skfolio 0.8.0__py3-none-any.whl → 0.9.0__py3-none-any.whl

skfolio/population/_population.py

@@ -813,8 +813,7 @@ class Population(list):
                         )
                         + "<extra></extra>",
                         colorbar=dict(
-                            title=str(z),
-                            titleside="top",
+                            title=dict(text=str(z), side="top"),
                             tickformat=",.2%" if not z.is_ratio else None,
                         ),
                     )

skfolio/pre_selection/__init__.py

@@ -1,6 +1,7 @@
 """Pre Selection module."""
 
 from skfolio.pre_selection._drop_correlated import DropCorrelated
+from skfolio.pre_selection._drop_zero_variance import DropZeroVariance
 from skfolio.pre_selection._select_complete import SelectComplete
 from skfolio.pre_selection._select_k_extremes import SelectKExtremes
 from skfolio.pre_selection._select_non_dominated import SelectNonDominated
@@ -8,6 +9,7 @@ from skfolio.pre_selection._select_non_expiring import SelectNonExpiring
 
 __all__ = [
     "DropCorrelated",
+    "DropZeroVariance",
     "SelectComplete",
     "SelectKExtremes",
     "SelectNonDominated",

skfolio/pre_selection/_drop_zero_variance.py

@@ -0,0 +1,75 @@
+"""Pre-selection DropZeroVariance module."""
+
+# Copyright (c) 2025
+# Author: Vincent Maladiere <maladiere.vincent@gmail.com>
+# SPDX-License-Identifier: BSD-3-Clause
+
+import numpy as np
+import numpy.typing as npt
+import sklearn.base as skb
+import sklearn.feature_selection as skf
+import sklearn.utils.validation as skv
+
+
+class DropZeroVariance(skf.SelectorMixin, skb.BaseEstimator):
+    """Transformer for dropping assets with near-zero variance.
+
+    On short windows, some assets can experience a near-zero variance, making
+    the covariance matrix improper for optimization. This simple transformer drops
+    assets whose variance is below some threshold.
+
+    Parameters
+    ----------
+    threshold : float, default=1e-8
+        Minimum variance threshold. The default value is 1e-8. For daily asset returns,
+        this value filters out assets whose daily standard deviation is below 1e-4
+        (0.01%), which corresponds to an annual standard deviation of approximately
+        0.16%, assuming 252 trading days.
+
+    Attributes
+    ----------
+    to_keep_ : ndarray of shape (n_assets, )
+        Boolean array indicating which assets are remaining.
+
+    n_features_in_ : int
+        Number of assets seen during `fit`.
+
+    feature_names_in_ : ndarray of shape (`n_features_in_`,)
+        Names of assets seen during `fit`. Defined only when `X`
+        has assets names that are all strings.
+    """
+
+    to_keep_: np.ndarray
+
+    def __init__(self, threshold: float = 1e-8):
+        self.threshold = threshold
+
+    def fit(self, X: npt.ArrayLike, y=None):
+        """Fit the transformer on some assets.
+
+        Parameters
+        ----------
+        X : array-like of shape (n_observations, n_assets)
+            Price returns of the assets.
+
+        y : Ignored
+            Not used, present for API consistency by convention.
+
+        Returns
+        -------
+        self : DropZeroVariance
+            Fitted estimator.
+        """
+        X = skv.validate_data(self, X)
+        if self.threshold < 0:
+            raise ValueError(
+                f"`threshold` must be higher than 0, got {self.threshold}."
+            )
+
+        self.to_keep_ = X.var(axis=0) > self.threshold
+
+        return self
+
+    def _get_support_mask(self):
+        skv.check_is_fitted(self)
+        return self.to_keep_

{skfolio-0.8.0.dist-info → skfolio-0.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: skfolio
-Version: 0.8.0
+Version: 0.9.0
 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>, Matteo Manzi <matteomanzi09@gmail.com>

{skfolio-0.8.0.dist-info → skfolio-0.9.0.dist-info}/RECORD

@@ -83,13 +83,14 @@ skfolio/optimization/ensemble/_stacking.py,sha256=DaswFVBTghP10vHGESn6aLT7C9wgp-
 skfolio/optimization/naive/__init__.py,sha256=1QKgOuA6DoqKVOsJxWKogaGPyOir6ln-aQ28PTAbtJs,181
 skfolio/optimization/naive/_naive.py,sha256=w5lDVpn5YeO6NN5dRzSRvj-V6GpfLogOW7FVxevwZl8,6453
 skfolio/population/__init__.py,sha256=ehKwWhDJCifjhEL-QezVR0xYjzRTeyHbrEMbfWjF9cU,106
-skfolio/population/_population.py,sha256=jmfy759zm5Z0ReRBaHMHCaPHEOf8AFxqXVzYrNhaVIw,31354
+skfolio/population/_population.py,sha256=5HNSubjalwKWeukaPPGH8LKgQ9ICpcVFp4h_MtiUhak,31332
 skfolio/portfolio/__init__.py,sha256=YeDSH0ZdyE-lcbDqpNw9IOltURtoM-ewAzzcec44Q5Q,586
 skfolio/portfolio/_base.py,sha256=V81HUQ2CWmohGOeNip1dPESGnmRKQk8eDAthjkvVFhQ,40541
 skfolio/portfolio/_multi_period_portfolio.py,sha256=9z71aZL2GrV6rQ_EkIyPkK-mJ9N2ZLZCIinSScfRgfw,24412
 skfolio/portfolio/_portfolio.py,sha256=o1e1KNZAuxlC8y3zTIcaW7c2jk_LlEBCzEF8FRJht20,32791
-skfolio/pre_selection/__init__.py,sha256=3hqxwd8nAa1dBna5MrE1P5JPrM-OkSvXGyhbMq7ZKIk,511
+skfolio/pre_selection/__init__.py,sha256=6J_D0QIMi24owwJJP6vxYnIgIyWZuMzCMnpMCEpAvCo,606
 skfolio/pre_selection/_drop_correlated.py,sha256=4-PSd8R20Rcdyc8Zzcy9B2eRPEtaEkM3YXi74YKF-Pk,3839
+skfolio/pre_selection/_drop_zero_variance.py,sha256=66Mi0Fta1kdmLw0CCqa7p9AqpoBpS9B3fGPLqhb8VIU,2312
 skfolio/pre_selection/_select_complete.py,sha256=2nEvcjROMJzhAHMCHADeAiCws_tc-BMtndIkjRexL84,3902
 skfolio/pre_selection/_select_k_extremes.py,sha256=nMugK88igmscribCw_I1UnjE_O7cuIjrJF8AGuVTfiA,3082
 skfolio/pre_selection/_select_non_dominated.py,sha256=Auv7G8E1QNO96heb35oBWmFLd68LlVDRgSpcg7wpv5A,6004
@@ -113,8 +114,8 @@ skfolio/utils/equations.py,sha256=yj6-TReoPq3YaUQyAx-t4wZNbODON2T4TyA82z2SnkU,15
 skfolio/utils/sorting.py,sha256=F7gfIBfnulfDUiqvzrlR-pba4PPLJT6NH7-5s4sdRhw,3521
 skfolio/utils/stats.py,sha256=glVHo7rjwy06dl5kkULLOADMrEkVJcfXXAz-1qmYQL4,17005
 skfolio/utils/tools.py,sha256=sGJFiqc60TqXyaWoH7JdsbaFYj_bvwq3hHIk6FxDC3U,22994
-skfolio-0.8.0.dist-info/licenses/LICENSE,sha256=F6Gi-ZJX5BlVzYK8R9NcvAkAsKa7KO29xB1OScbrH6Q,1526
-skfolio-0.8.0.dist-info/METADATA,sha256=2I3oPRJjRLU5M_KQRaAx9xmrcARPZbaMuE8qu2RdSAE,22383
-skfolio-0.8.0.dist-info/WHEEL,sha256=1tXe9gY0PYatrMPMDd6jXqjfpz_B-Wqm32CPfRC58XU,91
-skfolio-0.8.0.dist-info/top_level.txt,sha256=NXEaoS9Ms7t32gxkb867nV0OKlU0KmssL7IJBVo0fJs,8
-skfolio-0.8.0.dist-info/RECORD,,
+skfolio-0.9.0.dist-info/licenses/LICENSE,sha256=F6Gi-ZJX5BlVzYK8R9NcvAkAsKa7KO29xB1OScbrH6Q,1526
+skfolio-0.9.0.dist-info/METADATA,sha256=_qGGSm5oQZaU1lYBcKTfslMYdmLJ1oe3pQK0MCTUhOQ,22383
+skfolio-0.9.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+skfolio-0.9.0.dist-info/top_level.txt,sha256=NXEaoS9Ms7t32gxkb867nV0OKlU0KmssL7IJBVo0fJs,8
+skfolio-0.9.0.dist-info/RECORD,,

{skfolio-0.8.0.dist-info → skfolio-0.9.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (77.0.3)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any