feat(data_preprocessing): Add unit tests and improve diagnosis mapping

- Implemented unit tests for the map_diagnosis_to_numerical function.
- Added test cases covering successful mapping, handling of missing 'diagnosis' column, and empty DataFrames.
- Fixed map_diagnosis_to_numerical to gracefully handle input DataFrames missing the 'diagnosis' column by using .get(), preventing KeyError.
- Refactored pytest fixtures (sample_data_1, sample_data_2, empty_data) into 	ests/conftest.py for shared use across test files.

Author: anibalrojosan

README.md

@@ -25,11 +25,18 @@ breast-cancer-ops/
 │   │   └── pipeline_utils.py     # Defines the scikit-learn pipeline structure
 │   └── streamlit_app.py      # Streamlit user interface for predictions
 ├── tests/                     # For unit and integration tests
+│   ├── __init__.py            # Makes 'tests' a Python package
+│   ├── conftest.py            # Shared pytest fixtures across test files
 │   ├── bash_test.sh
 │   ├── powershell_test.ps1
+│   ├── sample_payload.json    # For API/integration tests
 │   ├── unit/
-│   │   └── test_data_ingestion.py
-│   └── sample_payload.json
+│   │   ├── __init__.py           # Makes 'unit' a Python package
+│   │   ├── dat-ingestion/       # Tests for src/model/dat-ingestion.py
+│   │   │   └── test_dat-ingestion.py
+│   │   ├── data_preprocessing/   # Tests for src/model/data_preprocessing.py
+│   │   │   ├── test_drop_unnecessary_columns.py
+│   │   │   └── test_map_diagnosis_to_numerical.py
 ├── pytest.ini                 # pytest configuration
 ├── README.md                  # Project documentation
 └── requirements.txt           # Python dependencies

src/model/data_preprocessing.py

@@ -6,7 +6,12 @@ def drop_unnecessary_columns(df):
 
 def map_diagnosis_to_numerical(df):
     """Converts the 'diagnosis' column to numerical (M=1, B=0)."""
-    df['diagnosis'] = df['diagnosis'].map({'M': 1, 'B': 0})
+    # Use .get() to retrieve the 'diagnosis' Series.If 'diagnosis' doesn't exist, 
+    # .get() returns the default value, which we set to an empty Series with 
+    # the correct index. This ensures .map() is always called on a Series, 
+    # preventing KeyError.
+    diagnosis_series = df.get('diagnosis', pd.Series(index=df.index, dtype='object'))
+    df['diagnosis'] = diagnosis_series.map({'M': 1, 'B': 0})
     return df
 
 def prepare_features_and_target(df):

tests/conftest.py

@@ -18,7 +18,7 @@ def sample_data_1():
 def sample_data_2():
     'Provides a sample dataframe for testing preprocessing functions'
     data = {
-        'diagnosis': ['M', 'B', 'M'],
+#        'diagnosis': ['M', 'B', 'M'],
         'feature_1': [0.1, 0.2, 0.3],
         'feature_2': [0.4, 0.5, 0.6],
         'feature_3': [0.7, 0.8, 0.9],

tests/unit/data_preprocessing/test_map_diagnosis_to_numerical.py

@@ -18,4 +18,21 @@ def test_map_diagnosis_to_numerical_success(sample_data_1):
     # Assert that the other columns remain the same
     assert result['feature_1'].equals(sample_data_1['feature_1'])
     assert result['feature_2'].equals(sample_data_1['feature_2'])
-    assert result['feature_3'].equals(sample_data_1['feature_3'])
+    assert result['feature_3'].equals(sample_data_1['feature_3'])
+
+def test_map_diagnosis_to_numerical_missing(sample_data_2):
+    '''Test the behavior when the diagnosis column is missing in the dataframe.
+    The diagnosis column should be created and filled with NaN.'''
+    df = sample_data_2.copy()
+    result = map_diagnosis_to_numerical(df)
+
+    # Assert that diagnosis column it's created
+    assert 'diagnosis' in result.columns
+
+    # Assert that the 'diagnosis' column is filled with NaN
+    assert result['diagnosis'].isnull().all()
+
+    # Assert that the other columns remain the same
+    assert result['feature_1'].equals(sample_data_2['feature_1'])
+    assert result['feature_2'].equals(sample_data_2['feature_2'])
+    assert result['feature_3'].equals(sample_data_2['feature_3'])