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_does_nothing_on_regression(self):
df = pd.DataFrame({
'category': ['a', 'b', 'c'],
'gender': ['F', 'M', 'F'],
'outcome': [1, 5, 4],
'string_outcome': ['Y', 'N', 'Y']
})
result = transformers.DataFrameConvertTargetToBinary('regression', 'string_outcome').fit_transform(df)
self.assertTrue(df.equals(result))
def test_converts_y_n_for_classification(self):
df = pd.DataFrame({
'category': ['a', 'b', 'c'],
'gender': ['F', 'M', 'F'],
'outcome': [1, 5, 4],
'string_outcome': ['Y', 'N', 'Y']
})
expected = pd.DataFrame({
'category': ['a', 'b', 'c'],
'gender': ['F', 'M', 'F'],
'outcome': [1, 5, 4],
'string_outcome': [1, 0, 1]
})
result = transformers.DataFrameConvertTargetToBinary('classification', 'string_outcome').fit_transform(df)
self.assertTrue(expected.equals(result))