skfolio 0.1.3__py3-none-any.whl → 0.2.1__py3-none-any.whl

skfolio/model_selection/__init__.py

@@ -6,6 +6,7 @@
 from skfolio.model_selection._combinatorial import (
     BaseCombinatorialCV,
     CombinatorialPurgedCV,
+    optimal_folds_number,
 )
 from skfolio.model_selection._validation import cross_val_predict
 from skfolio.model_selection._walk_forward import WalkForward
@@ -15,4 +16,5 @@ __all__ = [
     "WalkForward",
     "BaseCombinatorialCV",
     "CombinatorialPurgedCV",
+    "optimal_folds_number",
 ]

skfolio/model_selection/_combinatorial.py

@@ -197,19 +197,13 @@ class CombinatorialPurgedCV(BaseCombinatorialCV):
     @property
     def n_splits(self) -> int:
         """Number of splits"""
-        return int(
-            math.factorial(self.n_folds)
-            / (
-                math.factorial(self.n_test_folds)
-                * math.factorial(self.n_folds - self.n_test_folds)
-            )
-        )
+        return _n_splits(n_folds=self.n_folds, n_test_folds=self.n_test_folds)
 
     @property
     def n_test_paths(self) -> int:
         """Number of test paths that can be reconstructed from the train/test
         combinations"""
-        return self.n_splits * self.n_test_folds // self.n_folds
+        return _n_test_paths(n_folds=self.n_folds, n_test_folds=self.n_test_folds)
 
     @property
     def test_set_index(self) -> np.ndarray:
@@ -320,17 +314,20 @@ class CombinatorialPurgedCV(BaseCombinatorialCV):
             yield train_index, test_index_list
 
     def summary(self, X) -> pd.Series:
-        n_samples = X.shape[0]
+        n_observations = X.shape[0]
+        avg_train_size = _avg_train_size(
+            n_observations=n_observations,
+            n_folds=self.n_folds,
+            n_test_folds=self.n_test_folds,
+        )
         return pd.Series(
             {
-                "Number of Observations": n_samples,
+                "Number of Observations": n_observations,
                 "Total Number of Folds": self.n_folds,
                 "Number of Test Folds": self.n_test_folds,
                 "Purge Size": self.purged_size,
                 "Embargo Size": self.embargo_size,
-                "Average Training Size": int(
-                    n_samples / self.n_folds * (self.n_folds - self.n_test_folds)
-                ),
+                "Average Training Size": int(avg_train_size),
                 "Number of Test Paths": self.n_test_paths,
                 "Number of Training Combinations": self.n_splits,
             }
@@ -410,3 +407,155 @@ class CombinatorialPurgedCV(BaseCombinatorialCV):
         )
 
         return fig
+
+
+def _n_splits(n_folds: int, n_test_folds: int) -> int:
+    """Number of splits.
+
+    Parameters
+    ----------
+    n_folds : int
+        Number of folds.
+
+    n_test_folds : int
+        Number of test folds.
+
+    Returns
+    -------
+    n_splits : int
+        Number of splits
+    """
+    return int(math.comb(n_folds, n_test_folds))
+
+
+def _n_test_paths(n_folds: int, n_test_folds: int) -> int:
+    """Number of test paths that can be reconstructed from the train/test
+    combinations
+
+    Parameters
+    ----------
+    n_folds : int
+        Number of folds.
+
+    n_test_folds : int
+        Number of test folds.
+
+    Returns
+    -------
+    n_splits : int
+        Number of test paths.
+    """
+    return (
+        _n_splits(n_folds=n_folds, n_test_folds=n_test_folds) * n_test_folds // n_folds
+    )
+
+
+def _avg_train_size(n_observations: int, n_folds: int, n_test_folds: int) -> float:
+    """Average number of observations contained in each training set.
+
+    Parameters
+    ----------
+    n_observations : int
+        Number of observations.
+
+    n_folds : int
+        Number of folds.
+
+    n_test_folds : int
+        Number of test folds.
+
+    Returns
+    -------
+    avg_train_size : float
+        Average number of observations contained in each training set.
+    """
+    return n_observations / n_folds * (n_folds - n_test_folds)
+
+
+def optimal_folds_number(
+    n_observations: int,
+    target_train_size: int,
+    target_n_test_paths: int,
+    weight_train_size: float = 1,
+    weight_n_test_paths: float = 1,
+) -> tuple[int, int]:
+    r"""Find the optimal number of folds (total folds and test folds) for a target
+    training size and a target number of test paths.
+
+    We find `x = n_folds` and `y = n_test_folds` that minimizes the below
+    cost function of the relative distance from the two targets:
+
+    .. math::
+           cost(x,y) = w_{f} \times \lvert\frac{f(x,y)-f_{target}}{f_{target}}\rvert + w_{g} \times \lvert\frac{g(x,y)-g_{target}}{g_{target}}\rvert
+
+    with :math:`w_{f}` and :math:`w_{g}` the weights assigned to the distance
+    from each target and :math:`f(x,y)` and :math:`g(x,y)` the average training size
+    and the number of test paths as a function of the number of total folds and test
+    folds.
+
+    This is a combinatorial problem with :math:`\frac{T\times(T-3)}{2}` combinations,
+    with :math:`T` the number of observations.
+
+    We reduce the search space by using the combinatorial symetry
+    :math:`{n \choose k}={n \choose n-k}` and skipping cost computation above 1e5.
+
+    Parameters
+    ----------
+    n_observations : int
+        Number of observations.
+
+    target_train_size : int
+        The target number of observation in the training set.
+
+    target_n_test_paths : int
+        The target number of test paths (that can be reconstructed from the train/test
+        combinations).
+
+    weight_train_size : float, default=1
+        The weight assigned to the distance from the target train size.
+        The default value is 1.
+
+    weight_n_test_paths : float, default=1
+        The weight assigned to the distance from the target number of test paths.
+        The default value is 1.
+
+    Returns
+    -------
+    n_folds : int
+        Optimal number of total folds.
+
+    n_test_folds : int
+        Optimal number of test folds.
+    """
+
+    def _cost(
+        x: int,
+        y: int,
+    ) -> float:
+        n_test_paths = _n_test_paths(n_folds=x, n_test_folds=y)
+        avg_train_size = _avg_train_size(
+            n_observations=n_observations, n_folds=x, n_test_folds=y
+        )
+        return (
+            weight_n_test_paths
+            * abs(n_test_paths - target_n_test_paths)
+            / target_n_test_paths
+            + weight_train_size
+            * abs(avg_train_size - target_train_size)
+            / target_train_size
+        )
+
+    costs = []
+    res = []
+    for n_folds in range(3, n_observations + 1):
+        i = None
+        for n_test_folds in range(2, n_folds):
+            if i is None or n_folds - n_test_folds <= i:
+                cost = _cost(x=n_folds, y=n_test_folds)
+                costs.append(cost)
+                res.append((n_folds, n_test_folds))
+                if i is None and cost > 1e5:
+                    i = n_test_folds
+
+    j = np.argmin(costs)
+    return res[j]

skfolio/optimization/_base.py

@@ -29,8 +29,8 @@ class BaseOptimization(skb.BaseEstimator, ABC):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------
@@ -84,7 +84,12 @@ class BaseOptimization(skb.BaseEstimator, ABC):
             ptf_kwargs = self.portfolio_params.copy()
 
         # Set the default portfolio parameters equal to the optimization parameters
-        for param in ["transaction_costs", "management_fees", "previous_weights"]:
+        for param in [
+            "transaction_costs",
+            "management_fees",
+            "previous_weights",
+            "risk_free_rate",
+        ]:
             if param not in ptf_kwargs and hasattr(self, param):
                 ptf_kwargs[param] = getattr(self, param)
 

skfolio/optimization/cluster/hierarchical/_base.py

@@ -8,6 +8,7 @@
 # scikit-learn, Copyright (c) 2007-2010 David Cournapeau, Fabian Pedregosa, Olivier
 
 from abc import ABC, abstractmethod
+from typing import Any
 
 import numpy as np
 import numpy.typing as npt
@@ -183,8 +184,8 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------
@@ -235,7 +236,7 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
         self,
         value: float | dict | np.ndarray | list,
         n_assets: int,
-        fill_value: any,
+        fill_value: Any,
         name: str,
     ) -> np.ndarray:
         """Convert input to cleaned 1D array
@@ -250,7 +251,7 @@ class BaseHierarchicalOptimization(BaseOptimization, ABC):
         n_assets : int
             Number of assets. Used to verify the shape of the converted array.
 
-        fill_value : any
+        fill_value : Any
             When `items` is a dictionary, elements that are not in `asset_names` are
             filled with `fill_value` in the converted array.
 

skfolio/optimization/cluster/hierarchical/_herc.py

@@ -204,8 +204,8 @@ class HierarchicalEqualRiskContribution(BaseHierarchicalOptimization):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------

skfolio/optimization/cluster/hierarchical/_hrp.py

@@ -204,8 +204,8 @@ class HierarchicalRiskParity(BaseHierarchicalOptimization):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------

skfolio/optimization/convex/_base.py

@@ -9,6 +9,7 @@
 import warnings
 from abc import ABC, abstractmethod
 from enum import auto
+from typing import Any
 
 import cvxpy as cp
 import cvxpy.constraints.constraint as cpc
@@ -403,8 +404,8 @@ class ConvexOptimization(BaseOptimization, ABC):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------
@@ -575,7 +576,7 @@ class ConvexOptimization(BaseOptimization, ABC):
         self,
         value: float | dict | npt.ArrayLike | None,
         n_assets: int,
-        fill_value: any,
+        fill_value: Any,
         name: str,
     ) -> float | np.ndarray:
         """Convert input to cleaned float or ndarray.
@@ -588,7 +589,7 @@ class ConvexOptimization(BaseOptimization, ABC):
         n_assets : int
             Number of assets. Used to verify the shape of the converted array.
 
-        fill_value : any
+        fill_value : Any
             When `items` is a dictionary, elements that are not in `asset_names` are
             filled with `fill_value` in the converted array.
 

skfolio/optimization/convex/_distributionally_robust.py

@@ -208,8 +208,8 @@ class DistributionallyRobustCVaR(ConvexOptimization):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------

skfolio/optimization/convex/_maximum_diversification.py

@@ -303,8 +303,8 @@ class MaximumDiversification(MeanRisk):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------

skfolio/optimization/convex/_mean_risk.py

@@ -510,8 +510,8 @@ class MeanRisk(ConvexOptimization):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the 
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------

skfolio/optimization/convex/_risk_budgeting.py

@@ -340,8 +340,8 @@ class RiskBudgeting(ConvexOptimization):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the 
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------

skfolio/optimization/naive/_naive.py

@@ -31,8 +31,8 @@ class InverseVolatility(BaseOptimization):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------
@@ -95,8 +95,8 @@ class EqualWeighted(BaseOptimization):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------
@@ -139,8 +139,8 @@ class Random(BaseOptimization):
     portfolio_params :  dict, optional
         Portfolio parameters passed to the portfolio evaluated by the `predict` and
         `score` methods. If not provided, the `name`, `transaction_costs`,
-        `management_fees` and `previous_weights` are copied from the optimization
-        model and systematically passed to the portfolio.
+        `management_fees`, `previous_weights` and `risk_free_rate` are copied from the
+        optimization model and passed to the portfolio.
 
     Attributes
     ----------

skfolio/population/_population.py

@@ -7,6 +7,7 @@ A population is a collection of portfolios.
 # License: BSD 3 clause
 
 import inspect
+from typing import Any
 
 import numpy as np
 import pandas as pd
@@ -15,7 +16,7 @@ import plotly.graph_objects as go
 import scipy.interpolate as sci
 
 import skfolio.typing as skt
-from skfolio.portfolio import BasePortfolio, MultiPeriodPortfolio, Portfolio
+from skfolio.portfolio import BasePortfolio, MultiPeriodPortfolio
 from skfolio.utils.sorting import non_denominated_sort
 from skfolio.utils.tools import deduplicate_names
 
@@ -30,14 +31,14 @@ class Population(list):
 
     Parameters
     ----------
-    iterable : list[Portfolio | MultiPeriodPortfolio]
+    iterable : list[BasePortfolio]
         The list of portfolios. Each item can be of type
         :class:`~skfolio.portfolio.Portfolio` and/or
         :class:`~skfolio.portfolio.MultiPeriodPortfolio`.
         Empty list are accepted.
     """
 
-    def __init__(self, iterable: list[Portfolio | MultiPeriodPortfolio]) -> None:
+    def __init__(self, iterable: list[BasePortfolio]) -> None:
         super().__init__(self._validate_item(item) for item in iterable)
 
     def __repr__(self) -> str:
@@ -45,43 +46,43 @@ class Population(list):
 
     def __getitem__(
         self, indices: int | list[int] | slice
-    ) -> "Portfolio | MultiPeriodPortfolio|Population":
+    ) -> "BasePortfolio | Population":
         item = super().__getitem__(indices)
         if isinstance(item, list):
             return self.__class__(item)
         return item
 
-    def __setitem__(self, index: int, item: Portfolio | MultiPeriodPortfolio) -> None:
+    def __setitem__(self, index: int, item: BasePortfolio) -> None:
         super().__setitem__(index, self._validate_item(item))
 
-    def __add__(self, other: Portfolio | MultiPeriodPortfolio) -> "Population":
+    def __add__(self, other: BasePortfolio) -> "Population":
         if not isinstance(other, Population):
             raise TypeError(
                 f"Cannot add a Population with an object of type {type(other)}"
             )
         return self.__class__(super().__add__(other))
 
-    def insert(self, index, item: Portfolio | MultiPeriodPortfolio) -> None:
+    def insert(self, index, item: BasePortfolio) -> None:
         """Insert portfolio before index."""
         super().insert(index, self._validate_item(item))
 
-    def append(self, item: Portfolio | MultiPeriodPortfolio) -> None:
+    def append(self, item: BasePortfolio) -> None:
         """Append portfolio to the end of the population list."""
         super().append(self._validate_item(item))
 
-    def extend(self, other: Portfolio | MultiPeriodPortfolio) -> None:
+    def extend(self, other: BasePortfolio) -> None:
         """Extend population list by appending elements from the iterable."""
         if isinstance(other, type(self)):
             super().extend(other)
         else:
             super().extend(self._validate_item(item) for item in other)
 
-    def set_portfolio_params(self, **params: any) -> "Population":
+    def set_portfolio_params(self, **params: Any) -> "Population":
         """Set the parameters of all the portfolios.
 
         Parameters
         ----------
-        **params : any
+        **params : Any
             Portfolio parameters.
 
         Returns
@@ -111,13 +112,14 @@ class Population(list):
 
     @staticmethod
     def _validate_item(
-        item: Portfolio | MultiPeriodPortfolio,
-    ) -> Portfolio | MultiPeriodPortfolio:
+        item: BasePortfolio,
+    ) -> BasePortfolio:
         """Validate that items are of type Portfolio or MultiPeriodPortfolio."""
-        if isinstance(item, Portfolio | MultiPeriodPortfolio):
+        if isinstance(item, BasePortfolio):
             return item
         raise TypeError(
-            "Population only accept items of type Portfolio and MultiPeriodPortfolio"
+            "Population only accept items that inherit from BasePortfolio such as "
+            "Portfolio or MultiPeriodPortfolio"
             f", got {type(item).__name__}"
         )
 
@@ -324,7 +326,7 @@ class Population(list):
         q: float,
         names: skt.Names | None = None,
         tags: skt.Tags | None = None,
-    ) -> Portfolio | MultiPeriodPortfolio:
+    ) -> BasePortfolio:
         """Returns the portfolio corresponding to the `q` quantile for a given portfolio
         measure.
 
@@ -344,7 +346,7 @@ class Population(list):
 
         Returns
         -------
-        values : Portfolio | MultiPeriodPortfolio
+        values : BasePortfolio
            Portfolio corresponding to the `q` quantile for the measure.
         """
         if not 0 <= q <= 1:
@@ -360,7 +362,7 @@ class Population(list):
         measure: skt.Measure,
         names: skt.Names | None = None,
         tags: skt.Tags | None = None,
-    ) -> Portfolio | MultiPeriodPortfolio:
+    ) -> BasePortfolio:
         """Returns the portfolio with the minimum measure.
 
         Parameters
@@ -376,7 +378,7 @@ class Population(list):
 
         Returns
         -------
-        values : Portfolio | MultiPeriodPortfolio
+        values : BasePortfolio
             The portfolio with minimum measure.
         """
         return self.quantile(measure=measure, q=0, names=names, tags=tags)
@@ -386,7 +388,7 @@ class Population(list):
         measure: skt.Measure,
         names: skt.Names | None = None,
         tags: skt.Tags | None = None,
-    ) -> Portfolio | MultiPeriodPortfolio:
+    ) -> BasePortfolio:
         """Returns the portfolio with the maximum measure.
 
         Parameters
@@ -402,7 +404,7 @@ class Population(list):
 
         Returns
         -------
-        values : Portfolio | MultiPeriodPortfolio
+        values : BasePortfolio
             The portfolio with maximum measure.
         """
         return self.quantile(measure=measure, q=1, names=names, tags=tags)

skfolio/prior/_black_litterman.py

@@ -156,7 +156,7 @@ class BlackLitterman(BasePrior):
             check_type=BasePrior,
         )
         # fitting prior estimator
-        self.prior_estimator_.fit(X)
+        self.prior_estimator_.fit(X, y)
 
         prior_mu = self.prior_estimator_.prior_model_.mu
         prior_covariance = self.prior_estimator_.prior_model_.covariance

skfolio/prior/_empirical.py

@@ -120,11 +120,11 @@ class EmpiricalPrior(BasePrior):
                     "`is_log_normal` is `False`"
                 )
             # Expected returns
-            self.mu_estimator_.fit(X)
+            self.mu_estimator_.fit(X, y)
             mu = self.mu_estimator_.mu_
 
             # Covariance
-            self.covariance_estimator_.fit(X)
+            self.covariance_estimator_.fit(X, y)
             covariance = self.covariance_estimator_.covariance_
         else:
             if self.investment_horizon is None:
@@ -134,14 +134,15 @@ class EmpiricalPrior(BasePrior):
                 )
             # Convert linear returns to log returns
             X_log = np.log(1 + X)
+            y_log = np.log(1 + y) if y is not None else None
 
             # Estimates the moments on the log returns
             # Expected returns
-            self.mu_estimator_.fit(X_log)
+            self.mu_estimator_.fit(X_log, y_log)
             mu = self.mu_estimator_.mu_
 
             # Covariance
-            self.covariance_estimator_.fit(X_log)
+            self.covariance_estimator_.fit(X_log, y_log)
             covariance = self.covariance_estimator_.covariance_
 
             # Using the property of aggregation across time we scale this distribution

skfolio/prior/_factor_model.py

@@ -9,6 +9,7 @@
 # Grisel Licensed under BSD 3 clause.
 
 from abc import ABC, abstractmethod
+from typing import Any
 
 import numpy as np
 import numpy.typing as npt
@@ -196,7 +197,7 @@ class FactorModel(BasePrior):
         self.max_iteration = max_iteration
 
     # noinspection PyMethodOverriding, PyPep8Naming
-    def fit(self, X: npt.ArrayLike, y: any):
+    def fit(self, X: npt.ArrayLike, y: Any):
         """Fit the Factor Model estimator.
 
         Parameters

skfolio/utils/tools.py

@@ -10,6 +10,7 @@
 from collections.abc import Callable, Iterator
 from enum import Enum
 from functools import wraps
+from typing import Any
 
 import numpy as np
 import numpy.typing as npt
@@ -41,7 +42,7 @@ class AutoEnum(str, Enum):
 
     @staticmethod
     def _generate_next_value_(
-        name: str, start: int, count: int, last_values: any
+        name: str, start: int, count: int, last_values: Any
     ) -> str:
         """Overriding `auto()`"""
         return name.lower()
@@ -179,7 +180,7 @@ def args_names(func: object) -> list[str]:
 
 
 def check_estimator(
-    estimator: skb.BaseEstimator | None, default: skb.BaseEstimator, check_type: any
+    estimator: skb.BaseEstimator | None, default: skb.BaseEstimator, check_type: Any
 ):
     """Check the estimator type and returns its cloned version it provided, otherwise
      return the default estimator.
@@ -192,7 +193,7 @@ def check_estimator(
     default : BaseEstimator
         Default estimator to return when `estimator` is `None`.
 
-    check_type : any
+    check_type : Any
         Expected type of the estimator to check against.
 
     Returns
@@ -211,7 +212,7 @@ def check_estimator(
 def input_to_array(
     items: dict | npt.ArrayLike,
     n_assets: int,
-    fill_value: any,
+    fill_value: Any,
     dim: int,
     assets_names: np.ndarray | None,
     name: str,
@@ -228,7 +229,7 @@ def input_to_array(
         Expected number of assets.
         Used to verify the shape of the converted array.
 
-    fill_value : any
+    fill_value : Any
         When `items` is a dictionary, elements that are not in `asset_names` are filled
         with `fill_value` in the converted array.
 
@@ -424,7 +425,7 @@ def safe_split(
 
 
 def fit_single_estimator(
-    estimator: any,
+    estimator: Any,
     X: npt.ArrayLike,
     y: npt.ArrayLike | None = None,
     indices: np.ndarray | None = None,
@@ -463,7 +464,7 @@ def fit_single_estimator(
 
 
 def fit_and_predict(
-    estimator: any,
+    estimator: Any,
     X: npt.ArrayLike,
     y: npt.ArrayLike | None,
     train: np.ndarray,

{skfolio-0.1.3.dist-info → skfolio-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: skfolio
-Version: 0.1.3
+Version: 0.2.1
 Summary: Portfolio optimization built on top of scikit-learn
 Author-email: Hugo Delatte <delatte.hugo@gmail.com>
 Maintainer-email: Hugo Delatte <delatte.hugo@gmail.com>
@@ -84,37 +84,37 @@ Requires-Dist: ruff ; extra == 'tests'
 
 .. -*- mode: rst -*-
 
-|Licence|_ |Codecov|_ |Black|_ |PythonVersion|_ |PyPi|_ |CI/CD|_ |Downloads|_ |Ruff|_ |Contribution|_ |Website|_
+|Licence| |Codecov| |Black| |PythonVersion| |PyPi| |CI/CD| |Downloads| |Ruff| |Contribution| |Website|
 
 .. |Licence| image:: https://img.shields.io/badge/License-BSD%203--Clause-blue.svg
-.. _Licence: https://github.com/skfolio/skfolio/blob/main/LICENSE
+   :target: https://github.com/skfolio/skfolio/blob/main/LICENSE
 
 .. |Codecov| image:: https://codecov.io/gh/skfolio/skfolio/graph/badge.svg?token=KJ0SE4LHPV
-.. _Codecov: https://codecov.io/gh/skfolio/skfolio
+   :target: https://codecov.io/gh/skfolio/skfolio
 
-.. |PythonVersion| image:: https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue
-.. _PythonVersion: https://pypi.org/project/skfolio/
+.. |PythonVersion| image:: https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue.svg
+   :target: https://pypi.org/project/skfolio/
 
 .. |PyPi| image:: https://img.shields.io/pypi/v/skfolio
-.. _PyPi: https://pypi.org/project/skfolio
+   :target: https://pypi.org/project/skfolio
 
 .. |Black| image:: https://img.shields.io/badge/code%20style-black-000000.svg
-.. _Black: https://github.com/psf/black
+   :target: https://github.com/psf/black
 
-.. |CI/CD| image:: https://img.shields.io/github/actions/workflow/status/skfolio/skfolio/release.yml?logo=github
-.. _CI/CD: https://github.com/skfolio/skfolio/raw/main/LICENSE
+.. |CI/CD| image:: https://img.shields.io/github/actions/workflow/status/skfolio/skfolio/release.yml.svg?logo=github
+   :target: https://github.com/skfolio/skfolio/raw/main/LICENSE
 
 .. |Downloads| image:: https://static.pepy.tech/badge/skfolio
-.. _Downloads: https://pepy.tech/project/skfolio
+   :target: https://pepy.tech/project/skfolio
 
 .. |Ruff| image:: https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json
-.. _Ruff: https://github.com/astral-sh/ruff
+   :target: https://github.com/astral-sh/ruff
 
 .. |Contribution| image:: https://img.shields.io/badge/Contributions-Welcome-blue
-.. _Contribution: https://github.com/skfolio/skfolio/blob/main/CONTRIBUTING.md
+   :target: https://github.com/skfolio/skfolio/blob/main/CONTRIBUTING.md
 
-.. |Website| image:: https://img.shields.io/website-up-down-53cc0d-red/http/skfolio.org
-.. _Website: https://skfolio.org
+.. |Website| image:: https://img.shields.io/website.svg?down_color=red&down_message=down&up_color=53cc0d&up_message=up&url=https://skfolio.org
+   :target: https://skfolio.org
 
 .. |PythonMinVersion| replace:: 3.10
 .. |NumpyMinVersion| replace:: 1.23.4
@@ -563,7 +563,7 @@ Black & Litterman Factor Model
 ------------------------------
 .. code-block:: python
 
-    factor_views = ["MTUM - QUAL == 0.03 ", "SIZE - TLT == 0.04", "VLUE == 0.06"]
+    factor_views = ["MTUM - QUAL == 0.03 ", "VLUE == 0.06"]
     model = MeanRisk(
         objective_function=ObjectiveFunction.MAXIMIZE_RATIO,
         prior_estimator=FactorModel(

{skfolio-0.1.3.dist-info → skfolio-0.2.1.dist-info}/RECORD

@@ -17,8 +17,8 @@ skfolio/measures/_enums.py,sha256=NJcngwg9b2JMMiekwkWU9POfnDvgfUgtYtyV2VSFDVM,89
 skfolio/measures/_measures.py,sha256=VU9tahJKJvt8PaJZNxWkmFkFU4PsN0FfYO32Je6D53E,16829
 skfolio/metrics/__init__.py,sha256=MomHJ5_bgjq4qUwGS2bfhNmG_ld0oQ4wK6y0Yy_Eonc,75
 skfolio/metrics/_scorer.py,sha256=h1VuZk-zzn4rIChHl9FvM7RxqVT3b-jR1CEB-cr9F2s,4306
-skfolio/model_selection/__init__.py,sha256=QYYm5lYyioZuPnsTu-b3lz-tCcl3Gwrx-y9IIvep13A,453
-skfolio/model_selection/_combinatorial.py,sha256=Dts2eic69ZTa8HOLcf3n1MyfakA_HxRT7JWn5WTXGlQ,14782
+skfolio/model_selection/__init__.py,sha256=8j9Z5tpbgBScjFbn8ZsCm_6rZO7RkPQ1QIF8BqYMVA8,507
+skfolio/model_selection/_combinatorial.py,sha256=DHfbnjqaOGV5bT_9pGuoR23JN6iEp8Tn0Kr6sLq1Xmg,19045
 skfolio/model_selection/_validation.py,sha256=Rs3j6LFfm8HJCnaoUXlPnNsqxIyjRmMhmGWvvJ0olXA,7686
 skfolio/model_selection/_walk_forward.py,sha256=pbMD8VM1OoKiEtrlPeCLG29xVijsq1RArSjTvGO1FnU,7539
 skfolio/moments/__init__.py,sha256=BaP6FjU-CEsV_mcC2AOKXNFy-_wXZsk-jqzJG6mTpsM,746
@@ -29,26 +29,26 @@ skfolio/moments/expected_returns/__init__.py,sha256=NETEcKKYKsQvzUU4ZIq6mgT14zdr
 skfolio/moments/expected_returns/_base.py,sha256=xk9mzi48uCOHaMTGQBMr3FU7Ai_shxYhmGeOsVwjv9Q,871
 skfolio/moments/expected_returns/_expected_returns.py,sha256=T_tt_dsYgXrjIM2REUii7_4_R8IEc3xdtuv45yYM-5o,13388
 skfolio/optimization/__init__.py,sha256=vXIbwWJL48zJ1jy7ZB2PPBVx7rZo0vVA8QQQuD-L6ts,1021
-skfolio/optimization/_base.py,sha256=O8jYu9Tv1IHIHvvcRXBCa-rjPnhKYvVn_Up6QI2ymig,5668
+skfolio/optimization/_base.py,sha256=LoRONJP70AwbFpdgqVS_g145pCx0JGkazjWvkQzT_iM,5748
 skfolio/optimization/cluster/__init__.py,sha256=M3xVdYhNKp4e9CB7hzb4yjTxkkNCHh7Mt_KGFFrkOgs,388
 skfolio/optimization/cluster/_nco.py,sha256=MKzNvDIAbqS_D41Vp7tNa7OrXYq_bYVSQEVbVCHOEWA,14834
 skfolio/optimization/cluster/hierarchical/__init__.py,sha256=YnfcPHvjwB6kcG4hoQqc0NqIJKaG7OjBtmXNbOxCq08,405
-skfolio/optimization/cluster/hierarchical/_base.py,sha256=0FtVcrMOFsQIJVaShf_qoHBRSuVmR4qzmJdvJc214HI,17255
-skfolio/optimization/cluster/hierarchical/_herc.py,sha256=JyXYX4PE17alCzIv6piF-G7_nprgzdzfYp35kjAeWMo,17235
-skfolio/optimization/cluster/hierarchical/_hrp.py,sha256=CSBfOk47uv_9tLdWTI2dnh2UXDqy8iXdBbc4rK7G7-0,16120
+skfolio/optimization/cluster/hierarchical/_base.py,sha256=BVJ8Yq2Yg3Z0iqgx0HwS2OxPLVruoSzrelyYQmt_AiQ,17281
+skfolio/optimization/cluster/hierarchical/_herc.py,sha256=p7VdEeJOD5ykA1H9FOLaEqIL6D_YYF8VXXfAqTSRdjs,17238
+skfolio/optimization/cluster/hierarchical/_hrp.py,sha256=i3bliOjWxDX3V3vekhl_Gf_MZ4HroU4r_3rAR-QnyK0,16123
 skfolio/optimization/convex/__init__.py,sha256=F6BPFikTo0B-7JCKazqLGEwM3RkgTNbFm5GAGkaq9Uo,570
-skfolio/optimization/convex/_base.py,sha256=CyEP2JXP0ISnEZRsV-tumH9wwPGBbyM6MDf1B-jCxyw,75413
-skfolio/optimization/convex/_distributionally_robust.py,sha256=nQW_MD0wlVY_tvLvRq_CvezOn4q92YC7wHfzFE9k9tY,17308
-skfolio/optimization/convex/_maximum_diversification.py,sha256=8wQn5eFEat5wixmu0cfaswAee8D5C-hzV4s5ntUoAFM,19137
-skfolio/optimization/convex/_mean_risk.py,sha256=ivAjLXis4fUZ9XOvh_iOemfnvgDAzrK3LDvrlaa2TpA,43130
-skfolio/optimization/convex/_risk_budgeting.py,sha256=wXCgn64w2alAGG-dGJ8IwFrhYVtybM-O2hXiFaXietg,23618
+skfolio/optimization/convex/_base.py,sha256=xvhgSQ5X7Lqz6kzGtldlDLIMV61gwrphW9_qMQSG498,75439
+skfolio/optimization/convex/_distributionally_robust.py,sha256=PHAZvXb_zRXpeDD90fgxVEQAuYH5EY8fTpYQ8jO9shA,17311
+skfolio/optimization/convex/_maximum_diversification.py,sha256=vqUJZdR28X75LQ18XXWLGd7yX9-f5wvOByN0UVSyd_Y,19140
+skfolio/optimization/convex/_mean_risk.py,sha256=q9aH_thsmKeK_3-8jQOLN1S9z9DXvZmYGgj0a2ezAl0,43134
+skfolio/optimization/convex/_risk_budgeting.py,sha256=pRMTA-CCTsV-yysADA3b9RDjLGPk4Jw0eP5ZVQ5W_sc,23622
 skfolio/optimization/ensemble/__init__.py,sha256=8TXxcxH2_gG3C1xtgQj9OHHr0Le8lhdejtlURL6T3ZY,158
 skfolio/optimization/ensemble/_base.py,sha256=GaNDQu6ivosYuwMrb-b0PhToCsNrmhSYyXkxeM8W4rU,3399
 skfolio/optimization/ensemble/_stacking.py,sha256=2PodXf_JahToShSAbwQRXosEer3ESOAhpsnB6SCwztk,13148
 skfolio/optimization/naive/__init__.py,sha256=Dkr55R48urC-jfYN007NTbei16N91Na_EDYLVqzhGgQ,147
-skfolio/optimization/naive/_naive.py,sha256=sadsU8TnNRf28EDLg-KZ4yJm2FvV204vdsb1MhVJyMQ,5561
+skfolio/optimization/naive/_naive.py,sha256=lXBUK0-JZd_30xUqnwv3IN1-yvKNVrub2A4ZVdfjmnY,5570
 skfolio/population/__init__.py,sha256=rsPPMUv95aTK7vmpPeQwF8NzFuBwk6RDo5g4HNaPzNM,80
-skfolio/population/_population.py,sha256=O5o8OmR7szAA6NRKvELyq2P6B14jHMUaB8LMbrS3b7E,29411
+skfolio/population/_population.py,sha256=DNBjR2Ob_Rz3B70mwLIrWd_ElOvHxDWjN3EQs-rGHCk,29148
 skfolio/portfolio/__init__.py,sha256=YYtcAPmA2zeCxFGTXegg2FXcA7py6CxOX7IMTdYuXl0,586
 skfolio/portfolio/_base.py,sha256=jO6YKXu8oxE-uldl2CayLvbA40yfeCA1vNa_xm-WcWo,38313
 skfolio/portfolio/_multi_period_portfolio.py,sha256=63RwL0oTn-3L5LON6f2e9J58zw9q8S2gQ5c8JfSnN28,22759
@@ -59,9 +59,9 @@ skfolio/preprocessing/__init__.py,sha256=15A1bzfPsbfxxXgGP1gstf4R0E_347Wn18z5W5j
 skfolio/preprocessing/_returns.py,sha256=_7UtXugQPWitNrrZ3M2dUOAun8aVr0lI45Ms6KFiS94,3826
 skfolio/prior/__init__.py,sha256=jql8NTiWlykPKJUXTOPdqm531mP8Pul1QAR6hXTXA6c,446
 skfolio/prior/_base.py,sha256=Dx6rX0X6ymDiieFOI-ik3xMNNFhYEtwLSXOdajf5wZY,1927
-skfolio/prior/_black_litterman.py,sha256=JuwVXLXY5qHETBZDg0wmBGMSQehJp_1t7c1-kanKaiU,9397
-skfolio/prior/_empirical.py,sha256=YhCYW8R3vqs3ntF4WSokuwLW6Gd98df7f8LL8zCS-D0,5740
-skfolio/prior/_factor_model.py,sha256=feQzb04-BjBN-ryba5niAhI3RRuRAcUxD8yuiNOIWsI,9642
+skfolio/prior/_black_litterman.py,sha256=sVx8113xeP4B6LA4rICKp0cgw7w3F46aQzIQY_34QwQ,9400
+skfolio/prior/_empirical.py,sha256=eHBSXVzIEvA2oBAnv6HW9D8iy3xKDxpCN_xsg8j8Ye8,5821
+skfolio/prior/_factor_model.py,sha256=xC-womM7oC91jRaIQP7MSiRPkwm5b7pkWHi-5mOb2jY,9665
 skfolio/uncertainty_set/__init__.py,sha256=LlMHtYv9G9fgtM7m4sCSToS9et57Pm2Q2gGchTVrj6c,617
 skfolio/uncertainty_set/_base.py,sha256=rZ3g2AhDKFQTPajgh6Fz5S5TTf0qM4Ie6RGxPhp32D8,3301
 skfolio/uncertainty_set/_bootstrap.py,sha256=Rig8ZGc8rEOnYygPyTaDSu5lp3wGuZrQVRoJTm3UuAA,10301
@@ -71,11 +71,11 @@ skfolio/utils/bootstrap.py,sha256=3zY2kO_GQURKEcQMCasJOSByde9Mt2IAi3KJH0_a4mk,35
 skfolio/utils/equations.py,sha256=w0HsYjA7cS0mHYsI9MpixHLkof3HN26nc14ZfqFrHlE,11047
 skfolio/utils/sorting.py,sha256=lSjMvH2L-sSj-06B3MlwBrH1rtjCeGEe4hG894W7TE0,3504
 skfolio/utils/stats.py,sha256=IP36nMc5j5Hcqjbg7lvDIsGp1GWRdOh5jU3W6Z8nkYs,13132
-skfolio/utils/tools.py,sha256=roj4zTwmfunPb8HtxcOPAsCKpk0ZPEPnQztSglE9t4o,15351
+skfolio/utils/tools.py,sha256=xa42f7U3Ki8-CJS6g8w7bKCLI_QMJ8D6LxLBjlEM7Ok,15374
 skfolio/utils/fixes/__init__.py,sha256=knHau8PRZP07XDHR59CW8VWxkpTP0gdr6RAHJrO-zaA,95
 skfolio/utils/fixes/_dendrogram.py,sha256=9aIhSnMwpQHJhQx7IpXC3jlw6YJ3H4XQnnx_d4nMllQ,13551
-skfolio-0.1.3.dist-info/LICENSE,sha256=F6Gi-ZJX5BlVzYK8R9NcvAkAsKa7KO29xB1OScbrH6Q,1526
-skfolio-0.1.3.dist-info/METADATA,sha256=JXNH0_kBjWWR-hp4XQfTtLWP5KIQW5i4pN7SK7lFpYY,19567
-skfolio-0.1.3.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-skfolio-0.1.3.dist-info/top_level.txt,sha256=NXEaoS9Ms7t32gxkb867nV0OKlU0KmssL7IJBVo0fJs,8
-skfolio-0.1.3.dist-info/RECORD,,
+skfolio-0.2.1.dist-info/LICENSE,sha256=F6Gi-ZJX5BlVzYK8R9NcvAkAsKa7KO29xB1OScbrH6Q,1526
+skfolio-0.2.1.dist-info/METADATA,sha256=OzW5QNHb_EG_jHtP5lPqWas8EAMyl6FPgS3XP6CXulQ,19585
+skfolio-0.2.1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+skfolio-0.2.1.dist-info/top_level.txt,sha256=NXEaoS9Ms7t32gxkb867nV0OKlU0KmssL7IJBVo0fJs,8
+skfolio-0.2.1.dist-info/RECORD,,