def test2_ig(self):
input_df = pd.read_csv("test/data/feature_selection/tree_based_test_input.csv")
input_df_dt = direct_type_generator(input_df, ['uri'], hierarchy=True)
expected_df = pd.read_csv("test/data/feature_selection/tree_based_test2_expected.csv")
output_df = tree_based_filter(input_df_dt, 'europe', metric='IG')
pd.testing.assert_frame_equal(output_df, expected_df, check_like=True)
def transform(self, X, y=None):
X = direct_type_generator(X,
self.columns,
self.endpoint,
self.uri_data_model,
self.progress,
self.prefix,
self.regex_filter,
self.result_type,
self.bundled_mode,
self.hierarchy,
self.prefix_lookup,
caching=self.caching)
return X
def test2_no_pruning_correlation(self):
df = pd.DataFrame({
'entities': ['Paris', 'Buenos Aires', 'Mannheim', "München"],
'link': ['http://dbpedia.org/resource/Paris', 'http://dbpedia.org/resource/Buenos_Aires',
'http://dbpedia.org/resource/Mannheim', 'http://dbpedia.org/resource/Munich']
})
expected_df = pd.read_csv("test\data\feature_selection\hierarchy_based_test2_expected.csv")
input_df = direct_type_generator(df, ["link"], regex_filter=['A'], result_type="boolean", bundled_mode=True, hierarchy=True)
output_df = hierarchy_based_filter(input_df, "link", threshold=0.99, G=input_DG, metric="correlation", pruning=False)
pd.testing.assert_frame_equal(output_df, expected_df, check_like=True)
