def test_generate_holiday_events3():
"""Tests generate_holiday_events pre_post_num_dict parameter"""
# Tests pre_post_num_dict
countries = ["UnitedStates", "India"]
year_start = 2019
year_end = 2020
holidays_to_model_separately = [
"New Year's Day",
"Diwali",
"Columbus Day"
]
pre_num = 2
post_num = 2
pre_post_num_dict = {
"New Year's Day": (0, 2),
"Columbus Day": (1, 3)}
daily_event_df_dict = generate_holiday_events(
countries=countries,
holidays_to_model_separately=holidays_to_model_separately,
year_start=year_start,
year_end=year_end,
pre_num=pre_num,
post_num=post_num,
pre_post_num_dict=pre_post_num_dict)
# expected
expected_holidays = [
"New Years Day_plus_2",
"Diwali_minus_2",
"Diwali_plus_2",
"Columbus Day_minus_1",
"Columbus Day_plus_3"
]
assert all([holiday in daily_event_df_dict.keys() for holiday in expected_holidays])
unexpected_holidays = [
"New Years Day_minus_1",
"New Years Day_plus_3",
"Diwali_minus_3",
"Diwali_plus_3",
"Columbus Day_minus_2",
"Columbus Day_plus_4"
]
assert not any([holiday in daily_event_df_dict.keys() for holiday in unexpected_holidays])
with pytest.warns(UserWarning) as record:
pre_post_num_dict = {"Bank Holiday": (1, 1)}
generate_holiday_events(
countries=countries,
holidays_to_model_separately=holidays_to_model_separately,
year_start=year_start,
year_end=year_end,
pre_num=pre_num,
post_num=post_num,
pre_post_num_dict=pre_post_num_dict)
assert "Requested holiday 'Bank Holiday' is not valid. Valid holidays are" in record[0].message.args[0]
def test_generate_holiday_events():
"""Tests generate_holiday_events"""
countries = ["UnitedStates", "UnitedKingdom", "India", "France"]
year_start = 2019
year_end = 2020
holidays_to_model_separately = [
"New Year's Day",
"Christmas Day",
"Independence Day",
"Thanksgiving",
"Labor Day",
"Good Friday",
"Easter Monday [England, Wales, Northern Ireland]",
"Memorial Day",
"Veterans Day"]
pre_num = 2
post_num = 2
daily_event_df_dict = generate_holiday_events(
countries=countries,
holidays_to_model_separately=holidays_to_model_separately,
year_start=year_start,
year_end=year_end,
pre_num=pre_num,
post_num=post_num)
cleaned_holidays = [
holiday.replace("'", "") for holiday in holidays_to_model_separately]
cleaned_holidays += ["Other"] # default value is "Other"
expected_holidays = cleaned_holidays.copy()
for i in range(1, pre_num+1):
expected_holidays += [f"{holiday}_minus_{i}" for holiday in cleaned_holidays]
for i in range(1, post_num+1):
expected_holidays += [f"{holiday}_plus_{i}" for holiday in cleaned_holidays]
assert set(expected_holidays) == set(list(daily_event_df_dict.keys()))
assert daily_event_df_dict["Christmas Day"].equals(pd.DataFrame({
EVENT_DF_DATE_COL: [datetime.datetime(2019, 12, 25), datetime.datetime(2020, 12, 25)],
EVENT_DF_LABEL_COL: [EVENT_INDICATOR, EVENT_INDICATOR]
}))
assert daily_event_df_dict["Easter Monday [England, Wales, Northern Ireland]_plus_1"].equals(pd.DataFrame({
EVENT_DF_DATE_COL: [datetime.datetime(2019, 4, 23), datetime.datetime(2020, 4, 14)],
EVENT_DF_LABEL_COL: [EVENT_INDICATOR, EVENT_INDICATOR]
}))
assert daily_event_df_dict["Veterans Day_minus_2"].equals(pd.DataFrame({
EVENT_DF_DATE_COL: [datetime.datetime(2019, 11, 9), datetime.datetime(2020, 11, 9)],
EVENT_DF_LABEL_COL: [EVENT_INDICATOR, EVENT_INDICATOR]
}))
def test_generate_holiday_events2():
"""Tests proper handling of pre_num = 0 and post_num = 0"""
countries = ["UnitedStates", "UnitedKingdom", "India", "France"]
year_start = 2019
year_end = 2020
holidays_to_model_separately = [
"New Year's Day",
"Christmas Day",
"Independence Day",
"Thanksgiving",
"Labor Day",
"Good Friday",
"Easter Monday [England, Wales, Northern Ireland]",
"Memorial Day",
"Veterans Day"]
daily_event_df_dict1 = generate_holiday_events(
countries=countries,
holidays_to_model_separately=holidays_to_model_separately,
year_start=year_start,
year_end=year_end,
pre_num=0,
post_num=0)
holidays_dict = get_holidays(
countries,
year_start=year_start,
year_end=year_end)
# merges country DataFrames, removes duplicate holidays
holiday_df = dedup_holiday_dict(holidays_dict)
# creates separate DataFrame for each holiday
daily_event_df_dict2 = split_events_into_dictionaries(
holiday_df,
holidays_to_model_separately)
assert daily_event_df_dict1.keys() == daily_event_df_dict2.keys()
def test_run_template_2():
"""Runs custom template with all options"""
data = generate_df_with_reg_for_tests(
freq="D",
periods=400,
remove_extra_cols=True,
mask_test_actuals=True)
reg_cols = ["regressor1", "regressor2", "regressor_categ"]
keep_cols = [TIME_COL, VALUE_COL] + reg_cols
df = data["df"][keep_cols]
forecast_horizon = data["test_df"].shape[0]
daily_event_df_dict = generate_holiday_events(
countries=["UnitedStates"],
holidays_to_model_separately=["New Year's Day"],
year_start=2017,
year_end=2022,
pre_num=2,
post_num=2)
event_pred_cols = get_event_pred_cols(daily_event_df_dict)
model_components = ModelComponentsParam(
seasonality={
"fs_components_df": pd.DataFrame({
"name": ["tow", "tom", "toq", "toy"],
"period": [7.0, 1.0, 1.0, 1.0],
"order": [2, 1, 1, 5],
"seas_names": ["weekly", "monthly", "quarterly", "yearly"]
})
},
events={
"daily_event_df_dict": daily_event_df_dict
},
changepoints={
"changepoints_dict": {
"method": "auto",
"yearly_seasonality_order": 3,
"regularization_strength": 0.5,
"resample_freq": "14D",
"potential_changepoint_distance": "56D",
"no_changepoint_proportion_from_end": 0.2
},
"seasonality_changepoints_dict": {
"potential_changepoint_distance": "60D",
"regularization_strength": 0.5,
"no_changepoint_proportion_from_end": 0.2
},
},
autoregression=None,
uncertainty={
"uncertainty_dict": None,
},
custom={
"origin_for_time_vars": None,
"extra_pred_cols": [["ct1"] + reg_cols + event_pred_cols], # growth, regressors, events
"fit_algorithm_dict": {
"fit_algorithm": "ridge",
"fit_algorithm_params": {"cv": 2}
},
"min_admissible_value": min(df[VALUE_COL]) - abs(max(df[VALUE_COL])),
"max_admissible_value": max(df[VALUE_COL]) * 2,
}
)
config = ForecastConfig(
model_template=ModelTemplateEnum.SK.name,
forecast_horizon=forecast_horizon,
coverage=0.9,
model_components_param=model_components,
)
with warnings.catch_warnings():
warnings.simplefilter("ignore")
result = Forecaster().run_forecast_config(
df=df,
config=config,
)
rmse = EvaluationMetricEnum.RootMeanSquaredError.get_metric_name()
q80 = EvaluationMetricEnum.Quantile80.get_metric_name()
assert result.backtest.test_evaluation[rmse] == pytest.approx(2.692, rel=1e-2)
assert result.backtest.test_evaluation[q80] == pytest.approx(1.531, rel=1e-2)
assert result.backtest.test_evaluation[PREDICTION_BAND_COVERAGE] == pytest.approx(0.823, rel=1e-2)
assert result.forecast.train_evaluation[rmse] == pytest.approx(2.304, rel=1e-2)
assert result.forecast.train_evaluation[q80] == pytest.approx(0.921, rel=1e-2)
assert result.forecast.train_evaluation[PREDICTION_BAND_COVERAGE] == pytest.approx(0.897, rel=1e-2)
check_forecast_pipeline_result(
result,
coverage=0.9,
strategy=None,
score_func=EvaluationMetricEnum.MeanAbsolutePercentError.name,
greater_is_better=False)
def params_components():
"""Parameters for ``forecast_silverkite``"""
autoreg_dict = {
"lag_dict": {
"orders": [7]
},
"agg_lag_dict": {
"orders_list": [[7, 7 * 2, 7 * 3]],
"interval_list": [(7, 7 * 2)]
},
"series_na_fill_func": lambda s: s.bfill().ffill()
}
uncertainty_dict = {
"uncertainty_method": "simple_conditional_residuals",
"params": {
"conditional_cols": ["dow"],
"quantiles": [0.025, 0.975],
"quantile_estimation_method": "normal_fit",
"sample_size_thresh": 5,
"small_sample_size_method": "std_quantiles",
"small_sample_size_quantile": 0.98
}
}
# generate holidays
countries = ["US", "India"]
holidays_to_model_separately = [
"New Year's Day", "Christmas Day", "Independence Day", "Thanksgiving",
"Labor Day", "Memorial Day", "Veterans Day"
]
event_df_dict = generate_holiday_events(
countries=countries,
holidays_to_model_separately=holidays_to_model_separately,
year_start=2015,
year_end=2025,
pre_num=2,
post_num=2)
# constant event effect at daily level
event_cols = [f"Q('events_{key}')" for key in event_df_dict.keys()]
interaction_cols = cols_interact(static_col="is_weekend",
fs_name="tow",
fs_order=4,
fs_seas_name="weekly")
extra_pred_cols = ["ct_sqrt", "dow_hr", "ct1", "ct1:tod", "regressor1", "regressor2"] + \
event_cols + interaction_cols
# seasonality terms
fs_components_df = pd.DataFrame({
"name": ["tod", "tow", "ct1"],
"period": [24.0, 7.0, 1.0],
"order": [12, 4, 5],
"seas_names": ["daily", "weekly", "yearly"]
})
# changepoints
changepoints_dict = dict(
method="custom",
dates=["2018-01-01", "2019-01-02-16", "2019-01-03", "2019-02-01"],
continuous_time_col="ct2")
return {
"coverage":
0.95,
"origin_for_time_vars":
convert_date_to_continuous_time(datetime.datetime(2018, 1, 3)),
"extra_pred_cols":
extra_pred_cols,
"train_test_thresh":
None,
"training_fraction":
None,
"fit_algorithm":
"ridge",
"daily_event_df_dict":
event_df_dict,
"changepoints_dict":
changepoints_dict,
"fs_components_df":
fs_components_df,
"autoreg_dict":
autoreg_dict,
"min_admissible_value":
None,
"max_admissible_value":
None,
"uncertainty_dict":
uncertainty_dict
}