SIENTIAPDE-1241: Added remaining training repository tests

tests/utils/repository/test_training_repository.py

@@ -1,6 +1,7 @@
 """Unit tests for TrainingRepository."""
 
-from unittest.mock import MagicMock
+from io import BytesIO
+from unittest.mock import MagicMock, patch
 
 import numpy as np
 import pandas as pd
@@ -466,3 +467,263 @@ class TestAfterTrainCalculation:
         # Verify inverse_transform was called
         assert mock_scaler.inverse_transform.called
         assert result.y_pred is not None
+
+
+class TestTrain:
+    """Tests for train method."""
+
+    @pytest.fixture
+    def sample_csv_data(self):
+        """Create sample CSV data in BytesIO."""
+        csv_content = """var1,var2,var3,target
+1.0,2.0,3.0,10.0
+2.0,3.0,4.0,15.0
+3.0,4.0,5.0,20.0
+4.0,5.0,6.0,25.0
+5.0,6.0,7.0,30.0
+6.0,7.0,8.0,35.0
+7.0,8.0,9.0,40.0
+8.0,9.0,10.0,45.0
+9.0,10.0,11.0,50.0
+10.0,11.0,12.0,55.0
+"""
+        return BytesIO(csv_content.encode('utf-8'))
+
+    @patch('model_manager.utils.repository.training_repository.split_train_test')
+    @patch('model_manager.utils.repository.training_repository.load_data')
+    def test_train_basic_workflow(
+        self, mock_load_data, mock_split_train_test, training_repo, sample_params, sample_csv_data
+    ):
+        """Test basic training workflow."""
+        # Mock load_data to return a DataFrame
+        mock_df = pd.DataFrame({
+            'var1': [1, 2, 3, 4, 5],
+            'var2': [2, 3, 4, 5, 6],
+            'var3': [3, 4, 5, 6, 7],
+            'target': [10, 15, 20, 25, 30],
+        })
+        mock_load_data.return_value = mock_df
+
+        # Mock split_train_test to return train/test splits
+        x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
+        x_test = pd.DataFrame({'var1': [4, 5], 'var2': [5, 6], 'var3': [6, 7]})
+        y_train = pd.Series([10, 15, 20], name='target')
+        y_test = pd.Series([25, 30], name='target')
+        mock_split_train_test.return_value = (x_train, x_test, y_train, y_test)
+
+        result = training_repo.train(sample_csv_data, sample_params)
+
+        # Verify result structure
+        assert result is not None
+        assert isinstance(result, TrainModelResult)
+        assert result.regr is not None
+        assert result.x_train is not None
+        assert result.x_test is not None
+        assert result.y_train is not None
+        assert result.y_test is not None
+        assert result.process_data is not None
+        assert result.scaler_dict is not None
+
+        # Verify load_data was called correctly
+        mock_load_data.assert_called_once_with(
+            sample_csv_data, sample_params.line_separator, sample_params.decimal_separator
+        )
+
+        # Verify split was called
+        assert mock_split_train_test.called
+
+    @patch('model_manager.utils.repository.training_repository.split_train_test')
+    @patch('model_manager.utils.repository.training_repository.load_data')
+    def test_train_with_scaler(
+        self, mock_load_data, mock_split_train_test, training_repo, sample_params, sample_csv_data
+    ):
+        """Test training with scaler enabled."""
+        sample_params.use_scaler = True
+
+        mock_df = pd.DataFrame({
+            'var1': [1, 2, 3, 4, 5],
+            'var2': [2, 3, 4, 5, 6],
+            'var3': [3, 4, 5, 6, 7],
+            'target': [10, 15, 20, 25, 30],
+        })
+        mock_load_data.return_value = mock_df
+
+        x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
+        x_test = pd.DataFrame({'var1': [4, 5], 'var2': [5, 6], 'var3': [6, 7]})
+        y_train = pd.Series([10, 15, 20], name='target')
+        y_test = pd.Series([25, 30], name='target')
+        mock_split_train_test.return_value = (x_train, x_test, y_train, y_test)
+
+        result = training_repo.train(sample_csv_data, sample_params)
+
+        assert result is not None
+        assert result.scaler_dict is not None
+
+    @patch('model_manager.utils.repository.training_repository.split_train_test')
+    @patch('model_manager.utils.repository.training_repository.load_data')
+    def test_train_with_shuffle_enabled(
+        self, mock_load_data, mock_split_train_test, training_repo, sample_params, sample_csv_data
+    ):
+        """Test training with shuffle enabled."""
+        sample_params.shuffle = True
+
+        mock_df = pd.DataFrame({
+            'var1': [1, 2, 3, 4, 5],
+            'var2': [2, 3, 4, 5, 6],
+            'var3': [3, 4, 5, 6, 7],
+            'target': [10, 15, 20, 25, 30],
+        })
+        mock_load_data.return_value = mock_df
+
+        x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
+        x_test = pd.DataFrame({'var1': [4, 5], 'var2': [5, 6], 'var3': [6, 7]})
+        y_train = pd.Series([10, 15, 20], name='target')
+        y_test = pd.Series([25, 30], name='target')
+        mock_split_train_test.return_value = (x_train, x_test, y_train, y_test)
+
+        result = training_repo.train(sample_csv_data, sample_params)
+
+        # Verify split was called with shuffle=True
+        call_kwargs = mock_split_train_test.call_args[1]
+        assert call_kwargs['shuffle'] is True
+
+    @patch('model_manager.utils.repository.training_repository.split_train_test')
+    @patch('model_manager.utils.repository.training_repository.load_data')
+    def test_train_with_different_train_size(
+        self, mock_load_data, mock_split_train_test, training_repo, sample_params, sample_csv_data
+    ):
+        """Test training with different train size."""
+        sample_params.train_size = 70
+
+        mock_df = pd.DataFrame({
+            'var1': [1, 2, 3, 4, 5],
+            'var2': [2, 3, 4, 5, 6],
+            'var3': [3, 4, 5, 6, 7],
+            'target': [10, 15, 20, 25, 30],
+        })
+        mock_load_data.return_value = mock_df
+
+        x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
+        x_test = pd.DataFrame({'var1': [4, 5], 'var2': [5, 6], 'var3': [6, 7]})
+        y_train = pd.Series([10, 15, 20], name='target')
+        y_test = pd.Series([25, 30], name='target')
+        mock_split_train_test.return_value = (x_train, x_test, y_train, y_test)
+
+        result = training_repo.train(sample_csv_data, sample_params)
+
+        # Verify split was called with train_size=0.7
+        call_kwargs = mock_split_train_test.call_args[1]
+        assert call_kwargs['train_size'] == 0.7
+
+    @patch('model_manager.utils.repository.training_repository.split_train_test')
+    @patch('model_manager.utils.repository.training_repository.load_data')
+    def test_train_raises_on_empty_data_after_transform(
+        self, mock_load_data, mock_split_train_test, training_repo, sample_params, sample_csv_data
+    ):
+        """Test that ValueError is raised when transformed data is empty."""
+        # Mock load_data to return empty DataFrame
+        mock_df = pd.DataFrame({
+            'var1': [],
+            'var2': [],
+            'var3': [],
+            'target': [],
+        })
+        mock_load_data.return_value = mock_df
+
+        with pytest.raises(ValueError, match='Data view is empty after transformation'):
+            training_repo.train(sample_csv_data, sample_params)
+
+    @patch('model_manager.utils.repository.training_repository.split_train_test')
+    @patch('model_manager.utils.repository.training_repository.load_data')
+    def test_train_logs_success(
+        self,
+        mock_load_data,
+        mock_split_train_test,
+        training_repo,
+        mock_logger,
+        sample_params,
+        sample_csv_data,
+    ):
+        """Test that training success is logged."""
+        mock_df = pd.DataFrame({
+            'var1': [1, 2, 3, 4, 5],
+            'var2': [2, 3, 4, 5, 6],
+            'var3': [3, 4, 5, 6, 7],
+            'target': [10, 15, 20, 25, 30],
+        })
+        mock_load_data.return_value = mock_df
+
+        x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
+        x_test = pd.DataFrame({'var1': [4, 5], 'var2': [5, 6], 'var3': [6, 7]})
+        y_train = pd.Series([10, 15, 20], name='target')
+        y_test = pd.Series([25, 30], name='target')
+        mock_split_train_test.return_value = (x_train, x_test, y_train, y_test)
+
+        training_repo.train(sample_csv_data, sample_params)
+
+        # Verify success was logged
+        mock_logger.info.assert_called()
+        assert any(
+            'Model trained successfully' in str(call) for call in mock_logger.info.call_args_list
+        )
+
+    @patch('model_manager.utils.repository.training_repository.split_train_test')
+    @patch('model_manager.utils.repository.training_repository.load_data')
+    def test_train_with_custom_separators(
+        self, mock_load_data, mock_split_train_test, training_repo, sample_params, sample_csv_data
+    ):
+        """Test training with custom line and decimal separators."""
+        sample_params.line_separator = ';'
+        sample_params.decimal_separator = ','
+
+        mock_df = pd.DataFrame({
+            'var1': [1, 2, 3, 4, 5],
+            'var2': [2, 3, 4, 5, 6],
+            'var3': [3, 4, 5, 6, 7],
+            'target': [10, 15, 20, 25, 30],
+        })
+        mock_load_data.return_value = mock_df
+
+        x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
+        x_test = pd.DataFrame({'var1': [4, 5], 'var2': [5, 6], 'var3': [6, 7]})
+        y_train = pd.Series([10, 15, 20], name='target')
+        y_test = pd.Series([25, 30], name='target')
+        mock_split_train_test.return_value = (x_train, x_test, y_train, y_test)
+
+        training_repo.train(sample_csv_data, sample_params)
+
+        # Verify load_data was called with custom separators
+        mock_load_data.assert_called_once_with(sample_csv_data, ';', ',')
+
+    @patch('model_manager.utils.repository.training_repository.split_train_test')
+    @patch('model_manager.utils.repository.training_repository.load_data')
+    def test_train_result_contains_all_fields(
+        self, mock_load_data, mock_split_train_test, training_repo, sample_params, sample_csv_data
+    ):
+        """Test that TrainModelResult contains all expected fields."""
+        mock_df = pd.DataFrame({
+            'var1': [1, 2, 3, 4, 5],
+            'var2': [2, 3, 4, 5, 6],
+            'var3': [3, 4, 5, 6, 7],
+            'target': [10, 15, 20, 25, 30],
+        })
+        mock_load_data.return_value = mock_df
+
+        x_train = pd.DataFrame({'var1': [1, 2, 3], 'var2': [2, 3, 4], 'var3': [3, 4, 5]})
+        x_test = pd.DataFrame({'var1': [4, 5], 'var2': [5, 6], 'var3': [6, 7]})
+        y_train = pd.Series([10, 15, 20], name='target')
+        y_test = pd.Series([25, 30], name='target')
+        mock_split_train_test.return_value = (x_train, x_test, y_train, y_test)
+
+        result = training_repo.train(sample_csv_data, sample_params)
+
+        # Verify all expected fields are present
+        assert hasattr(result, 'params')
+        assert hasattr(result, 'process_data')
+        assert hasattr(result, 'x_train')
+        assert hasattr(result, 'x_test')
+        assert hasattr(result, 'y_train')
+        assert hasattr(result, 'y_test')
+        assert hasattr(result, 'regr')
+        assert hasattr(result, 'scaler_dict')
+        assert result.params == sample_params