def test_local_dask_cluster_extraction(self):
Distributor = LocalDaskDistributor(n_workers=1)
df = self.create_test_data_sample()
extracted_features = extract_features(df,
column_id="id",
column_sort="sort",
column_kind="kind",
column_value="val",
distributor=Distributor)
self.assertIsInstance(extracted_features, pd.DataFrame)
self.assertTrue(
np.all(extracted_features.a__maximum == np.array([71, 77])))
self.assertTrue(
np.all(extracted_features.a__sum_values == np.array([691, 1017])))
self.assertTrue(
np.all(
extracted_features.a__abs_energy == np.array([32211, 63167])))
self.assertTrue(
np.all(extracted_features.b__sum_values == np.array([757, 695])))
self.assertTrue(
np.all(extracted_features.b__minimum == np.array([3, 1])))
self.assertTrue(
np.all(
extracted_features.b__abs_energy == np.array([36619, 35483])))
self.assertTrue(
np.all(extracted_features.b__mean == np.array([37.85, 34.75])))
self.assertTrue(
np.all(extracted_features.b__median == np.array([39.5, 28.0])))
raw_data = pd.read_csv('data\Key Metrics_full.csv',
sep=";",
decimal=',',
index_col='Date',
parse_dates=True,
dayfirst=True,
usecols=[
'Date', 'Team Name', 'Product Category',
'Product Subcategory', 'Sales'
])
# Clean & Prep Data
clean_df = DataPrep.DataPrepping(raw_data)
del (raw_data)
clean_df['TS_ID'] = clean_df['Team Name'] + clean_df['Product Subcategory']
TS_Ready = clean_df.drop(
['Team Name', 'Product Category', 'Product Subcategory'], axis=1)
Distributor = LocalDaskDistributor(n_workers=3)
extracted_features = extract_features(timeseries_container=TS_Ready,
column_id='TS_ID',
column_sort="Salesdate",
distributor=Distributor)
extracted_features['TS_ID'] = extracted_features.index
extracted_features.to_csv('data\TSFresh Features.csv', index=False)
extracted_features.columns