def config_with_default_periods(freq,
frequency_end_of_week=None,
frequency_step_hours=None,
frequency_step_minutes=None):
config = {
"frequency_unit": freq,
"time_column": "date",
"target_columns": ["value1"],
"long_format": False,
"decomposition_model": "multiplicative",
"expert": False
}
default_season_length = {
"12M": 4,
"6M": 2,
"3M": 4,
"M": 12,
"W": 52,
"D": 7,
"B": 5,
"H": 24,
"min": 60
}
if frequency_end_of_week:
config["frequency_end_of_week"] = frequency_end_of_week
elif frequency_step_hours:
config["frequency_step_hours"] = frequency_step_hours
elif frequency_step_minutes:
config["frequency_step_minutes"] = frequency_step_minutes
input_dataset_columns = ["value1", "value2", "country", "date"]
config["season_length_{}".format(freq)] = default_season_length[freq]
dku_config = STLConfig()
dku_config.add_parameters(config, input_dataset_columns)
return dku_config
def test_advanced_degrees(self, config, input_df, input_dataset_columns):
config["additional_parameters_STL"] = {
"seasonal_deg": "1",
"trend_deg": "1",
"low_pass_deg": "1"
}
dku_config = STLConfig()
dku_config.add_parameters(config, input_dataset_columns)
timeseries_preparator = TimeseriesPreparator(dku_config)
df_prepared = timeseries_preparator.prepare_timeseries_dataframe(
input_df)
decomposition = STLDecomposition(dku_config)
result_df = decomposition.fit(df_prepared)
assert result_df.shape == (26, 6)
np.testing.assert_array_equal(
np.round(result_df.value1_trend.values, 4),
np.array([
547017.8314, 537486.722, 528097.1954, 518846.2605, 509728.8989,
500744.2034, 491895.324, 483188.5115, 474630.5299, 466256.2782,
458496.2869, 454985.6935, 453114.0625, 452740.149, 453810.1866,
456404.7768, 463218.9767, 470913.292, 478947.2522, 487217.229,
495684.7824, 504325.6079, 513126.1746, 522081.8564,
531195.1428, 540473.2835
]))
assert np.mean(result_df["value1_trend"]) == 492101.0195351211
assert np.mean(result_df["value1_seasonal"]) == 32625.652227975654
assert np.mean(result_df["value1_residuals"]) == -5345.248686173698
config["additional_parameters_STL"] = {
"seasonal_deg": "1",
"trend_deg": "0"
}
dku_config = STLConfig()
dku_config.add_parameters(config, input_dataset_columns)
timeseries_preparator = TimeseriesPreparator(dku_config)
df_prepared = timeseries_preparator.prepare_timeseries_dataframe(
input_df)
decomposition = STLDecomposition(dku_config)
result_df = decomposition.fit(df_prepared)
assert result_df.shape == (26, 6)
np.testing.assert_array_equal(
np.round(result_df.value1_seasonal.values, 4),
np.array([
334926.5396, 363552.8324, 380642.7497, 151182.772,
-168020.8919, -209675.4339, -276299.0916, -289677.7104,
-278165.1873, -126041.2679, -8513.4181, 175315.4394,
425222.6624, 396736.9844, 290811.7923, 45628.9471, -110941.82,
-272356.2149, -303391.2037, -338667.781, -295226.877,
-106373.2845, 41186.7333, 274657.8578, 516720.1595, 432742.083
]))
assert np.mean(result_df["value1_trend"]) == 470658.0934271346
assert np.mean(result_df["value1_seasonal"]) == 40229.89887290871
assert np.mean(result_df["value1_residuals"]) == 8493.430776879803
def test_invalid_seasonal(self, advanced_config, input_dataset_columns):
dku_config = STLConfig()
advanced_config["seasonal_stl"] = 8
with pytest.raises(DSSParameterError) as odd_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "odd" in str(odd_err.value)
advanced_config["seasonal_stl"] = 9.5
with pytest.raises(DSSParameterError) as double_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "type" in str(double_err.value)
assert "int" in str(double_err.value)
advanced_config["seasonal_stl"] = "string"
with pytest.raises(DSSParameterError) as str_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "type" in str(str_err.value)
assert "int" in str(str_err.value)
advanced_config.pop("seasonal_stl")
with pytest.raises(DSSParameterError) as str_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "required" in str(str_err.value)
def test_robust_params(self, advanced_config, input_dataset_columns):
dku_config = STLConfig()
advanced_config["robust_stl"] = False
assert dku_config.add_parameters(advanced_config,
input_dataset_columns) is None
advanced_config["robust_stl"] = 42
with pytest.raises(DSSParameterError) as err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "bool" in str(err.value)
advanced_config.pop("robust_stl")
dku_config.add_parameters(advanced_config, input_dataset_columns)
assert dku_config.robust_stl == False
def test_additional_parameters(self, advanced_config,
input_dataset_columns):
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {"invalid_key": ""}
with pytest.raises(DSSParameterError) as str_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "keys" in str(str_err.value)
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {"invalid_key": "5"}
with pytest.raises(DSSParameterError) as str_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "keys" in str(str_err.value)
def test_advanced_params(self, advanced_config, input_dataset_columns):
dku_config = STLConfig()
assert dku_config.add_parameters(advanced_config,
input_dataset_columns) is None
def test_add_parameters(self, basic_config, input_dataset_columns):
dku_config = STLConfig()
assert dku_config.add_parameters(basic_config,
input_dataset_columns) is None
def test_advanced_smoothers(self, advanced_config, input_dataset_columns):
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {
"trend": "23",
"low_pass": "******"
}
dku_config.add_parameters(advanced_config, input_dataset_columns)
assert dku_config.additional_parameters_STL == {
"trend": 23,
"low_pass": 31
}
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {
"trend": "None",
"low_pass": "******"
}
dku_config.add_parameters(advanced_config, input_dataset_columns)
assert dku_config.additional_parameters_STL == {
"trend": None,
"low_pass": 31
}
advanced_config["additional_parameters_STL"] = {"trend": ""}
dku_config.add_parameters(advanced_config, input_dataset_columns)
assert dku_config.additional_parameters_STL == {"trend": None}
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {"trend": "2"}
with pytest.raises(ValueError) as str_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "odd" in str(str_err.value)
advanced_config["additional_parameters_STL"] = {"trend": "-2"}
with pytest.raises(ValueError):
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "positive" in str(str_err.value)
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {"trend": "5"}
with pytest.raises(ValueError):
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "greater" in str(str_err.value)
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {"trend": "string"}
with pytest.raises(ValueError):
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "integer" in str(str_err.value)
def test_advanced_speed_jumps(self, advanced_config,
input_dataset_columns):
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {
"seasonal_jump": "2",
"trend_jump": "3",
"low_pass_jump": "4"
}
dku_config.add_parameters(advanced_config, input_dataset_columns)
assert dku_config.additional_parameters_STL == {
"seasonal_jump": 2,
"trend_jump": 3,
"low_pass_jump": 4
}
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {
"seasonal_jump": "-1000"
}
with pytest.raises(ValueError) as str_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "positive integer" in str(str_err.value)
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {
"seasonal_jump": "string"
}
with pytest.raises(ValueError):
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "positive integer" in str(str_err.value)
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {"seasonal_jump": ""}
with pytest.raises(ValueError):
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "positive integer" in str(str_err.value)
def test_advanced_degrees(self, advanced_config, input_dataset_columns):
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {
"seasonal_deg": "1",
"trend_deg": "1",
"low_pass_deg": "1"
}
dku_config.add_parameters(advanced_config, input_dataset_columns)
assert dku_config.additional_parameters_STL == {
"seasonal_deg": 1,
"trend_deg": 1,
"low_pass_deg": 1
}
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {"seasonal_deg": "1000"}
with pytest.raises(ValueError) as str_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "must be equal to 0 or 1" in str(str_err.value)
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {
"seasonal_deg": "string"
}
with pytest.raises(ValueError) as str_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "must be equal to 0 or 1" in str(str_err.value)
dku_config = STLConfig()
advanced_config["additional_parameters_STL"] = {"low_pass_deg": ""}
with pytest.raises(ValueError) as str_err:
_ = dku_config.add_parameters(advanced_config,
input_dataset_columns)
assert "must be equal to 0 or 1" in str(str_err.value)
def dku_config(config, input_dataset_columns):
dku_config = STLConfig()
dku_config.add_parameters(config, input_dataset_columns)
return dku_config
def test_advanced_smoothers(self, config, input_df, input_dataset_columns):
config["decomposition_model"] = "additive"
config["additional_parameters_STL"] = {"trend": "35", "low_pass": "******"}
dku_config = STLConfig()
dku_config.add_parameters(config, input_dataset_columns)
timeseries_preparator = TimeseriesPreparator(dku_config)
df_prepared = timeseries_preparator.prepare_timeseries_dataframe(
input_df)
decomposition = STLDecomposition(dku_config)
result_df = decomposition.fit(df_prepared)
assert result_df.shape == (26, 6)
np.testing.assert_array_equal(
np.round(result_df.value1_seasonal.values, 4),
np.array([
329279.6394, 360305.5117, 378691.0343, 151319.491,
-166075.4661, -206300.4391, -272041.7161, -285356.053,
-274969.4078, -125368.4261, -10804.3636, 173084.5489,
421640.9531, 393264.9995, 288207.4229, 42573.3565,
-111402.3446, -270267.5348, -299889.3857, -334837.5864,
-291850.134, -103986.6224, 42205.6726, 274027.7075,
515335.6499, 429183.6225
]))
assert np.mean(result_df["value1_trend"]) == 482542.4367257319
assert np.mean(result_df["value1_seasonal"]) == 40229.62038767122
assert np.mean(result_df["value1_residuals"]) == -3390.634036480091
config["additional_parameters_STL"] = {
"trend": "2999999",
"low_pass": "******"
}
dku_config = STLConfig()
dku_config.add_parameters(config, input_dataset_columns)
timeseries_preparator = TimeseriesPreparator(dku_config)
df_prepared = timeseries_preparator.prepare_timeseries_dataframe(
input_df)
decomposition = STLDecomposition(dku_config)
result_df = decomposition.fit(df_prepared)
assert result_df.shape == (26, 6)
assert np.mean(result_df["value1_trend"]) == 476077.5935197392
assert np.mean(result_df["value1_seasonal"]) == 43303.82955718398
assert np.mean(result_df["value1_residuals"]) == -3.134258664571322e-11
config["additional_parameters_STL"] = {"trend": ""}
dku_config = STLConfig()
dku_config.add_parameters(config, input_dataset_columns)
timeseries_preparator = TimeseriesPreparator(dku_config)
df_prepared = timeseries_preparator.prepare_timeseries_dataframe(
input_df)
decomposition = STLDecomposition(dku_config)
result_df = decomposition.fit(df_prepared)
assert result_df.shape == (26, 6)
assert np.mean(result_df["value1_trend"]) == 492101.0195351211
assert np.mean(result_df["value1_seasonal"]) == 32625.652227975654
assert np.mean(result_df["value1_residuals"]) == -5345.248686173698
config["additional_parameters_STL"] = {"trend": "None"}
dku_config = STLConfig()
dku_config.add_parameters(config, input_dataset_columns)
timeseries_preparator = TimeseriesPreparator(dku_config)
df_prepared = timeseries_preparator.prepare_timeseries_dataframe(
input_df)
decomposition = STLDecomposition(dku_config)
result_df = decomposition.fit(df_prepared)
assert result_df.shape == (26, 6)
assert np.mean(result_df["value1_trend"]) == 492101.0195351211
assert np.mean(result_df["value1_seasonal"]) == 32625.652227975654
assert np.mean(result_df["value1_residuals"]) == -5345.248686173698