def full_pipeline(model_type,
predicted_column,
grain_column,
impute=True,
verbose=True):
"""
Builds the data preparation pipeline. Sequentially runs transformers and filters to clean and prepare the data.
Note advanced users may wish to use their own custom pipeline.
"""
# Note: this could be done more elegantly using FeatureUnions _if_ you are not using pandas dataframes for
# inputs of the later pipelines as FeatureUnion intrinsically converts outputs to numpy arrays.
pipeline = Pipeline([
('remove_DTS_columns', hcai_filters.DataframeColumnSuffixFilter()),
('remove_grain_column',
hcai_filters.DataframeColumnRemover(grain_column)),
# Perform one of two basic imputation methods
# TODO we need to think about making this optional to solve the problem of rare and very predictive values
('imputation',
hcai_transformers.DataFrameImputer(impute=impute, verbose=verbose)),
('null_row_filter',
hcai_filters.DataframeNullValueFilter(excluded_columns=None)),
('convert_target_to_binary',
hcai_transformers.DataFrameConvertTargetToBinary(
model_type, predicted_column)),
('prediction_to_numeric',
hcai_transformers.DataFrameConvertColumnToNumeric(predicted_column)),
('create_dummy_variables',
hcai_transformers.DataFrameCreateDummyVariables(
excluded_columns=[predicted_column])),
])
return pipeline
def test_removes_row_all_nulls_exception(self):
df = pd.DataFrame({'a': [1, None, 2, 3],
'b': ['m', 'f', None, 'f'],
'c': [3, 4, 5, None],
'd': [None, 8, 1, 3],
'label': ['Y', 'N', 'Y', 'N']})
self.assertRaises(HealthcareAIError, filters.DataframeNullValueFilter().fit_transform, df)
def test_removes_row_with_all_nulls(self):
df = pd.DataFrame({
'category': ['a', None, None],
'gender': ['F', 'M', None],
'age': [1, 5, None]
})
result = filters.DataframeNullValueFilter().fit_transform(df)
self.assertEqual(len(result), 1)
def test_removes_nothing_when_no_nulls_exist(self):
df = pd.DataFrame({
'category': ['a', 'b', 'c'],
'gender': ['F', 'M', 'F'],
'age': [1, 5, 4]
})
result = filters.DataframeNullValueFilter().fit_transform(df)
self.assertEqual(len(result), 3)
