self, w: cp.Variable) -> list[cp.Expression]:
-        """Returns the list of CVXPY expressions evaluated by calling the
+        """Return the list of CVXPY expressions evaluated by calling the
         `add_constraint`s function if provided, otherwise returns an empty list.
 
         Parameters
@@ -1037,7 +1037,7 @@ class ConvexOptimization(BaseOptimization, ABC):
     def _cvx_expected_return(
         self, prior_model: PriorModel, w: cp.Variable
     ) -> cp.Expression:
-        """Expected Return expression"""
+        """Expected Return expression."""
         if self.overwrite_expected_return is None:
             expected_return = prior_model.mu @ w
         else:
@@ -1685,7 +1685,8 @@ class ConvexOptimization(BaseOptimization, ABC):
         z2 = cp.vstack([w_reshaped, factor_reshaped])
 
         risk = covariance_uncertainty_set.k * cp.pnorm(
-            sc.linalg.sqrtm(covariance_uncertainty_set.sigma) @ (cp.vec(x) + cp.vec(y)),
+            sc.linalg.sqrtm(covariance_uncertainty_set.sigma)
+            @ (cp.vec(x, order="F") + cp.vec(y, order="F")),
             2,
         ) + cp.trace(prior_model.covariance @ (x + y))
         # semi-definite positive constraints

skfolio/optimization/convex/_distributionally_robust.py

@@ -2,12 +2,13 @@
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import cvxpy as cp
 import numpy as np
 import numpy.typing as npt
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 import skfolio.typing as skt
 from skfolio.measures import RiskMeasure
@@ -93,7 +94,7 @@ class DistributionallyRobustCVaR(ConvexOptimization):
         all weights). `None` means no budget constraints.
         The default value is `1.0` (fully invested portfolio).
 
-        Examples:
+        For example:
 
              * `budget = 1` --> fully invested portfolio.
              * `budget = 0` --> market neutral portfolio.
@@ -133,7 +134,7 @@ class DistributionallyRobustCVaR(ConvexOptimization):
         `groups` if the input `X` of the `fit` method is a DataFrame with these
         assets names in columns.
 
-        Examples:
+        For example:
 
             * "SPX >= 0.10" --> SPX weight must be greater than 10% (note that you can also use `min_weights`)
             * "SX5E + TLT >= 0.2" --> the sum of SX5E and TLT weights must be greater than 20%
@@ -147,7 +148,7 @@ class DistributionallyRobustCVaR(ConvexOptimization):
         (asset name/asset groups) and the input `X` of the `fit` method must be a
         DataFrame with the assets names in columns.
 
-        Examples:
+        For example:
 
             * groups = {"SX5E": ["Equity", "Europe"], "SPX": ["Equity", "US"], "TLT": ["Bond", "US"]}
             * groups = [["Equity", "Equity", "Bond"], ["Europe", "US", "US"]]
@@ -331,7 +332,9 @@ class DistributionallyRobustCVaR(ConvexOptimization):
         """
         routed_params = skm.process_routing(self, "fit", **fit_params)
 
-        self._check_feature_names(X, reset=True)
+        # `X` is unchanged and only `feature_names_in_` is performed
+        _ = skv.validate_data(self, X, skip_check_array=True)
+
         # Used to avoid adding multiple times similar constrains linked to identical
         # risk models
         self.prior_estimator_ = check_estimator(

skfolio/optimization/convex/_maximum_diversification.py

@@ -2,10 +2,11 @@
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import numpy as np
 import numpy.typing as npt
+import sklearn.utils.validation as skv
 
 import skfolio.typing as skt
 from skfolio.measures import RiskMeasure
@@ -76,7 +77,7 @@ class MaximumDiversification(MeanRisk):
         all weights). `None` means no budget constraints.
         The default value is `1.0` (fully invested portfolio).
 
-        Examples:
+        For example:
 
              * `budget = 1` --> fully invested portfolio.
              * `budget = 0` --> market neutral portfolio.
@@ -209,7 +210,7 @@ class MaximumDiversification(MeanRisk):
         `groups` if the input `X` of the `fit` method is a DataFrame with these
         assets names in columns.
 
-        Examples:
+        For example:
 
             * "SPX >= 0.10" --> SPX weight must be greater than 10% (note that you can also use `min_weights`)
             * "SX5E + TLT >= 0.2" --> the sum of SX5E and TLT weights must be greater than 20%
@@ -223,7 +224,7 @@ class MaximumDiversification(MeanRisk):
         (asset name/asset groups) and the input `X` of the `fit` method must be a
         DataFrame with the assets names in columns.
 
-        Examples:
+        For example:
 
             * groups = {"SX5E": ["Equity", "Europe"], "SPX": ["Equity", "US"], "TLT": ["Bond", "US"]}
             * groups = [["Equity", "Equity", "Bond"], ["Europe", "US", "US"]]
@@ -423,10 +424,11 @@ class MaximumDiversification(MeanRisk):
         self : MaximumDiversification
            Fitted estimator.
         """
-        self._check_feature_names(X, reset=True)
+        # `X` is unchanged and only `feature_names_in_` is performed
+        _ = skv.validate_data(self, X, skip_check_array=True)
 
         def func(w, obj):
-            """weighted volatilities"""
+            """Weighted volatilities."""
             covariance = obj.prior_estimator_.prior_model_.covariance
             return np.sqrt(np.diag(covariance)) @ w
 

skfolio/optimization/convex/_mean_risk.py

@@ -4,7 +4,7 @@ import warnings
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 # The optimization features are derived
 # from Riskfolio-Lib, Copyright (c) 2020-2023, Dany Cajas, Licensed under BSD 3 clause.
 import cvxpy as cp
@@ -13,6 +13,7 @@ import numpy.typing as npt
 import pandas as pd
 import sklearn as sk
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 import skfolio.typing as skt
 from skfolio.measures import RiskMeasure
@@ -193,7 +194,7 @@ class MeanRisk(ConvexOptimization):
         all weights). `None` means no budget constraints.
         The default value is `1.0` (fully invested portfolio).
 
-        Examples:
+        For example:
 
              * `budget = 1` --> fully invested portfolio.
              * `budget = 0` --> market neutral portfolio.
@@ -378,7 +379,7 @@ class MeanRisk(ConvexOptimization):
         `groups` if the input `X` of the `fit` method is a DataFrame with these
         assets names in columns.
 
-        Examples:
+        For example:
 
             * "SPX >= 0.10" --> SPX weight must be greater than 10% (note that you can also use `min_weights`)
             * "SX5E + TLT >= 0.2" --> the sum of SX5E and TLT weights must be greater than 20%
@@ -392,7 +393,7 @@ class MeanRisk(ConvexOptimization):
         (asset name/asset groups) and the input `X` of the `fit` method must be a
         DataFrame with the assets names in columns.
 
-        Examples:
+        For example:
 
             * groups = {"SX5E": ["Equity", "Europe"], "SPX": ["Equity", "US"], "TLT": ["Bond", "US"]}
             * groups = [["Equity", "Equity", "Bond"], ["Europe", "US", "US"]]
@@ -711,7 +712,7 @@ class MeanRisk(ConvexOptimization):
         self.max_gini_mean_difference = max_gini_mean_difference
 
     def _validation(self) -> None:
-        """Validate the input parameters"""
+        """Validate the input parameters."""
         if not isinstance(self.risk_measure, RiskMeasure):
             raise TypeError("risk_measure must be of type `RiskMeasure`")
         if not isinstance(self.objective_function, ObjectiveFunction):
@@ -764,7 +765,9 @@ class MeanRisk(ConvexOptimization):
         """
         routed_params = skm.process_routing(self, "fit", **fit_params)
 
-        self._check_feature_names(X, reset=True)
+        # `X` is unchanged and only `feature_names_in_` is performed
+        _ = skv.validate_data(self, X, skip_check_array=True)
+
         # Validate
         self._validation()
         # Used to avoid adding multiple times similar constrains linked to identical
@@ -893,7 +896,7 @@ class MeanRisk(ConvexOptimization):
                         " 1d-array, a single-column DataFrame or a Series"
                     )
                 y = y[y.columns[0]]
-            _, y = self._validate_data(X, y)
+            _, y = skv.validate_data(self, X, y)
             tracking_error = self._tracking_error(
                 prior_model=prior_model, w=w, y=y, factor=factor
             )
@@ -1117,5 +1120,4 @@ def _optimal_homogenization_factor(mu: np.ndarray) -> float:
     value : float
         Homogenization factor.
     """
-
     return min(1e3, max(1e-3, np.mean(np.abs(mu))))

skfolio/optimization/convex/_risk_budgeting.py

@@ -2,7 +2,7 @@
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 # The optimization features are derived
 # from Riskfolio-Lib, Copyright (c) 2020-2023, Dany Cajas, Licensed under BSD 3 clause.
 
@@ -10,6 +10,7 @@ import cvxpy as cp
 import numpy as np
 import numpy.typing as npt
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 import skfolio.typing as skt
 from skfolio.measures import RiskMeasure
@@ -225,7 +226,7 @@ class RiskBudgeting(ConvexOptimization):
         `groups` if the input `X` of the `fit` method is a DataFrame with these
         assets names in columns.
 
-        Examples:
+        For example:
 
             * "SPX >= 0.10" --> SPX weight must be greater than 10% (note that you can also use `min_weights`)
             * "SX5E + TLT >= 0.2" --> the sum of SX5E and TLT weights must be greater than 20%
@@ -239,7 +240,7 @@ class RiskBudgeting(ConvexOptimization):
         (asset name/asset groups) and the input `X` of the `fit` method must be a
         DataFrame with the assets names in columns.
 
-        Examples:
+        For example:
 
             * groups = {"SX5E": ["Equity", "Europe"], "SPX": ["Equity", "US"], "TLT": ["Bond", "US"]}
             * groups = [["Equity", "Equity", "Bond"], ["Europe", "US", "US"]]
@@ -452,7 +453,8 @@ class RiskBudgeting(ConvexOptimization):
         """
         routed_params = skm.process_routing(self, "fit", **fit_params)
 
-        self._check_feature_names(X, reset=True)
+        # `X` is unchanged and only `feature_names_in_` is performed
+        _ = skv.validate_data(self, X, skip_check_array=True)
 
         if not isinstance(self.risk_measure, RiskMeasure):
             raise TypeError("risk_measure must be of type `RiskMeasure`")

skfolio/optimization/ensemble/__init__.py

@@ -1,3 +1,5 @@
+"""Ensemble Optimization module."""
+
 from skfolio.optimization.ensemble._stacking import (
     BaseComposition,
     StackingOptimization,

skfolio/optimization/ensemble/_base.py

@@ -1,10 +1,10 @@
 """Base Composition estimator.
-Follow same implementation as Base composition from sklearn
+Follow same implementation as Base composition from sklearn.
 """
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 # Implementation derived from:
 # scikit-learn, Copyright (c) 2007-2010 David Cournapeau, Fabian Pedregosa, Olivier
 # Grisel Licensed under BSD 3 clause.

skfolio/optimization/ensemble/_stacking.py

@@ -2,7 +2,7 @@
 
 # Copyright (c) 2023
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 # Implementation derived from:
 # scikit-learn, Copyright (c) 2007-2010 David Cournapeau, Fabian Pedregosa, Olivier
 # Grisel Licensed under BSD 3 clause.
@@ -330,9 +330,9 @@ class StackingOptimization(BaseOptimization, BaseComposition):
             # We validate and convert to numpy array only after base-estimator fitting
             # to keep the assets names in case they are used in the estimator.
             if y is not None:
-                _, y = self._validate_data(X, y, multi_output=True)
+                _, y = skv.validate_data(self, X, y, multi_output=True)
             else:
-                _ = self._validate_data(X)
+                _ = skv.validate_data(self, X)
 
             if isinstance(self.cv, BaseCombinatorialCV):
                 X_pred = np.array(

skfolio/optimization/naive/__init__.py

@@ -1,3 +1,5 @@
+"""Naive Optimization module."""
+
 from skfolio.optimization.naive._naive import EqualWeighted, InverseVolatility, Random
 
-__all__ = ["InverseVolatility", "EqualWeighted", "Random"]
+__all__ = ["EqualWeighted", "InverseVolatility", "Random"]

skfolio/optimization/naive/_naive.py

@@ -1,11 +1,12 @@
 """Naive estimators."""
 
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import numpy as np
 import numpy.typing as npt
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 from skfolio.optimization._base import BaseOptimization
 from skfolio.prior import BasePrior, EmpiricalPrior
@@ -141,7 +142,7 @@ class EqualWeighted(BaseOptimization):
         self : EqualWeighted
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         n_assets = X.shape[1]
         self.weights_ = np.ones(n_assets) / n_assets
         return self
@@ -185,7 +186,7 @@ class Random(BaseOptimization):
         self : EqualWeighted
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         n_assets = X.shape[1]
         self.weights_ = rand_weights_dirichlet(n=n_assets)
         return self

skfolio/population/__init__.py

@@ -1,3 +1,5 @@
+"""Population module."""
+
 from skfolio.population._population import Population
 
 __all__ = ["Population"]