[ENH] Added Test Cases For convolution based-Classification

aeon/classification/convolution_based/tests/test_hydra.py

@@ -0,0 +1,52 @@
+"""Hydra classifier test code."""
+
+import numpy as np
+import pytest
+
+from aeon.classification.convolution_based import HydraClassifier
+from aeon.datasets import load_basic_motions, load_unit_test
+from aeon.utils.validation._dependencies import _check_soft_dependencies
+
+
+@pytest.mark.skipif(
+    not _check_soft_dependencies(["torch"], severity="none"),
+    reason="pytorch soft dependency not found.",
+)
+def test_hydra_univariate():
+    """Test of Hydra classifier on univariate."""
+    X_train, y_train = load_unit_test(split="train")
+    X_test, y_test = load_unit_test(split="test")
+
+    clf = HydraClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)
+
+
+@pytest.mark.skipif(
+    not _check_soft_dependencies(["torch"], severity="none"),
+    reason="pytorch soft dependency not found.",
+)
+def test_hydra_multivariate():
+    """Test of Hydra classifier on multivariate."""
+    X_train, y_train = load_basic_motions(split="train")
+    X_test, y_test = load_basic_motions(split="test")
+
+    clf = HydraClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)

aeon/classification/convolution_based/tests/test_minirocket.py

@@ -0,0 +1,42 @@
+"""MiniRocket classifier test code."""
+
+import numpy as np
+
+from aeon.classification.convolution_based import MiniRocketClassifier
+from aeon.datasets import load_basic_motions, load_unit_test
+
+
+def test_minirocket_univariate():
+    """Test of MiniRocket classifier on univariate."""
+    X_train, y_train = load_unit_test(split="train")
+    X_test, y_test = load_unit_test(split="test")
+
+    clf = MiniRocketClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)
+
+
+def test_minirocket_multivariate():
+    """Test of MiniRocket classifier on multivariate."""
+    X_train, y_train = load_basic_motions(split="train")
+    X_test, y_test = load_basic_motions(split="test")
+
+    clf = MiniRocketClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)

aeon/classification/convolution_based/tests/test_mr_hydra.py

@@ -0,0 +1,52 @@
+"""MultiRocketHydra classifier test code."""
+
+import numpy as np
+import pytest
+
+from aeon.classification.convolution_based import MultiRocketHydraClassifier
+from aeon.datasets import load_basic_motions, load_unit_test
+from aeon.utils.validation._dependencies import _check_soft_dependencies
+
+
+@pytest.mark.skipif(
+    not _check_soft_dependencies(["torch"], severity="none"),
+    reason="pytorch soft dependency not found.",
+)
+def test_mr_hydra_univariate():
+    """Test of MultiRocketHydra classifier on univariate."""
+    X_train, y_train = load_unit_test(split="train")
+    X_test, y_test = load_unit_test(split="test")
+
+    clf = MultiRocketHydraClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)
+
+
+@pytest.mark.skipif(
+    not _check_soft_dependencies(["torch"], severity="none"),
+    reason="pytorch soft dependency not found.",
+)
+def test_mr_hydra_multivariate():
+    """Test of MultiRocketHydra classifier on multivariate."""
+    X_train, y_train = load_basic_motions(split="train")
+    X_test, y_test = load_basic_motions(split="test")
+
+    clf = MultiRocketHydraClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)

aeon/classification/convolution_based/tests/test_multirocket.py

@@ -0,0 +1,42 @@
+"""MultiRocket classifier test code."""
+
+import numpy as np
+
+from aeon.classification.convolution_based import MultiRocketClassifier
+from aeon.datasets import load_basic_motions, load_unit_test
+
+
+def test_multirocket_univariate():
+    """Test of MultiRocket classifier on univariate."""
+    X_train, y_train = load_unit_test(split="train")
+    X_test, y_test = load_unit_test(split="test")
+
+    clf = MultiRocketClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)
+
+
+def test_multirocket_multivariate():
+    """Test of MultiRocket classifier on multivariate."""
+    X_train, y_train = load_basic_motions(split="train")
+    X_test, y_test = load_basic_motions(split="test")
+
+    clf = MultiRocketClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)

aeon/classification/convolution_based/tests/test_rocket.py

@@ -0,0 +1,42 @@
+"""RandOm Convolutional KErnel Transform (Rocket) classifier test code."""
+
+import numpy as np
+
+from aeon.classification.convolution_based import RocketClassifier
+from aeon.datasets import load_basic_motions, load_unit_test
+
+
+def test_rocket_univariate():
+    """Test of Rocket on univariate."""
+    X_train, y_train = load_unit_test(split="train")
+    X_test, y_test = load_unit_test(split="test")
+
+    clf = RocketClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)
+
+
+def test_rocket_multivariate():
+    """Test of Rocket on multivariate."""
+    X_train, y_train = load_basic_motions(split="train")
+    X_test, y_test = load_basic_motions(split="test")
+
+    clf = RocketClassifier(random_state=0)
+
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+    y_proba = clf.predict_proba(X_test)
+
+    assert clf.is_fitted
+    assert y_pred.shape == (X_test.shape[0],)
+    assert set(y_pred).issubset(set(y_train))
+    assert y_proba.shape == (X_test.shape[0], len(np.unique(y_train)))
+    assert np.all(y_proba >= 0) and np.all(y_proba <= 1)