Increase balance package test coverage (facebookresearch#281)

Summary:

The coverage report showed 98% overall coverage with 7 files having gaps. These tests cover previously untested edge cases including:

- CLI exception handling paths for weighting failures
- Sample class design effect diagnostics and IPW model parameters
- CBPS optimization convergence warnings and constraint violation exceptions
- Plotting functions with missing values, default parameters, and various dist_types
- Distance metrics with empty numeric columns

Differential Revision: D90946146

Author: talgalili

tests/test_cbps.py

@@ -1352,6 +1352,8 @@ def test_cbps_over_method_with_extreme_data_logs_warning(self) -> None:
             transformations=None,
             cbps_method="exact",
         )
+
+    def test_cbps_over_method_logs_warnings(self) -> None:
         """Test CBPS over method logs warnings when optimization fails (lines 713, 747, 765).
 
         Verifies that when optimization algorithms fail to converge, appropriate
@@ -1477,3 +1479,128 @@ def test_cbps_alpha_function_convergence_warning(self) -> None:
                 ),
                 msg=f"Expected exception to contain convergence-related message, got: {e}",
             )
+
+
+class TestCbpsOptimizationConvergenceWithMocking(balance.testutil.BalanceTestCase):
+    """Test CBPS optimization convergence warning branches using mocking (lines 689, 713, 726, 747, 765, 778).
+
+    These tests use unittest.mock to directly control scipy.optimize.minimize return values,
+    ensuring the specific warning and exception branches in _cbps_optimization are executed.
+    """
+
+    def _create_simple_test_data(self) -> tuple:
+        """Create simple test data for CBPS testing."""
+        sample_df = pd.DataFrame({"a": [1.0, 2.0, 3.0, 4.0, 5.0]})
+        target_df = pd.DataFrame({"a": [2.0, 3.0, 4.0, 5.0, 6.0]})
+        sample_weights = pd.Series([1.0] * 5)
+        target_weights = pd.Series([1.0] * 5)
+        return sample_df, sample_weights, target_df, target_weights
+
+    def test_exact_method_constraint_violation_exception(self) -> None:
+        """Test line 726: Exception when exact method constraints can't be satisfied.
+
+        Uses mocking to simulate scipy.optimize.minimize returning success=False
+        with a specific constraint violation message.
+        """
+        from unittest.mock import MagicMock, patch
+
+        sample_df, sample_weights, target_df, target_weights = (
+            self._create_simple_test_data()
+        )
+
+        def mock_minimize(fun, x0, **kwargs):
+            result = MagicMock()
+            # Simulate constraint violation failure
+            result.__getitem__ = lambda self, key: {
+                "success": np.bool_(False),
+                "message": "Did not converge to a solution satisfying the constraints",
+                "x": x0,
+                "fun": 100.0,
+            }[key]
+            return result
+
+        def mock_minimize_scalar(fun, **kwargs):
+            return {
+                "success": np.bool_(True),
+                "message": "Success",
+                "x": np.array([1.0]),
+            }
+
+        with patch(
+            "scipy.optimize.minimize_scalar", side_effect=mock_minimize_scalar
+        ), patch("scipy.optimize.minimize", side_effect=mock_minimize):
+            with self.assertRaises(Exception) as context:
+                balance_cbps.cbps(
+                    sample_df,
+                    sample_weights,
+                    target_df,
+                    target_weights,
+                    transformations=None,
+                    cbps_method="exact",
+                )
+
+            self.assertIn(
+                "no solution satisfying the constraints",
+                str(context.exception).lower(),
+                msg="Expected exception about constraint violation",
+            )
+
+    def test_over_method_both_gmm_constraint_violation_exception(self) -> None:
+        """Test line 778: Exception when over method both GMM optimizations fail with constraint violation.
+
+        Uses mocking to simulate both gmm_loss optimizations failing with constraint messages.
+        """
+        from unittest.mock import MagicMock, patch
+
+        sample_df, sample_weights, target_df, target_weights = (
+            self._create_simple_test_data()
+        )
+
+        call_count = [0]
+
+        def mock_minimize(fun, x0, **kwargs):
+            call_count[0] += 1
+            result = MagicMock()
+            if call_count[0] == 1:
+                # First call is balance_optimize - succeed
+                result.__getitem__ = lambda self, key: {
+                    "success": np.bool_(True),
+                    "message": "Success",
+                    "x": x0,
+                    "fun": 1.0,
+                }[key]
+            else:
+                # Both GMM optimizations fail with constraint violation
+                result.__getitem__ = lambda self, key: {
+                    "success": np.bool_(False),
+                    "message": "Did not converge to a solution satisfying the constraints",
+                    "x": x0,
+                    "fun": 100.0,
+                }[key]
+            return result
+
+        def mock_minimize_scalar(fun, **kwargs):
+            return {
+                "success": np.bool_(True),
+                "message": "Success",
+                "x": np.array([1.0]),
+            }
+
+        with patch(
+            "scipy.optimize.minimize_scalar", side_effect=mock_minimize_scalar
+        ), patch("scipy.optimize.minimize", side_effect=mock_minimize):
+            with self.assertRaises(Exception) as context:
+                balance_cbps.cbps(
+                    sample_df,
+                    sample_weights,
+                    target_df,
+                    target_weights,
+                    transformations=None,
+                    cbps_method="over",
+                )
+
+            self.assertIn(
+                "no solution satisfying the constraints",
+                str(context.exception).lower(),
+                msg="Expected exception about constraint violation in over method",
+            )

tests/test_cli.py

@@ -1377,3 +1377,147 @@ def test_adapt_output_empty_df_returns_empty(self) -> None:
         df = pd.DataFrame()
         result = cli.adapt_output(df)
         self.assertTrue(result.empty)
+
+    def test_cli_succeed_on_weighting_failure_with_return_df_with_original_dtypes(
+        self,
+    ) -> None:
+        """Test succeed_on_weighting_failure flag with return_df_with_original_dtypes.
+
+        Verifies lines 757-794 in cli.py - the exception handling path when
+        weighting fails and return_df_with_original_dtypes is True.
+        """
+        with (
+            tempfile.TemporaryDirectory() as temp_dir,
+            tempfile.NamedTemporaryFile("w", suffix=".csv", delete=False) as in_file,
+        ):
+            in_contents = "x,y,is_respondent,id,weight\na,b,1,1,1\na,b,0,1,1"
+            in_file.write(in_contents)
+            in_file.close()
+            out_file = os.path.join(temp_dir, "out.csv")
+            diagnostics_out_file = os.path.join(temp_dir, "diagnostics_out.csv")
+
+            parser = make_parser()
+
+            args = parser.parse_args(
+                [
+                    "--input_file",
+                    in_file.name,
+                    "--output_file",
+                    out_file,
+                    "--diagnostics_output_file",
+                    diagnostics_out_file,
+                    "--covariate_columns",
+                    "x,y",
+                    "--succeed_on_weighting_failure",
+                    "--return_df_with_original_dtypes",
+                ]
+            )
+            cli = BalanceCLI(args)
+            cli.update_attributes_for_main_used_by_adjust()
+            cli.main()
+
+            self.assertTrue(os.path.isfile(out_file))
+            self.assertTrue(os.path.isfile(diagnostics_out_file))
+
+            diagnostics_df = pd.read_csv(diagnostics_out_file)
+            self.assertIn("adjustment_failure", diagnostics_df["metric"].values)
+
+    def test_cli_ipw_method_with_model_in_adjusted_kwargs(self) -> None:
+        """Test CLI with IPW method to verify model is passed to adjust.
+
+        Verifies line 719 in cli.py where model is added to adjusted_kwargs.
+        """
+        input_dataset = _create_sample_and_target_data()
+
+        with (
+            tempfile.TemporaryDirectory() as temp_dir,
+            tempfile.NamedTemporaryFile("w", suffix=".csv", delete=False) as input_file,
+        ):
+            input_dataset.to_csv(path_or_buf=input_file)
+            input_file.close()
+            output_file = os.path.join(temp_dir, "weights_out.csv")
+            diagnostics_output_file = os.path.join(temp_dir, "diagnostics_out.csv")
+            features = "age,gender"
+
+            parser = make_parser()
+            args = parser.parse_args(
+                [
+                    "--input_file",
+                    input_file.name,
+                    "--output_file",
+                    output_file,
+                    "--diagnostics_output_file",
+                    diagnostics_output_file,
+                    "--covariate_columns",
+                    features,
+                    "--method=ipw",
+                    "--ipw_logistic_regression_kwargs",
+                    '{"solver": "lbfgs", "max_iter": 200}',
+                ]
+            )
+            cli = BalanceCLI(args)
+            cli.update_attributes_for_main_used_by_adjust()
+            cli.main()
+
+            self.assertTrue(os.path.isfile(output_file))
+            self.assertTrue(os.path.isfile(diagnostics_output_file))
+
+    def test_cli_batch_columns_empty_batches(self) -> None:
+        """Test CLI batch processing with empty batches.
+
+        Verifies lines 1082-1099, 1101-1106 in cli.py - batch processing
+        path including the empty results case.
+        """
+        with (
+            tempfile.TemporaryDirectory() as temp_dir,
+            tempfile.NamedTemporaryFile("w", suffix=".csv", delete=False) as in_file,
+        ):
+            in_contents = (
+                "x,y,is_respondent,id,weight,batch\n"
+                + ("1.0,50,1,1,1,A\n" * 50)
+                + ("2.0,60,0,1,1,A\n" * 50)
+                + ("1.0,50,1,2,1,B\n" * 50)
+                + ("2.0,60,0,2,1,B\n" * 50)
+            )
+            in_file.write(in_contents)
+            in_file.close()
+            out_file = os.path.join(temp_dir, "out.csv")
+            diagnostics_out_file = os.path.join(temp_dir, "diagnostics_out.csv")
+
+            parser = make_parser()
+            args = parser.parse_args(
+                [
+                    "--input_file",
+                    in_file.name,
+                    "--output_file",
+                    out_file,
+                    "--diagnostics_output_file",
+                    diagnostics_out_file,
+                    "--covariate_columns",
+                    "x,y",
+                    "--batch_columns",
+                    "batch",
+                ]
+            )
+            cli = BalanceCLI(args)
+            cli.update_attributes_for_main_used_by_adjust()
+            cli.main()
+
+            self.assertTrue(os.path.isfile(out_file))
+            self.assertTrue(os.path.isfile(diagnostics_out_file))
+
+            output_df = pd.read_csv(out_file)
+            self.assertTrue(len(output_df) > 0)
+
+
+class TestCliMainFunction(balance.testutil.BalanceTestCase):
+    """Test cases for CLI main() entry point function (lines 1421-1425)."""
+
+    def test_main_is_callable(self) -> None:
+        """Test that main function is callable.
+
+        Verifies lines 1421-1425 in cli.py.
+        """
+        from balance.cli import main
+
+        self.assertTrue(callable(main))