chore(release): v1.1.0 (#80)

docs/_autosummary/xeofs.models.OPA.rst

@@ -0,0 +1,34 @@
+xeofs.models.OPA
+================
+
+.. currentmodule:: xeofs.models
+
+.. autoclass:: OPA
+   :members:
+   :show-inheritance: 
+   :inherited-members:
+
+
+   .. automethod:: __init__
+
+
+   .. rubric:: Methods
+
+   .. autosummary::
+
+      ~OPA.__init__
+      ~OPA.components
+      ~OPA.compute
+      ~OPA.decorrelation_time
+      ~OPA.filter_patterns
+      ~OPA.fit
+      ~OPA.get_params
+      ~OPA.inverse_transform
+      ~OPA.scores
+      ~OPA.transform
+
+
+
+
+
+

docs/api_core_methods.rst

@@ -6,4 +6,5 @@ Core methods
    :recursive:
 
    xeofs.models.EOF
+   xeofs.models.OPA
    xeofs.models.MCA

docs/models.rst

@@ -26,6 +26,17 @@ The supported models in ``xeofs`` currently include:
       Uncovers co-varying patterns between two sets of data.
 
 
+.. grid:: 2
+
+    .. grid-item-card::  Optimal Persistence Analysis (OPA)
+      :link: api_core_methods
+      :link-type: doc
+
+
+      Identifies the optimal persistence patterns (OPP) with the largest decorrelation time.
+
+
+
 Enhanced Interpretability
 ---------------------------
 

tests/models/test_decomposer.py

@@ -40,25 +40,97 @@ def test_init(decomposer):
     assert decomposer.solver_kwargs["random_state"] == 42
 
 
-def test_fit(decomposer, mock_data_array):
+def test_fit_full(mock_data_array):
+    decomposer = Decomposer(n_modes=2, solver="full")
     decomposer.fit(mock_data_array)
-    assert "scores_" in decomposer.__dict__
-    assert "singular_values_" in decomposer.__dict__
-    assert "components_" in decomposer.__dict__
+    assert "U_" in decomposer.__dict__
+    assert "s_" in decomposer.__dict__
+    assert "V_" in decomposer.__dict__
 
+    # Check that indeed 2 modes are returned
+    assert decomposer.U_.shape[1] == 2
+    assert decomposer.s_.shape[0] == 2
+    assert decomposer.V_.shape[1] == 2
 
-def test_fit_dask(mock_dask_data_array):
+
+def test_fit_full_matrices(mock_data_array):
+    decomposer = Decomposer(n_modes=2, solver="full", full_matrices=False)
+    decomposer.fit(mock_data_array)
+    assert "U_" in decomposer.__dict__
+    assert "s_" in decomposer.__dict__
+    assert "V_" in decomposer.__dict__
+
+    # Check that indeed 2 modes are returned
+    assert decomposer.U_.shape[1] == 2
+    assert decomposer.s_.shape[0] == 2
+    assert decomposer.V_.shape[1] == 2
+
+
+def test_fit_randomized(mock_data_array):
+    decomposer = Decomposer(n_modes=2, solver="randomized", random_state=42)
+    decomposer.fit(mock_data_array)
+    assert "U_" in decomposer.__dict__
+    assert "s_" in decomposer.__dict__
+    assert "V_" in decomposer.__dict__
+
+    # Check that indeed 2 modes are returned
+    assert decomposer.U_.shape[1] == 2
+    assert decomposer.s_.shape[0] == 2
+    assert decomposer.V_.shape[1] == 2
+
+
+def test_fit_dask_full(mock_dask_data_array):
     # The Dask SVD solver has no parameter 'random_state' but 'seed' instead,
     # so let's create a new decomposer for this case
-    decomposer = Decomposer(n_modes=2, seed=42)
+    decomposer = Decomposer(n_modes=2, solver="full")
     decomposer.fit(mock_dask_data_array)
-    assert "scores_" in decomposer.__dict__
-    assert "singular_values_" in decomposer.__dict__
-    assert "components_" in decomposer.__dict__
+    assert "U_" in decomposer.__dict__
+    assert "s_" in decomposer.__dict__
+    assert "V_" in decomposer.__dict__
+
+    # Check if the Dask SVD solver has been used
+    assert isinstance(decomposer.U_.data, DaskArray)
+    assert isinstance(decomposer.s_.data, DaskArray)
+    assert isinstance(decomposer.V_.data, DaskArray)
+
+    # Check that indeed 2 modes are returned
+    assert decomposer.U_.shape[1] == 2
+    assert decomposer.s_.shape[0] == 2
+    assert decomposer.V_.shape[1] == 2
+
+
+def test_fit_dask_randomized(mock_dask_data_array):
+    # The Dask SVD solver has no parameter 'random_state' but 'seed' instead,
+    # so let's create a new decomposer for this case
+    decomposer = Decomposer(n_modes=2, solver="randomized", seed=42)
+    decomposer.fit(mock_dask_data_array)
+    assert "U_" in decomposer.__dict__
+    assert "s_" in decomposer.__dict__
+    assert "V_" in decomposer.__dict__
+
+    # Check if the Dask SVD solver has been used
+    assert isinstance(decomposer.U_.data, DaskArray)
+    assert isinstance(decomposer.s_.data, DaskArray)
+    assert isinstance(decomposer.V_.data, DaskArray)
+
+    # Check that indeed 2 modes are returned
+    assert decomposer.U_.shape[1] == 2
+    assert decomposer.s_.shape[0] == 2
+    assert decomposer.V_.shape[1] == 2
 
 
-def test_fit_complex(decomposer, mock_complex_data_array):
+def test_fit_complex(mock_complex_data_array):
+    decomposer = Decomposer(n_modes=2, solver="randomized", random_state=42)
     decomposer.fit(mock_complex_data_array)
-    assert "scores_" in decomposer.__dict__
-    assert "singular_values_" in decomposer.__dict__
-    assert "components_" in decomposer.__dict__
+    assert "U_" in decomposer.__dict__
+    assert "s_" in decomposer.__dict__
+    assert "V_" in decomposer.__dict__
+
+    # Check that indeed 2 modes are returned
+    assert decomposer.U_.shape[1] == 2
+    assert decomposer.s_.shape[0] == 2
+    assert decomposer.V_.shape[1] == 2
+
+    # Check that U and V are complex
+    assert np.iscomplexobj(decomposer.U_.data)
+    assert np.iscomplexobj(decomposer.V_.data)

tests/models/test_eof.py

@@ -17,6 +17,7 @@ def test_init():
         "standardize": True,
         "use_coslat": True,
         "use_weights": False,
+        "solver": "auto",
     }
 
     # Assert preprocessor has been initialized
@@ -258,6 +259,7 @@ def test_get_params():
         "standardize": True,
         "use_coslat": True,
         "use_weights": False,
+        "solver": "auto",
     }
 
 
@@ -273,7 +275,7 @@ def test_transform(dim, mock_data_array):
     """Test projecting new unseen data onto the components (EOFs/eigenvectors)"""
 
     # Create a xarray DataArray with random data
-    model = EOF(n_modes=5, solver_kwargs={"random_state": 0})
+    model = EOF(n_modes=5, solver="full")
     model.fit(mock_data_array, dim)
     scores = model.scores()