def test_evaluate_only_added_features_true(self):
"""
The boolean flag `evaluate_only_extracted_features` makes sure that only the time series based features are
filtered. This unit tests checks that
"""
augmenter = RelevantFeatureAugmenter(
feature_extraction_settings=self.extraction_settings,
evaluate_only_added_features=True,
column_value="val",
column_id="id",
column_sort="sort",
column_kind="kind")
y = pd.Series({10: 1, 500: 0})
X = pd.DataFrame(index=[10, 500])
X["pre_feature"] = 0
augmenter.set_timeseries_container(self.test_df)
augmenter.fit(X, y)
transformed_X = augmenter.transform(X.copy())
self.assertEqual(
sum(["pre_feature" == column for column in transformed_X.columns]),
1)
def test_evaluate_only_added_features_false(self):
"""
The boolean flag `evaluate_only_extracted_features` makes sure that only the time series based features are
filtered. This unit tests checks that
"""
augmenter = RelevantFeatureAugmenter(
feature_extraction_settings=self.extraction_settings,
evaluate_only_added_features=False,
column_value="val",
column_id="id",
column_sort="sort",
column_kind="kind")
df, y = self.create_test_data_sample_with_target()
X = pd.DataFrame(index=np.unique(df.id))
X["pre_drop"] = 0
X["pre_keep"] = y
augmenter.set_timeseries_container(df)
augmenter.fit(X, y)
transformed_X = augmenter.transform(X.copy())
self.assertEqual(
sum(["pre_keep" == column for column in transformed_X.columns]), 1)
self.assertEqual(
sum(["pre_drop" == column for column in transformed_X.columns]), 0)
def test_nothing_relevant(self):
augmenter = RelevantFeatureAugmenter(kind_to_fc_parameters=self.kind_to_fc_parameters,
column_value="val", column_id="id", column_sort="sort",
column_kind="kind")
y = pd.Series({10: 1, 500: 0})
X = pd.DataFrame(index=[10, 500])
augmenter.set_timeseries_container(self.test_df)
augmenter.fit(X, y)
transformed_X = augmenter.transform(X.copy())
self.assertEqual(list(transformed_X.columns), [])
self.assertEqual(list(transformed_X.index), list(X.index))
def test_nothing_relevant(self):
augmenter = RelevantFeatureAugmenter(kind_to_fc_parameters=self.kind_to_fc_parameters,
column_value="val", column_id="id", column_sort="sort",
column_kind="kind")
y = pd.Series({10: 1, 500: 0})
X = pd.DataFrame(index=[10, 500])
augmenter.set_timeseries_container(self.test_df)
augmenter.fit(X, y)
transformed_X = augmenter.transform(X.copy())
self.assertEqual(list(transformed_X.columns), [])
self.assertEqual(list(transformed_X.index), list(X.index))
def test_impute_works(self):
self.extraction_settings.kind_to_calculation_settings_mapping["a"].update({"kurtosis": None})
augmeter = RelevantFeatureAugmenter(feature_extraction_settings=self.extraction_settings,
column_value="val", column_id="id", column_sort="sort",
column_kind="kind")
y = pd.Series({10: 1, 500: 0})
X = pd.DataFrame(index=[10, 500])
augmeter.set_timeseries_container(self.test_df)
augmeter.fit(X, y)
transformed_X = augmeter.transform(X.copy())
self.assertEqual(list(transformed_X.columns), [])
self.assertEqual(list(transformed_X.index), list(X.index))
def test_nothing_relevant(self):
augmenter = RelevantFeatureAugmenter(
feature_extraction_settings=self.extraction_settings,
column_value="val",
column_id="id",
column_sort="sort",
column_kind="kind")
y = pd.Series({1: 1, 5: 0})
X = pd.DataFrame(index=[1, 5])
augmenter.set_timeseries_container(self.test_df)
augmenter.fit(X, y)
transformed_X = augmenter.transform(X.copy())
self.assertEqual(list(transformed_X.columns), [])
self.assertEqual(list(transformed_X.index), list(X.index))
def test_evaluate_only_added_features_true(self):
"""
The boolean flag `evaluate_only_extracted_features` makes sure that only the time series based features are
filtered. This unit tests checks that
"""
augmenter = RelevantFeatureAugmenter(kind_to_fc_parameters=self.kind_to_fc_parameters,
filter_only_tsfresh_features=True,
column_value="val", column_id="id", column_sort="sort", column_kind="kind")
y = pd.Series({10: 1, 500: 0})
X = pd.DataFrame(index=[10, 500])
X["pre_feature"] = 0
augmenter.set_timeseries_container(self.test_df)
augmenter.fit(X, y)
transformed_X = augmenter.transform(X.copy())
self.assertEqual(sum(["pre_feature" == column for column in transformed_X.columns]), 1)
def test_evaluate_only_added_features_false(self):
"""
The boolean flag `evaluate_only_extracted_features` makes sure that only the time series based features are
filtered. This unit tests checks that
"""
augmenter = RelevantFeatureAugmenter(kind_to_fc_parameters=self.kind_to_fc_parameters,
filter_only_tsfresh_features=False,
column_value="val", column_id="id", column_sort="sort", column_kind="kind")
df, y = self.create_test_data_sample_with_target()
X = pd.DataFrame(index=np.unique(df.id))
X["pre_drop"] = 0
X["pre_keep"] = y
augmenter.set_timeseries_container(df)
augmenter.fit(X, y)
transformed_X = augmenter.transform(X.copy())
self.assertEqual(sum(["pre_keep" == column for column in transformed_X.columns]), 1)
self.assertEqual(sum(["pre_drop" == column for column in transformed_X.columns]), 0)