def test_ktrlite_span_level(make_daily_data, span_level):
train_df, test_df, coef = make_daily_data
ktrlite = KTRLiteMAP(
response_col='response',
date_col='date',
seasonality=[7, 365.25],
seasonality_fs_order=[2, 5],
span_level=span_level,
estimator_type=StanEstimatorMAP
)
ktrlite.fit(train_df)
predict_df = ktrlite.predict(test_df)
expected_columns = ['date', 'prediction_5', 'prediction', 'prediction_95']
expected_shape = (364, len(expected_columns))
expected_num_parameters = 6
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(ktrlite._posterior_samples) == expected_num_parameters
assert smape(test_df['response'].values, predict_df['prediction'].values) <= SMAPE_TOLERANCE
knots_df = ktrlite.get_level_knots()
levels_df = ktrlite.get_levels()
assert knots_df.shape[0] == round(1/span_level)
assert levels_df.shape[0] == ktrlite.num_of_observations
def test_ktrlite_level_knot_dates(make_daily_data, level_knot_dates):
train_df, test_df, coef = make_daily_data
ktrlite = KTRLiteMAP(
response_col='response',
date_col='date',
seasonality=[7, 365.25],
seasonality_fs_order=[2, 5],
level_knot_dates=level_knot_dates,
estimator_type=StanEstimatorMAP
)
ktrlite.fit(train_df)
predict_df = ktrlite.predict(test_df)
expected_columns = ['date', 'prediction_5', 'prediction', 'prediction_95']
expected_shape = (364, len(expected_columns))
expected_num_parameters = 6
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(ktrlite._posterior_samples) == expected_num_parameters
assert smape(test_df['response'].values, predict_df['prediction'].values) <= SMAPE_TOLERANCE
assert np.all(np.isin(ktrlite.level_knot_dates, level_knot_dates))
assert len(ktrlite.level_knot_dates) == len(level_knot_dates)
def test_ktrlite_predict_decompose(make_daily_data):
train_df, test_df, coef = make_daily_data
ktrlite = KTRLiteMAP(
response_col='response',
date_col='date',
seasonality=[7, 365.25],
seasonality_fs_order=[2, 5],
estimator_type=StanEstimatorMAP
)
ktrlite.fit(train_df)
predict_df = ktrlite.predict(test_df, decompose=True)
expected_columns = ['date', 'prediction_5', 'prediction', 'prediction_95',
'trend_5', 'trend', 'trend_95',
'seasonality_7_5', 'seasonality_7', 'seasonality_7_95',
'seasonality_365.25_5', 'seasonality_365.25', 'seasonality_365.25_95']
expected_shape = (364, len(expected_columns))
expected_num_parameters = 6
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(ktrlite._posterior_samples) == expected_num_parameters
assert smape(test_df['response'].values, predict_df['prediction'].values) <= SMAPE_TOLERANCE
def test_ktrlite_dual_seas(make_daily_data, seasonality_fs_order):
train_df, _, _ = make_daily_data
ktrlite = KTRLite(
response_col='response',
date_col='date',
seasonality=[7, 365.25],
seasonality_fs_order=seasonality_fs_order,
estimator='stan-map',
n_bootstrap_draws=-1,
)
ktrlite.fit(train_df)
predict_df = ktrlite.predict(train_df)
expected_columns = ['date', 'prediction']
expected_shape = (train_df.shape[0], len(expected_columns))
expected_num_parameters = 6
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(ktrlite._posterior_samples) == expected_num_parameters
smape_val = smape(train_df['response'].values,
predict_df['prediction'].values)
assert smape_val <= SMAPE_TOLERANCE
def test_ktr_seasonality(make_daily_data, seasonality, seas_segments):
train_df, _, _ = make_daily_data
ktr = KTR(
response_col='response',
date_col='date',
estimator='pyro-svi',
seasonality=seasonality,
seasonality_segments=seas_segments,
num_steps=100,
num_sample=100,
n_bootstrap_draws=-1,
)
ktr.fit(train_df)
predict_df = ktr.predict(train_df, decompose=True)
expected_columns = [
'date',
'prediction_5',
'prediction',
'prediction_95',
'trend_5',
'trend',
'trend_95',
'regression_5',
'regression',
'regression_95',
]
if len(seasonality) == 1:
expected_columns += [
'seasonality_365.25_5', 'seasonality_365.25',
'seasonality_365.25_95'
]
if len(seasonality) == 2:
expected_columns += [
'seasonality_7_5',
'seasonality_7',
'seasonality_7_95',
'seasonality_365.25_5',
'seasonality_365.25',
'seasonality_365.25_95',
]
expected_shape = (train_df.shape[0], len(expected_columns))
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert np.all(np.isfinite(predict_df['prediction'].values))
smape_val = smape(train_df['response'].values,
predict_df['prediction'].values)
assert smape_val <= SMAPE_TOLERANCE
def test_ktrx_coef_knot_distance(make_daily_data, coefficients_knot_length):
train_df, test_df, coef = make_daily_data
ktrlite = KTRLiteMAP(response_col='response',
date_col='date',
seasonality=[7, 365.25],
seasonality_fs_order=[2, 5],
estimator_type=StanEstimatorMAP)
ktrlite.fit(train_df)
level_knot_dates = ktrlite._level_knot_dates
level_knots = ktrlite._aggregate_posteriors['map']['lev_knot'][0]
seasonal_knots_input = {
'_seas_coef_knot_dates': ktrlite._coef_knot_dates,
'_sea_coef_knot': ktrlite._aggregate_posteriors['map']['coef_knot'],
'_seasonality': ktrlite._seasonality,
'_seasonality_fs_order': ktrlite._seasonality_fs_order,
}
ktrx = KTRXAggregated(
response_col='response',
date_col='date',
regressor_col=['a', 'b', 'c'],
coefficients_knot_length=coefficients_knot_length,
level_knot_dates=level_knot_dates,
level_knots=level_knots,
seasonal_knots_input=seasonal_knots_input,
estimator_type=PyroEstimatorVI,
)
ktrx.fit(train_df)
predict_df = ktrx.predict(test_df)
expected_columns = ['date', 'prediction_5', 'prediction', 'prediction_95']
expected_shape = (364, len(expected_columns))
expected_num_parameters = 7
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(ktrx._posterior_samples) == expected_num_parameters
assert smape(test_df['response'].values,
predict_df['prediction'].values) <= 0.5
def test_ktrlite_dual_seas(make_daily_data, estimator_type):
train_df, test_df, coef = make_daily_data
ktrlite = KTRLiteMAP(response_col='response',
date_col='date',
seasonality=[7, 365.25],
seasonality_fs_order=[2, 5],
estimator_type=estimator_type)
ktrlite.fit(train_df)
predict_df = ktrlite.predict(test_df)
expected_columns = ['date', 'prediction_5', 'prediction', 'prediction_95']
expected_shape = (364, len(expected_columns))
expected_num_parameters = 6
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(ktrlite._posterior_samples) == expected_num_parameters
assert smape(test_df['response'].values,
predict_df['prediction'].values) <= 0.5
def test_ktrlite_hourly_data(ca_hourly_electricity_data):
train_df, test_df = ca_hourly_electricity_data
ktrlite = KTRLite(
response_col='SDGE',
date_col='Dates',
seasonality=[24, 7, 365.25],
seasonality_fs_order=[3, 3, 5],
estimator='stan-map',
n_bootstrap_draws=-1,
)
ktrlite.fit(train_df)
predict_df = ktrlite.predict(train_df)
expected_columns = ['Dates', 'prediction']
expected_shape = (train_df.shape[0], len(expected_columns))
expected_num_parameters = 6
assert predict_df.shape == expected_shape
assert predict_df.columns.tolist() == expected_columns
assert len(ktrlite._posterior_samples) == expected_num_parameters
smape_val = smape(train_df['SDGE'].values, predict_df['prediction'].values)
assert smape_val <= SMAPE_TOLERANCE
