deprecate min cov det #294

Author: robertmartin8

docs/RiskModels.rst

@@ -44,6 +44,8 @@ covariance.
 
 .. automodule:: pypfopt.risk_models
 
+    :exclude-members: min_cov_determinant
+
     .. note::
 
         For any of these methods, if you would prefer to pass returns (the default is prices),
@@ -94,13 +96,6 @@ covariance.
         `blog post <https://reasonabledeviations.com/2018/08/15/exponential-covariance/>`_
         on my academic website.
 
-    .. autofunction:: min_cov_determinant
-
-        The minimum covariance determinant (MCD) estimator is designed to be robust to
-        outliers and 'contaminated' data [3]_. An efficient estimator is implemented in the
-        :py:mod:`sklearn.covariance` module, which is based on the algorithm presented in
-        Rousseeuw (1999) [4]_.
-
     .. autofunction:: cov_to_corr
 
     .. autofunction:: corr_to_cov

pypfopt/risk_models.py

@@ -83,8 +83,10 @@ def fix_nonpositive_semidefinite(matrix, fix_method="spectral"):
     else:
         raise NotImplementedError("Method {} not implemented".format(fix_method))
 
-    if not _is_positive_semidefinite(fixed_matrix):
-        warnings.warn("Could not fix matrix. Please try a different risk model.")
+    if not _is_positive_semidefinite(fixed_matrix):  # pragma: no cover
+        warnings.warn(
+            "Could not fix matrix. Please try a different risk model.", UserWarning
+        )
 
     # Rebuild labels if provided
     if isinstance(matrix, pd.DataFrame):
@@ -109,7 +111,6 @@ def risk_matrix(prices, method="sample_cov", **kwargs):
         - ``sample_cov``
         - ``semicovariance``
         - ``exp_cov``
-        - ``min_cov_determinant``
         - ``ledoit_wolf``
         - ``ledoit_wolf_constant_variance``
         - ``ledoit_wolf_single_factor``
@@ -127,8 +128,6 @@ def risk_matrix(prices, method="sample_cov", **kwargs):
         return semicovariance(prices, **kwargs)
     elif method == "exp_cov":
         return exp_cov(prices, **kwargs)
-    elif method == "min_cov_determinant":
-        return min_cov_determinant(prices, **kwargs)
     elif method == "ledoit_wolf" or method == "ledoit_wolf_constant_variance":
         return CovarianceShrinkage(prices, **kwargs).ledoit_wolf()
     elif method == "ledoit_wolf_single_factor":
@@ -290,6 +289,8 @@ def min_cov_determinant(
     :return: annualised estimate of covariance matrix
     :rtype: pd.DataFrame
     """
+    warnings.warn("min_cov_determinant is deprecated and will be removed in v1.5")
+
     if not isinstance(prices, pd.DataFrame):
         warnings.warn("data is not in a dataframe", RuntimeWarning)
         prices = pd.DataFrame(prices)
@@ -306,7 +307,8 @@ def min_cov_determinant(
         X = prices
     else:
         X = returns_from_prices(prices)
-    X = np.nan_to_num(X.values)
+    # X = np.nan_to_num(X.values)
+    X = X.dropna().values
     raw_cov_array = sklearn.covariance.fast_mcd(X, random_state=random_state)[1]
     cov = pd.DataFrame(raw_cov_array, index=assets, columns=assets) * frequency
     return fix_nonpositive_semidefinite(cov, kwargs.get("fix_method", "spectral"))
@@ -377,7 +379,7 @@ def __init__(self, prices, returns_data=False, frequency=252):
             from sklearn import covariance
 
             self.covariance = covariance
-        except (ModuleNotFoundError, ImportError):
+        except (ModuleNotFoundError, ImportError):  # pragma: no cover
             raise ImportError("Please install scikit-learn via pip or poetry")
 
         if not isinstance(prices, pd.DataFrame):

tests/test_risk_models.py

@@ -155,19 +155,20 @@ def test_exp_cov_limits():
     assert np.abs(S2 - sample_cov).max().max() < 1e-3
 
 
-def test_min_cov_det():
-    df = get_data()
-    S = risk_models.min_cov_determinant(df, random_state=8)
-    assert S.shape == (20, 20)
-    assert S.index.equals(df.columns)
-    assert S.index.equals(S.columns)
-    assert S.notnull().all().all()
-    # assert risk_models._is_positive_semidefinite(S)
-    # Cover that it works on np.ndarray, with a warning
-    with pytest.warns(RuntimeWarning):
-        S2 = risk_models.min_cov_determinant(df.to_numpy(), random_state=8)
-        assert isinstance(S2, pd.DataFrame)
-        np.testing.assert_equal(S.to_numpy(), S2.to_numpy())
+# def test_min_cov_det():
+#     df = get_data()
+#     S = risk_models.CovarianceShrinkage(df).ledoit_wolf()
+#     S = risk_models.min_cov_determinant(df, random_state=8)
+#     assert S.shape == (20, 20)
+#     assert S.index.equals(df.columns)
+#     assert S.index.equals(S.columns)
+#     assert S.notnull().all().all()
+#     # assert risk_models._is_positive_semidefinite(S)
+#     # Cover that it works on np.ndarray, with a warning
+#     with pytest.warns(RuntimeWarning):
+#         S2 = risk_models.min_cov_determinant(df.to_numpy(), random_state=8)
+#         assert isinstance(S2, pd.DataFrame)
+#         np.testing.assert_equal(S.to_numpy(), S2.to_numpy())
 
 
 def test_cov_to_corr():
@@ -311,7 +312,6 @@ def test_risk_matrix_and_returns_data():
         "sample_cov",
         "semicovariance",
         "exp_cov",
-        # FIXME: this fails "min_cov_determinant",
         "ledoit_wolf",
         "ledoit_wolf_constant_variance",
         "ledoit_wolf_single_factor",