fix(machine_learning): call features.any() in linear_discriminant_analysis (#15606)

In linear_discriminant_analysis, line 146 wrote if features.any: instead of calling if features.any():. Because the method object is always truthy, the else branch handling empty datasets was unreachable dead code, triggering ty warning[redundant-condition].

Call eatures.any() (matching line 107 in principal_component_analysis) and add a test case in test_linear_discriminant_analysis verifying that an empty dataset properly enters the else branch.

Validation:
- uvx ty check machine_learning/dimensionality_reduction.py -> All checks passed (0 diagnostics)
- uvx --with scipy --with scikit-learn --with numpy pytest machine_learning/dimensionality_reduction.py --doctest-modules -> 9 passed
- uvx ruff check / format -> clean

Author: hardikkaurani

machine_learning/dimensionality_reduction.py

@@ -143,7 +143,7 @@ def linear_discriminant_analysis(
     assert classes > dimensions
 
     # Check if features have been already loaded
-    if features.any:
+    if features.any():
         _, eigenvectors = eigh(
             covariance_between_classes(features, labels, classes),
             covariance_within_classes(features, labels, classes),
@@ -363,6 +363,11 @@ def test_linear_discriminant_analysis() -> None:
             )
         assert error_info.type is AssertionError
 
+    with pytest.raises(AssertionError):
+        linear_discriminant_analysis(
+            np.array([]), np.array([]), classes=2, dimensions=1
+        )
+
 
 def test_principal_component_analysis() -> None:
     features = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])