def test_basic_hourly(input_df, mock_isd_weather_source):
m = HourlyLoadProfileModel(fit_cdd=True)
assert str(m).startswith("HourlyLoadProfileModel")
assert m.n is None
assert m.params is None
assert m.r2 is None
assert m.rmse is None
assert m.y is None
output = m.fit(input_df)
assert "r2" in output
assert "rmse" in output
assert "cvrmse" in output
assert "model_params" in output
assert "n" in output
assert 'formula' in m.params
assert 'X_design_info' in m.params
index = pd.date_range('2011-01-01',
freq='H',
periods=365 * 24,
tz=pytz.UTC)
formatter = ModelDataFormatter("H")
formatted_predict_data = formatter.create_demand_fixture(
index, mock_isd_weather_source)
outputs, variance = m.predict(formatted_predict_data, summed=False)
assert outputs.shape == (365 * 24, )
assert all(variance > 0)
outputs, variance = m.predict(formatted_predict_data, summed=True)
assert outputs > 0
assert variance > 0
def test_basic_hourly_to_daily(hourly_trace, mock_isd_weather_source):
mdf = ModelDataFormatter("D")
df = mdf.create_input(hourly_trace, mock_isd_weather_source)
assert all(df.columns == ["energy", "tempF"])
assert df.index[0] == datetime(2000, 1, 1, 0, tzinfo=pytz.UTC)
assert df.index.freq == 'D'
assert_allclose(df.energy, [2])
assert_allclose(df.tempF, [35.507344])
def test_basic_hourly_to_daily(hourly_trace, mock_isd_weather_source):
mdf = ModelDataFormatter("D")
df = mdf.create_input(hourly_trace, mock_isd_weather_source)
assert all(df.columns == ["energy", "tempF"])
assert df.index[0] == datetime(2000, 1, 1, 0, tzinfo=pytz.UTC)
assert df.index.freq == 'D'
assert_allclose(df.energy, [2])
assert_allclose(df.tempF, [32.])
def test_basic_15min_to_daily(fifteen_min_trace, mock_isd_weather_source):
mdf = ModelDataFormatter("D")
df = mdf.create_input(fifteen_min_trace, mock_isd_weather_source)
assert all(df.columns == ["energy", "tempF"])
assert df.index[0] == datetime(2011, 1, 1, 0, tzinfo=pytz.UTC)
assert df.index.freq == 'D'
assert df.energy.shape == (100, )
assert df.tempF.shape == (100, )
def test_daily_demand_fixture(daily_trace, mock_isd_weather_source):
mdf = ModelDataFormatter("D")
df = mdf.create_demand_fixture(daily_trace.data.index,
mock_isd_weather_source)
assert all(df.columns == ["tempF"])
assert df.index[0] == datetime(2000, 1, 1, 0, tzinfo=pytz.UTC)
assert df.index[2] == datetime(2000, 1, 3, tzinfo=pytz.UTC)
assert df.index.freq == 'D'
assert_allclose(df.tempF, [35.507344, 35.282373, 35.064391])
def test_hourly_demand_fixture(hourly_trace, monkeypatch_temperature_data,
mock_isd_weather_source):
mdf = ModelDataFormatter("H")
df = mdf.create_demand_fixture(hourly_trace.data.index,
mock_isd_weather_source)
assert all(df.columns == ["tempF"])
assert df.index[0] == datetime(2000, 1, 1, 0, tzinfo=pytz.UTC)
assert df.index[2] == datetime(2000, 1, 1, 2, tzinfo=pytz.UTC)
assert df.index.freq == 'H'
assert_allclose(df.tempF, [35.617314, 35.607664, 35.598025])
def test_hourly_demand_fixture(hourly_trace, mock_isd_weather_source):
mdf = ModelDataFormatter("H")
df = mdf.create_demand_fixture(hourly_trace.data.index,
mock_isd_weather_source)
assert all(df.columns == ["tempF"])
assert df.index[0] == datetime(2000, 1, 1, 0, tzinfo=pytz.UTC)
assert df.index[2] == datetime(2000, 1, 1, 2, tzinfo=pytz.UTC)
assert df.index.freq == 'H'
assert_allclose(df.tempF, [32., 32., 32.])
def test_basic_usage(trace, modeling_period_set, monkeypatch_temperature_data,
mock_isd_weather_source):
# create SplitModeledEnergyTrace
formatter = ModelDataFormatter('D')
model_mapping = {
'modeling_period_1': SeasonalElasticNetCVModel(65, 65),
'modeling_period_2': SeasonalElasticNetCVModel(65, 65),
}
smet = SplitModeledEnergyTrace(
trace, formatter, model_mapping, modeling_period_set)
# fit normally
outputs = smet.fit(mock_isd_weather_source)
assert 'modeling_period_1' in smet.fit_outputs
assert 'modeling_period_2' in smet.fit_outputs
assert len(smet.fit_outputs) == 2
assert outputs['modeling_period_1']['status'] == 'SUCCESS'
assert outputs['modeling_period_1']['start_date'] == \
datetime(2000, 1, 1, tzinfo=pytz.UTC)
assert outputs['modeling_period_1']['end_date'] == \
datetime(2000, 9, 1, tzinfo=pytz.UTC)
assert outputs['modeling_period_1']['n_rows'] == 245
index = pd.date_range('2001-01-01', periods=6, freq='D', tz=pytz.UTC)
demand_fixture_data = \
smet.formatter.create_demand_fixture(index, mock_isd_weather_source)
mp1_pred, variance = smet.predict(
'modeling_period_1', demand_fixture_data, summed=False)
mp2_pred = smet.predict('modeling_period_2', demand_fixture_data)
assert mp1_pred.shape == (6,)
assert mp2_pred is None
assert variance > 0
with pytest.raises(KeyError):
smet.predict('modeling_period_3', demand_fixture_data)
def callable_(formatter, model, returnme):
return returnme
mp1_deriv = smet.compute_derivative(
'modeling_period_1', callable_, {"returnme": "A"})
mp2_deriv = smet.compute_derivative(
'modeling_period_2', callable_, {"returnme": "A"})
assert mp1_deriv == "A"
assert mp2_deriv is None
pred, variance = smet.predict(
'modeling_period_1', demand_fixture_data, summed=True)
# predict summed
assert_allclose(pred, 6.035919)
assert variance > 0
# bad weather source
smet.fit(None)
assert outputs['modeling_period_1']['status'] == 'FAILURE'
def test_basic_hourly(hourly_trace, mock_isd_weather_source):
mdf = ModelDataFormatter("H")
df = mdf.create_input(hourly_trace, mock_isd_weather_source)
assert all(df.columns == ["energy", "tempF"])
assert df.index[0] == datetime(2000, 1, 1, 0, tzinfo=pytz.UTC)
assert df.index[2] == datetime(2000, 1, 1, 2, tzinfo=pytz.UTC)
assert df.index.freq == 'H'
assert_allclose(df.energy, [1, 1, np.nan])
assert_allclose(df.tempF, [32., 32., 32.])
description = mdf.describe_input(df)
assert description.get('start_date') == \
datetime(2000, 1, 1, 0, tzinfo=pytz.UTC)
assert description.get('end_date') == \
datetime(2000, 1, 1, 2, tzinfo=pytz.UTC)
assert description.get('n_rows') == 3
def test_basic_daily(daily_trace, monkeypatch_temperature_data,
mock_isd_weather_source):
mdf = ModelDataFormatter("D")
df = mdf.create_input(daily_trace, mock_isd_weather_source)
assert all(df.columns == ["energy", "tempF"])
assert df.index[0] == datetime(2000, 1, 1, tzinfo=pytz.UTC)
assert df.index[2] == datetime(2000, 1, 3, tzinfo=pytz.UTC)
assert df.index.freq == 'D'
assert_allclose(df.energy, [1, 1, 0.])
assert_allclose(df.tempF, [35.507344, 35.282373, 35.064391])
description = mdf.describe_input(df)
assert description.get('start_date') == \
datetime(2000, 1, 1, tzinfo=pytz.UTC)
assert description.get('end_date') == \
datetime(2000, 1, 3, tzinfo=pytz.UTC)
assert description.get('n_rows') == 3
missing = mdf.get_input_data_mask(df)
assert missing.shape[0] == 3
assert missing.sum() == 0
daily = mdf.daily_trace_data(daily_trace)
assert daily.shape[0] == 3
assert_allclose(daily_trace.data.value.sum(), daily.sum())
def test_basic_hourly(hourly_trace, monkeypatch_temperature_data,
mock_isd_weather_source):
mdf = ModelDataFormatter("H")
df = mdf.create_input(hourly_trace, mock_isd_weather_source)
assert all(df.columns == ["energy", "tempF"])
assert df.index[0] == datetime(2000, 1, 1, 0, tzinfo=pytz.UTC)
assert df.index[2] == datetime(2000, 1, 1, 2, tzinfo=pytz.UTC)
assert df.index.freq == 'H'
assert_allclose(df.energy, [1, 1, 0])
assert_allclose(df.tempF, [35.617314, 35.607664, 35.598025])
description = mdf.describe_input(df)
assert description.get('start_date') == \
datetime(2000, 1, 1, 0, tzinfo=pytz.UTC)
assert description.get('end_date') == \
datetime(2000, 1, 1, 2, tzinfo=pytz.UTC)
assert description.get('n_rows') == 3
missing = mdf.get_input_data_mask(df)
assert missing.shape == (3, )
assert sum(missing) == 0
daily = mdf.daily_trace_data(hourly_trace)
assert daily.shape[0] == 1
assert_allclose(hourly_trace.data.value.sum(), daily.sum())
def split_modeled_energy_trace_daily(daily_trace, modeling_period_set,
mock_isd_weather_source):
# create SplitModeledEnergyTrace
formatter = ModelDataFormatter('D')
model_mapping = {
'modeling_period_1': SeasonalElasticNetCVModel(65, 65),
'modeling_period_2': SeasonalElasticNetCVModel(65, 65),
}
smet = SplitModeledEnergyTrace(daily_trace, formatter, model_mapping,
modeling_period_set)
smet.fit(mock_isd_weather_source)
return smet
def test_bad_weather_source(trace, modeling_period_set):
# create SplitModeledEnergyTrace
formatter = ModelDataFormatter('D')
model_mapping = {
'modeling_period_1': SeasonalElasticNetCVModel(65, 65),
'modeling_period_2': SeasonalElasticNetCVModel(65, 65),
}
smet = SplitModeledEnergyTrace(
trace, formatter, model_mapping, modeling_period_set)
# need to see that it gives a data sufficiency exception
outputs = smet.fit(None)
assert 'DataSufficiencyException' in outputs['modeling_period_1']['traceback']
assert 'DataSufficiencyException' in outputs['modeling_period_2']['traceback']
def test_basic_usage(mock_isd_weather_source, reporting_period_end_date,
reporting_period_no_end_date):
formatter = ModelDataFormatter("D")
model = MockModel()
output_end_date = gross_predicted(formatter, model,
mock_isd_weather_source,
reporting_period_end_date)
output_no_end_date = gross_predicted(formatter, model,
mock_isd_weather_source,
reporting_period_no_end_date)
assert_allclose(output_end_date['gross_predicted'],
(547, 23.388031127053, 23.388031127053, 547))
assert (output_end_date['gross_predicted'][0] <
output_no_end_date['gross_predicted'][0])
def input_df(monkeypatch_temperature_data, daily_trace,
mock_isd_weather_source):
mdf = ModelDataFormatter("D")
return mdf.create_input(daily_trace, mock_isd_weather_source)
def test_empty_description():
mdf = ModelDataFormatter("H")
description = mdf.describe_input(pd.DataFrame())
assert description['start_date'] is None
assert description['end_date'] is None
assert description['n_rows'] is 0
def input_df(mock_isd_weather_source, daily_trace):
mdf = ModelDataFormatter("D")
return mdf.create_input(daily_trace, mock_isd_weather_source)
def test_empty_description():
mdf = ModelDataFormatter("H")
description = mdf.describe_input(pd.DataFrame())
assert description['start_date'] is None
assert description['end_date'] is None
assert description['n_rows'] is 0
def test_repr():
mdf = ModelDataFormatter("H")
assert str(mdf) == 'ModelDataFormatter("H")'
def test_daily_to_hourly_fails(daily_trace, mock_isd_weather_source):
mdf = ModelDataFormatter("H")
with pytest.raises(ValueError):
mdf.create_input(daily_trace, mock_isd_weather_source)
def test_daily_to_hourly_fails(daily_trace, monkeypatch_temperature_data,
mock_isd_weather_source):
mdf = ModelDataFormatter("H")
with pytest.raises(ValueError):
mdf.create_input(daily_trace, mock_isd_weather_source)
def input_df(mock_isd_weather_source, hourly_trace):
mdf = ModelDataFormatter("H")
return mdf.create_input(hourly_trace, mock_isd_weather_source)
