def test_sample_cov_npd():
S = np.array([[0.03818144, 0.04182824], [0.04182824, 0.04149209]])
assert not risk_models._is_positive_semidefinite(S)
for method in {"spectral", "diag"}:
with pytest.warns(UserWarning) as w:
S2 = risk_models.fix_nonpositive_semidefinite(S, fix_method=method)
assert risk_models._is_positive_semidefinite(S2)
assert len(w) == 1
assert (
str(w[0].message) ==
"The covariance matrix is non positive semidefinite. Amending eigenvalues."
)
# Test works on DataFrame too, same results, index and columns rebuilt.
tickers = ["A", "B"]
S_df = pd.DataFrame(data=S, index=tickers, columns=tickers)
S2_df = risk_models.fix_nonpositive_semidefinite(S_df,
fix_method=method)
assert isinstance(S2_df, pd.DataFrame)
np.testing.assert_equal(S2_df.to_numpy(), S2)
assert S2_df.index.equals(S_df.index)
assert S2_df.columns.equals(S_df.columns)
with pytest.warns(UserWarning):
with pytest.raises(NotImplementedError):
risk_models.fix_nonpositive_semidefinite(S, fix_method="blah")
def test_sample_cov_npd():
S = np.array([[0.03818144, 0.04182824], [0.04182824, 0.04149209]])
assert not risk_models._is_positive_semidefinite(S)
for method in {"spectral", "diag"}:
with pytest.warns(UserWarning) as w:
S2 = risk_models.fix_nonpositive_semidefinite(S, fix_method=method)
assert risk_models._is_positive_semidefinite(S2)
assert len(w) == 1
assert (
str(w[0].message)
== "The covariance matrix is non positive semidefinite. Amending eigenvalues."
)
def test_risk_matrix_and_returns_data():
# Test the switcher method for simple calls
df = get_data()
for method in {
"sample_cov",
"semicovariance",
"exp_cov",
# FIXME: this fails "min_cov_determinant",
"ledoit_wolf",
"ledoit_wolf_constant_variance",
"ledoit_wolf_single_factor",
"ledoit_wolf_constant_correlation",
"oracle_approximating",
}:
S = risk_models.risk_matrix(df, method=method)
assert S.shape == (20, 20)
assert S.notnull().all().all()
assert risk_models._is_positive_semidefinite(S)
S2 = risk_models.risk_matrix(expected_returns.returns_from_prices(df),
returns_data=True,
method=method)
pd.testing.assert_frame_equal(S, S2)
def test_sample_cov_real_data():
df = get_data()
S = risk_models.sample_cov(df)
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)
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)
def test_semicovariance():
df = get_data()
S = risk_models.semicovariance(df)
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)
S2 = risk_models.semicovariance(df, frequency=2)
pd.testing.assert_frame_equal(S / 126, S2)
def test_oracle_approximating():
df = get_data()
cs = risk_models.CovarianceShrinkage(df)
shrunk_cov = cs.oracle_approximating()
assert 0 < cs.delta < 1
assert shrunk_cov.shape == (20, 20)
assert list(shrunk_cov.index) == list(df.columns)
assert list(shrunk_cov.columns) == list(df.columns)
assert not shrunk_cov.isnull().any().any()
assert risk_models._is_positive_semidefinite(shrunk_cov)
def test_ledoit_wolf_constant_correlation():
df = get_data()
cs = risk_models.CovarianceShrinkage(df)
shrunk_cov = cs.ledoit_wolf(shrinkage_target="constant_correlation")
assert 0 < cs.delta < 1
assert shrunk_cov.shape == (20, 20)
assert list(shrunk_cov.index) == list(df.columns)
assert list(shrunk_cov.columns) == list(df.columns)
assert not shrunk_cov.isnull().any().any()
assert risk_models._is_positive_semidefinite(shrunk_cov)
def test_shrunk_covariance():
df = get_data()
cs = risk_models.CovarianceShrinkage(df)
shrunk_cov = cs.shrunk_covariance(0.2)
assert cs.delta == 0.2
assert shrunk_cov.shape == (20, 20)
assert list(shrunk_cov.index) == list(df.columns)
assert list(shrunk_cov.columns) == list(df.columns)
assert not shrunk_cov.isnull().any().any()
assert risk_models._is_positive_semidefinite(shrunk_cov)
def test_semicovariance():
df = get_data()
S = risk_models.semicovariance(df)
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)
S2 = risk_models.semicovariance(df, frequency=2)
pd.testing.assert_frame_equal(S / 126, S2)
# Cover that it works on np.ndarray, with a warning
with pytest.warns(RuntimeWarning):
S2_np = risk_models.semicovariance(df.to_numpy(), frequency=2)
np.testing.assert_equal(S2_np, S2.to_numpy())
def test_risk_matrix_additional_kwargs():
df = get_data()
S = risk_models.sample_cov(df)
S2 = risk_models.risk_matrix(df, frequency=2)
pd.testing.assert_frame_equal(S / 126, S2)
S = risk_models.risk_matrix(
df, method="semicovariance", benchmark=0.0004, frequency=52
)
assert S.shape == (20, 20)
assert S.notnull().all().all()
assert risk_models._is_positive_semidefinite(S)
S = risk_models.risk_matrix(
expected_returns.returns_from_prices(df),
returns_data=True,
method="exp_cov",
span=60,
fix_method="diag",
)
assert S.shape == (20, 20)
assert S.notnull().all().all()
assert risk_models._is_positive_semidefinite(S)
def test_shrunk_covariance():
df = get_data()
cs = risk_models.CovarianceShrinkage(df)
shrunk_cov = cs.shrunk_covariance(0.2)
assert cs.delta == 0.2
assert shrunk_cov.shape == (20, 20)
assert list(shrunk_cov.index) == list(df.columns)
assert list(shrunk_cov.columns) == list(df.columns)
assert not shrunk_cov.isnull().any().any()
assert risk_models._is_positive_semidefinite(shrunk_cov)
with pytest.warns(RuntimeWarning) as w:
cs_numpy = risk_models.CovarianceShrinkage(df.to_numpy())
assert len(w) == 1
assert str(w[0].message) == "data is not in a dataframe"
shrunk_cov_numpy = cs_numpy.shrunk_covariance(0.2)
assert isinstance(shrunk_cov_numpy, pd.DataFrame)
np.testing.assert_equal(shrunk_cov_numpy.to_numpy(),
shrunk_cov.to_numpy())
def test_fix_npd_different_method():
df = get_data()
S = risk_models.sample_cov(df)
assert risk_models._is_positive_semidefinite(S)
S = risk_models.sample_cov(df, fix_method="diag")
assert risk_models._is_positive_semidefinite(S)
def test_is_positive_semidefinite():
a = np.zeros((100, 100))
assert risk_models._is_positive_semidefinite(a)
