skfolio 0.6.0__py3-none-any.whl → 0.7.0__py3-none-any.whl

skfolio/__init__.py

@@ -18,12 +18,12 @@ __version__ = importlib.metadata.version("skfolio")
 
 __all__ = [
     "BaseMeasure",
-    "PerfMeasure",
-    "RiskMeasure",
-    "ExtraRiskMeasure",
-    "RatioMeasure",
     "BasePortfolio",
-    "Portfolio",
+    "ExtraRiskMeasure",
     "MultiPeriodPortfolio",
+    "PerfMeasure",
     "Population",
+    "Portfolio",
+    "RatioMeasure",
+    "RiskMeasure",
 ]

skfolio/cluster/__init__.py

@@ -5,4 +5,4 @@
 
 from skfolio.cluster._hierarchical import HierarchicalClustering, LinkageMethod
 
-__all__ = ["LinkageMethod", "HierarchicalClustering"]
+__all__ = ["HierarchicalClustering", "LinkageMethod"]

skfolio/cluster/_hierarchical.py

@@ -180,7 +180,7 @@ class HierarchicalClustering(skb.ClusterMixin, skb.BaseEstimator):
         self : HierarchicalClustering
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         assert_is_distance(X)
         self.condensed_distance_ = scd.squareform(X, checks=False)
         self.linkage_matrix_ = sch.linkage(

skfolio/datasets/__init__.py

@@ -13,10 +13,10 @@ from skfolio.datasets._base import (
 )
 
 __all__ = [
-    "load_nasdaq_dataset",
     "load_factors_dataset",
     "load_ftse100_dataset",
+    "load_nasdaq_dataset",
     "load_sp500_dataset",
-    "load_sp500_index",
     "load_sp500_implied_vol_dataset",
+    "load_sp500_index",
 ]

skfolio/distance/__init__.py

@@ -16,11 +16,11 @@ from skfolio.distance._distance import (
 
 __all__ = [
     "BaseDistance",
-    "PearsonDistance",
-    "KendallDistance",
-    "SpearmanDistance",
     "CovarianceDistance",
     "DistanceCorrelation",
+    "KendallDistance",
     "MutualInformation",
     "NBinsMethod",
+    "PearsonDistance",
+    "SpearmanDistance",
 ]

skfolio/distance/_distance.py

@@ -11,6 +11,7 @@ import scipy.spatial.distance as scd
 import scipy.stats as sct
 import sklearn.metrics as skmc
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 from skfolio.distance._base import BaseDistance
 from skfolio.moments import BaseCovariance, GerberCovariance
@@ -85,7 +86,7 @@ class PearsonDistance(BaseDistance):
         self : PearsonDistance
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         corr = np.corrcoef(X.T)
         self.codependence_, self.distance_ = _corr_to_distance(
             corr, absolute=self.absolute, power=self.power
@@ -157,7 +158,7 @@ class KendallDistance(BaseDistance):
         self : KendallDistance
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         corr = pd.DataFrame(X).corr(method="kendall").to_numpy()
         self.codependence_, self.distance_ = _corr_to_distance(
             corr, absolute=self.absolute, power=self.power
@@ -229,7 +230,7 @@ class SpearmanDistance(BaseDistance):
         self : SpearmanDistance
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         corr = pd.DataFrame(X).corr(method="spearman").to_numpy()
         self.codependence_, self.distance_ = _corr_to_distance(
             corr, absolute=self.absolute, power=self.power
@@ -337,7 +338,7 @@ class CovarianceDistance(BaseDistance):
 
         # we validate and convert to numpy after all models have been fitted to keep the
         # features names information.
-        _ = self._validate_data(X)
+        _ = skv.validate_data(self, X)
 
         corr, _ = cov_to_corr(self.covariance_estimator_.covariance_)
         self.codependence_, self.distance_ = _corr_to_distance(
@@ -409,7 +410,7 @@ class DistanceCorrelation(BaseDistance):
         self : DistanceCorrelation
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         n_assets = X.shape[1]
         corr = np.ones((n_assets, n_assets))
         # TODO: parallelize
@@ -502,7 +503,7 @@ class MutualInformation(BaseDistance):
         self : MutualInformation
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         n_assets = X.shape[1]
         if self.n_bins is None:
             match self.n_bins_method:

skfolio/exceptions.py

@@ -8,11 +8,11 @@ classes used across skfolio.
 # License: BSD 3 clause
 
 __all__ = [
-    "OptimizationError",
+    "DuplicateGroupsError",
     "EquationToMatrixError",
     "GroupNotFoundError",
     "NonPositiveVarianceError",
-    "DuplicateGroupsError",
+    "OptimizationError",
 ]
 
 

skfolio/measures/__init__.py

@@ -43,36 +43,36 @@ from skfolio.measures._measures import (
 
 __all__ = [
     "BaseMeasure",
-    "PerfMeasure",
-    "RiskMeasure",
     "ExtraRiskMeasure",
+    "PerfMeasure",
     "RatioMeasure",
-    "mean",
+    "RiskMeasure",
+    "average_drawdown",
+    "cdar",
+    "cvar",
+    "drawdown_at_risk",
+    "edar",
+    "effective_number_assets",
+    "entropic_risk_measure",
+    "evar",
+    "first_lower_partial_moment",
+    "fourth_central_moment",
+    "fourth_lower_partial_moment",
     "get_cumulative_returns",
     "get_drawdowns",
-    "variance",
+    "gini_mean_difference",
+    "kurtosis",
+    "max_drawdown",
+    "mean",
+    "mean_absolute_deviation",
+    "owa_gmd_weights",
+    "semi_deviation",
     "semi_variance",
+    "skew",
     "standard_deviation",
-    "semi_deviation",
     "third_central_moment",
-    "fourth_central_moment",
-    "fourth_lower_partial_moment",
-    "cvar",
-    "mean_absolute_deviation",
+    "ulcer_index",
     "value_at_risk",
+    "variance",
     "worst_realization",
-    "first_lower_partial_moment",
-    "entropic_risk_measure",
-    "evar",
-    "drawdown_at_risk",
-    "cdar",
-    "max_drawdown",
-    "average_drawdown",
-    "edar",
-    "ulcer_index",
-    "gini_mean_difference",
-    "owa_gmd_weights",
-    "skew",
-    "kurtosis",
-    "effective_number_assets",
 ]

skfolio/model_selection/__init__.py

@@ -12,9 +12,9 @@ from skfolio.model_selection._validation import cross_val_predict
 from skfolio.model_selection._walk_forward import WalkForward
 
 __all__ = [
-    "cross_val_predict",
-    "WalkForward",
     "BaseCombinatorialCV",
     "CombinatorialPurgedCV",
+    "WalkForward",
+    "cross_val_predict",
     "optimal_folds_number",
 ]

skfolio/moments/__init__.py

@@ -23,21 +23,21 @@ from skfolio.moments.expected_returns import (
 )
 
 __all__ = [
+    "OAS",
+    "BaseCovariance",
     "BaseMu",
-    "EmpiricalMu",
+    "DenoiseCovariance",
+    "DetoneCovariance",
+    "EWCovariance",
     "EWMu",
-    "ShrunkMu",
-    "EquilibriumMu",
-    "ShrunkMuMethods",
-    "BaseCovariance",
     "EmpiricalCovariance",
-    "EWCovariance",
+    "EmpiricalMu",
+    "EquilibriumMu",
     "GerberCovariance",
-    "DenoiseCovariance",
-    "DetoneCovariance",
-    "LedoitWolf",
-    "OAS",
-    "ShrunkCovariance",
     "GraphicalLassoCV",
     "ImpliedCovariance",
+    "LedoitWolf",
+    "ShrunkCovariance",
+    "ShrunkMu",
+    "ShrunkMuMethods",
 ]

skfolio/moments/covariance/__init__.py

@@ -15,15 +15,15 @@ from skfolio.moments.covariance._oas import OAS
 from skfolio.moments.covariance._shrunk_covariance import ShrunkCovariance
 
 __all__ = [
+    "OAS",
     "BaseCovariance",
-    "EmpiricalCovariance",
-    "EWCovariance",
-    "GerberCovariance",
     "DenoiseCovariance",
     "DetoneCovariance",
-    "LedoitWolf",
-    "OAS",
-    "ShrunkCovariance",
+    "EWCovariance",
+    "EmpiricalCovariance",
+    "GerberCovariance",
     "GraphicalLassoCV",
     "ImpliedCovariance",
+    "LedoitWolf",
+    "ShrunkCovariance",
 ]

skfolio/moments/covariance/_denoise_covariance.py

@@ -12,6 +12,7 @@ import numpy.typing as npt
 import scipy.optimize as sco
 import sklearn.neighbors as skn
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 from skfolio.moments.covariance._base import BaseCovariance
 from skfolio.moments.covariance._empirical_covariance import EmpiricalCovariance
@@ -139,7 +140,7 @@ class DenoiseCovariance(BaseCovariance):
 
         # we validate and convert to numpy after all models have been fitted to keep
         # features names information.
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         n_observations, n_assets = X.shape
         q = n_observations / n_assets
         corr, std = cov_to_corr(self.covariance_estimator_.covariance_)

skfolio/moments/covariance/_detone_covariance.py

@@ -10,6 +10,7 @@
 import numpy as np
 import numpy.typing as npt
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 from skfolio.moments.covariance._base import BaseCovariance
 from skfolio.moments.covariance._empirical_covariance import EmpiricalCovariance
@@ -141,7 +142,7 @@ class DetoneCovariance(BaseCovariance):
 
         # we validate and convert to numpy after all models have been fitted to keep
         # features names information.
-        _ = self._validate_data(X)
+        _ = skv.validate_data(self, X)
         corr, std = cov_to_corr(self.covariance_estimator_.covariance_)
         e_val, e_vec = np.linalg.eigh(corr)
         indices = e_val.argsort()[::-1]

skfolio/moments/covariance/_empirical_covariance.py

@@ -9,6 +9,7 @@
 
 import numpy as np
 import numpy.typing as npt
+import sklearn.utils.validation as skv
 
 from skfolio.moments.covariance._base import BaseCovariance
 
@@ -92,7 +93,7 @@ class EmpiricalCovariance(BaseCovariance):
         self : EmpiricalCovariance
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         if self.window_size is not None:
             X = X[-int(self.window_size) :]
         covariance = np.cov(X.T, ddof=self.ddof)

skfolio/moments/covariance/_ew_covariance.py

@@ -9,6 +9,7 @@
 
 import numpy.typing as npt
 import pandas as pd
+import sklearn.utils.validation as skv
 
 from skfolio.moments.covariance._base import BaseCovariance
 
@@ -94,7 +95,7 @@ class EWCovariance(BaseCovariance):
         self : EWCovariance
           Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         if self.window_size is not None:
             X = X[-int(self.window_size) :]
         n_observations = X.shape[0]

skfolio/moments/covariance/_gerber_covariance.py

@@ -9,6 +9,7 @@
 
 import numpy as np
 import numpy.typing as npt
+import sklearn.utils.validation as skv
 
 from skfolio.moments.covariance._base import BaseCovariance
 from skfolio.utils.stats import corr_to_cov
@@ -131,7 +132,7 @@ class GerberCovariance(BaseCovariance):
         self : GerberCovariance
            Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         if self.window_size is not None:
             X = X[-self.window_size :]
         if not (1 > self.threshold > 0):

skfolio/moments/covariance/_implied_covariance.py

@@ -272,7 +272,7 @@ class ImpliedCovariance(BaseCovariance):
                 # and re-order to follow returns ordering.
                 implied_vol = safe_indexing(implied_vol, indices=indices, axis=1)
 
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         _, n_assets = X.shape
         implied_vol = check_implied_vol(implied_vol=implied_vol, X=X)
         implied_vol /= np.sqrt(self.annualized_factor)

skfolio/moments/expected_returns/__init__.py

@@ -10,9 +10,9 @@ from skfolio.moments.expected_returns._shrunk_mu import ShrunkMu, ShrunkMuMethod
 
 __all__ = [
     "BaseMu",
-    "EmpiricalMu",
     "EWMu",
-    "ShrunkMu",
+    "EmpiricalMu",
     "EquilibriumMu",
+    "ShrunkMu",
     "ShrunkMuMethods",
 ]

skfolio/moments/expected_returns/_empirical_mu.py

@@ -9,6 +9,7 @@
 
 import numpy as np
 import numpy.typing as npt
+import sklearn.utils.validation as skv
 
 from skfolio.moments.expected_returns._base import BaseMu
 
@@ -56,7 +57,7 @@ class EmpiricalMu(BaseMu):
         self : EmpiricalMu
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         if self.window_size is not None:
             X = X[-self.window_size :]
         self.mu_ = np.mean(X, axis=0)

skfolio/moments/expected_returns/_equilibrium_mu.py

@@ -10,6 +10,7 @@
 import numpy as np
 import numpy.typing as npt
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 from skfolio.moments.covariance import BaseCovariance, EmpiricalCovariance
 from skfolio.moments.expected_returns._base import BaseMu
@@ -114,7 +115,7 @@ class EquilibriumMu(BaseMu):
 
         # we validate and convert to numpy after all models have been fitted to keep
         # features names information.
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         n_assets = X.shape[1]
         if self.weights is None:
             weights = np.ones(n_assets) / n_assets

skfolio/moments/expected_returns/_ew_mu.py

@@ -9,6 +9,7 @@
 
 import numpy.typing as npt
 import pandas as pd
+import sklearn.utils.validation as skv
 
 from skfolio.moments.expected_returns._base import BaseMu
 
@@ -62,7 +63,7 @@ class EWMu(BaseMu):
         self : EWMu
             Fitted estimator.
         """
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         if self.window_size is not None:
             X = X[-self.window_size :]
         self.mu_ = pd.DataFrame(X).ewm(alpha=self.alpha).mean().iloc[-1, :].to_numpy()

skfolio/moments/expected_returns/_shrunk_mu.py

@@ -13,6 +13,7 @@ from enum import auto
 import numpy as np
 import numpy.typing as npt
 import sklearn.utils.metadata_routing as skm
+import sklearn.utils.validation as skv
 
 from skfolio.moments.covariance import BaseCovariance, EmpiricalCovariance
 from skfolio.moments.expected_returns._base import BaseMu
@@ -189,7 +190,7 @@ class ShrunkMu(BaseMu):
 
         # we validate and convert to numpy after all models have been fitted to keep
         # features names information.
-        X = self._validate_data(X)
+        X = skv.validate_data(self, X)
         n_observations, n_assets = X.shape
 
         covariance = self.covariance_estimator_.covariance_

skfolio/optimization/__init__.py

@@ -17,20 +17,20 @@ from skfolio.optimization.ensemble import BaseComposition, StackingOptimization
 from skfolio.optimization.naive import EqualWeighted, InverseVolatility, Random
 
 __all__ = [
+    "BaseComposition",
+    "BaseHierarchicalOptimization",
     "BaseOptimization",
-    "InverseVolatility",
-    "EqualWeighted",
-    "Random",
-    "ObjectiveFunction",
     "ConvexOptimization",
-    "MeanRisk",
-    "RiskBudgeting",
     "DistributionallyRobustCVaR",
-    "MaximumDiversification",
-    "BaseHierarchicalOptimization",
-    "HierarchicalRiskParity",
+    "EqualWeighted",
     "HierarchicalEqualRiskContribution",
+    "HierarchicalRiskParity",
+    "InverseVolatility",
+    "MaximumDiversification",
+    "MeanRisk",
     "NestedClustersOptimization",
-    "BaseComposition",
+    "ObjectiveFunction",
+    "Random",
+    "RiskBudgeting",
     "StackingOptimization",
 ]

skfolio/optimization/cluster/__init__.py

@@ -7,7 +7,7 @@ from skfolio.optimization.cluster.hierarchical import (
 
 __all__ = [
     "BaseHierarchicalOptimization",
-    "HierarchicalRiskParity",
     "HierarchicalEqualRiskContribution",
+    "HierarchicalRiskParity",
     "NestedClustersOptimization",
 ]

skfolio/optimization/cluster/_nco.py

@@ -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
@@ -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 = []

skfolio/optimization/cluster/hierarchical/__init__.py

@@ -8,6 +8,6 @@ from skfolio.optimization.cluster.hierarchical._hrp import HierarchicalRiskParit
 
 __all__ = [
     "BaseHierarchicalOptimization",
-    "HierarchicalRiskParity",
     "HierarchicalEqualRiskContribution",
+    "HierarchicalRiskParity",
 ]

skfolio/optimization/cluster/hierarchical/_herc.py

@@ -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
@@ -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

@@ -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
@@ -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

@@ -7,10 +7,10 @@ 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

@@ -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

@@ -8,6 +8,7 @@ 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
@@ -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

@@ -6,6 +6,7 @@
 
 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
@@ -423,7 +424,8 @@ 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"""

skfolio/optimization/convex/_mean_risk.py

@@ -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
@@ -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
             )