Merge pull request #42 from skfolio/feature/no-issue/skfolio-datasets

[ENH] Move datasets to another repo (skfolio-datasets)

src/skfolio/datasets/_base.py

@@ -140,7 +140,10 @@ def download_dataset(
         DataFrame with each row representing one observation and each column
         representing the asset price of a given observation.
     """
-    url = f"https://github.com/skfolio/skfolio/raw/main/datasets/{data_filename}.csv.gz"
+    url = (
+        f"https://github.com/skfolio/skfolio-datasets/raw/main/"
+        f"datasets/{data_filename}.csv.gz"
+    )
 
     data_home = get_data_home(data_home=data_home)
     filepath = os.path.join(data_home, f"{data_filename}.pkz")

src/skfolio/distance/_distance.py

@@ -4,7 +4,6 @@
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
 # License: BSD 3 clause
 
-
 import numpy as np
 import numpy.typing as npt
 import pandas as pd

src/skfolio/measures/_measures.py

@@ -6,7 +6,6 @@
 # Gini mean difference and OWA GMD weights features are derived
 # from Riskfolio-Lib, Copyright (c) 2020-2023, Dany Cajas, Licensed under BSD 3 clause.
 
-
 import numpy as np
 import scipy.optimize as sco
 

src/skfolio/optimization/cluster/hierarchical/_hrp.py

@@ -6,7 +6,6 @@
 # The risk measure generalization and constraint features are derived
 # from Riskfolio-Lib, Copyright (c) 2020-2023, Dany Cajas, Licensed under BSD 3 clause.
 
-
 import numpy as np
 import numpy.typing as npt
 import pandas as pd

src/skfolio/optimization/convex/_mean_risk.py

@@ -889,9 +889,9 @@ def fit(self, X: npt.ArrayLike, y: npt.ArrayLike | None = None) -> "MeanRisk":
                             self.covariance_uncertainty_set_estimator
                         )
                         self.covariance_uncertainty_set_estimator_.fit(X, y)
-                        args[
-                            arg_name
-                        ] = self.covariance_uncertainty_set_estimator_.uncertainty_set_
+                        args[arg_name] = (
+                            self.covariance_uncertainty_set_estimator_.uncertainty_set_
+                        )
                     else:
                         args[arg_name] = getattr(self, arg_name)
 

src/skfolio/population/_population.py

@@ -1,4 +1,4 @@
-""" Population module.
+"""Population module.
 A population is a collection of portfolios.
 """
 

src/skfolio/portfolio/_base.py

@@ -37,7 +37,6 @@
 #       the class attributes with the argument name preceded by the measure name and
 #       separated by '_'.
 
-
 import warnings
 from abc import abstractmethod
 from typing import ClassVar

src/skfolio/portfolio/_portfolio.py

@@ -8,7 +8,6 @@
 # Author: Hugo Delatte <delatte.hugo@gmail.com>
 # License: BSD 3 clause
 
-
 import numbers
 from typing import ClassVar
 

tests/test_utils/test_stats.py

@@ -1,7 +1,4 @@
-from pathlib import Path
-
 import numpy as np
-import pandas as pd
 import pytest
 import scipy.cluster.hierarchy as sch
 import scipy.spatial.distance as scd
@@ -72,12 +69,6 @@ def linkage_matrix(distance):
     return linkage_matrix
 
 
-@pytest.fixture(scope="module")
-def non_psd_cov():
-    file = Path(Path(__file__).parent.parent, "data", "covariance.csv")
-    return pd.read_csv(file, sep=",").to_numpy()
-
-
 def test_n_bins_freedman(returns):
     n_bins = n_bins_freedman(returns)
     assert n_bins == 329
@@ -97,12 +88,6 @@ def test_cov_nearest(nasdaq_X):
     assert is_cholesky_dec(cov2)
 
 
-def test_cov_nearest_cov_non_psd(non_psd_cov):
-    assert not is_cholesky_dec(non_psd_cov)
-    cov = cov_nearest(non_psd_cov)
-    assert is_cholesky_dec(cov)
-
-
 def test_corr_nearest_psd():
     x = np.array([[1, -0.2, -0.9], [-0.2, 1, -0.2], [-0.9, -0.2, 1]])
     y = cov_nearest(x, higham=True)