fix(portfolio): add effective number of assets

docs/api.rst

@@ -76,6 +76,7 @@ Functions
     measures.ulcer_index
     measures.gini_mean_difference
     measures.owa_gmd_weights
+    measures.effective_number_assets
 
 .. _portfolio_ref:
 

src/skfolio/measures/__init__.py

@@ -16,6 +16,7 @@
     cvar,
     drawdown_at_risk,
     edar,
+    effective_number_assets,
     entropic_risk_measure,
     evar,
     first_lower_partial_moment,
@@ -73,4 +74,5 @@
     "owa_gmd_weights",
     "skew",
     "kurtosis",
+    "effective_number_assets",
 ]

src/skfolio/measures/_measures.py

@@ -611,11 +611,13 @@ def gini_mean_difference(returns: np.ndarray) -> float:
 
 
 def effective_number_assets(weights: np.ndarray) -> float:
-    r"""
-    Computes the effective number of assets, defined as the inverse of the Herfindahl index [1]_:
+    r"""Computes the effective number of assets, defined as the inverse of the
+    Herfindahl index [1]_:
+
     .. math:: N_{eff} = \frac{1}{\Vert w \Vert_{2}^{2}}
 
-    It quantifies portfolio concentration, with a higher value indicating a more diversified portfolio.
+    It quantifies portfolio concentration, with a higher value indicating a more
+    diversified portfolio.
 
     Parameters
     ----------

src/skfolio/portfolio/_portfolio.py

@@ -18,7 +18,7 @@
 import plotly.express as px
 
 import skfolio.typing as skt
-from skfolio.measures import RiskMeasure
+from skfolio.measures import RiskMeasure, effective_number_assets
 from skfolio.portfolio._base import _ZERO_THRESHOLD, BasePortfolio
 from skfolio.utils.tools import (
     args_names,
@@ -691,6 +691,28 @@ def sric(self) -> float:
             self.n_observations * self.sharpe_ratio
         )
 
+    @property
+    def effective_number_assets(self) -> float:
+        r"""Computes the effective number of assets, defined as the inverse of the
+        Herfindahl index [1]_:
+
+        .. math:: N_{eff} = \frac{1}{\Vert w \Vert_{2}^{2}}
+
+        It quantifies portfolio concentration, with a higher value indicating a more
+        diversified portfolio.
+
+        Returns
+        -------
+        value : float
+            Effective number of assets.
+
+        References
+        ----------
+        .. [1] "Banking and Financial Institutions Law in a Nutshell".
+            Lovett, William Anthony (1988)
+        """
+        return effective_number_assets(weights=self.weights)
+
     # Public methods
     def expected_returns_from_assets(
         self, assets_expected_returns: np.ndarray
@@ -817,9 +839,12 @@ def summary(self, formatted: bool = True) -> pd.Series:
         """
         df = super().summary(formatted=formatted)
         assets_number = self.n_assets
+        effective_nb_assets = self.effective_number_assets
         if formatted:
-            assets_number = str(self.n_assets)
-        df["Assets number"] = assets_number
+            assets_number = str(assets_number)
+            effective_nb_assets = str(effective_nb_assets)
+        df["Effective Number of Assets"] = effective_nb_assets
+        df["Assets Number"] = assets_number
         return df
 
     def get_weight(self, asset: str) -> float:

tests/test_portfolio/test_portfolio.py

@@ -5,6 +5,7 @@
 from copy import copy
 
 import numpy as np
+import numpy.typing as npt
 import pandas as pd
 import pytest
 import skfolio.measures as mt
@@ -24,15 +25,15 @@
 
 
 @pytest.fixture(scope="module")
-def X():
+def X() -> pd.DataFrame:
     prices = load_sp500_dataset()
     prices = prices.loc[dt.date(2017, 1, 1) :]
     X = prices_to_returns(X=prices)
     return X
 
 
 @pytest.fixture(scope="module")
-def weights():
+def weights() -> np.ndarray:
     weights = np.array([
         0.12968013,
         0.09150399,
@@ -58,6 +59,12 @@ def weights():
     return weights
 
 
+@pytest.fixture
+def portfolio(X: pd.DataFrame, weights: np.ndarray) -> Portfolio:
+    portfolio = Portfolio(X=X, weights=weights, annualized_factor=252)
+    return portfolio
+
+
 @pytest.fixture(
     scope="module",
     params=list(PerfMeasure)
@@ -88,8 +95,7 @@ def _portfolio_returns(asset_returns: np.ndarray, weights: np.array) -> np.array
     return returns
 
 
-def test_pickle(X, weights):
-    portfolio = Portfolio(X=X, weights=weights, annualized_factor=252)
+def test_pickle(portfolio):
     portfolio.sharpe_ratio = 5
     pickled = pickle.dumps(portfolio)
     unpickled = pickle.loads(pickled)
@@ -298,15 +304,27 @@ def test_portfolio_risk_contribution(X, weights):
     assert contribution.shape == (X.shape[1],)
 
 
-def test_portfolio_metrics(X, weights, measure):
-    portfolio = Portfolio(X=X, weights=weights, annualized_factor=252)
+def test_portfolio_metrics(portfolio, measure):
     m = getattr(portfolio, measure.value)
     assert isinstance(m, float)
     assert not np.isnan(m)
     assert portfolio.sric
     assert portfolio.skew
     assert portfolio.kurtosis
     assert portfolio.diversification
+    assert portfolio.effective_number_assets
+
+
+def test_portfolio_effective_number_assets(portfolio):
+    np.testing.assert_almost_equal(portfolio.effective_number_assets, 6.00342169912319)
+
+
+def test_portfolio_sric(portfolio):
+    np.testing.assert_almost_equal(portfolio.sric, -0.20309958369097764)
+
+
+def test_portfolio_diversification(portfolio):
+    np.testing.assert_almost_equal(portfolio.diversification, 1.449839842913199)
 
 
 def test_portfolio_slots(X, weights):