def test_get_df():
dl = DataLoader()
# Daily data
data_path = dl.get_data_home(data_dir=None, data_sub_dir="daily")
df = dl.get_df(data_path=data_path, data_name="daily_peyton_manning")
assert list(df.columns) == ["ts", "y"]
assert df.shape == (2905, 2)
# Hourly data
data_path = dl.get_data_home(data_dir=None, data_sub_dir="hourly")
df = dl.get_df(data_path=data_path, data_name="hourly_parking")
assert list(df.columns) == [
"SystemCodeNumber", "Capacity", "Occupancy", "LastUpdated"
]
assert df.shape == (35717, 4)
# Error due to wrong file name
data_path = dl.get_data_home(data_dir=None, data_sub_dir="daily")
file_path = os.path.join(data_path, "parking.csv")
file_names = dl.get_data_names(data_path=data_path)
with pytest.raises(
ValueError,
match=
fr"Given file path '{file_path}' is not found. Available datasets "
fr"in data directory '{data_path}' are \{file_names}\."):
dl.get_df(data_path=data_path, data_name="parking")
def test_get_data_names():
dl = DataLoader()
# Returns empty set as there is no .csv file in 'data' folder
data_path = dl.get_data_home()
file_names = dl.get_data_names(data_path=data_path)
assert file_names == []
data_path = dl.get_data_home(data_sub_dir="daily")
file_names = dl.get_data_names(data_path=data_path)
assert set(file_names) == {
"daily_temperature_australia", "daily_demand_order",
"daily_female_births", "daily_istanbul_stock", "daily_peyton_manning"
}
def test_get_data_home():
dl = DataLoader()
# Default parameters
data_home = dl.get_data_home()
assert os.path.basename(os.path.normpath(data_home)) == "data"
# With subdirectory
data_home = dl.get_data_home(data_sub_dir="daily")
assert os.path.basename(os.path.normpath(data_home)) == "daily"
# Error due to non existing folder
data_dir = "/home/data"
with pytest.raises(ValueError, match=f"Requested data directory '{data_dir}' does not exist."):
dl.get_data_home(data_dir=data_dir)
def test_benchmark_silverkite_template_with_real_data():
# setting every list to 1 item to speed up test case
forecast_horizons = [30]
max_cvs = [3]
fit_algorithms = ["linear"]
metric = EvaluationMetricEnum.MeanSquaredError
evaluation_metric = EvaluationMetricParam(cv_selection_metric=metric.name)
# real data
dl = DataLoader()
data_path = dl.get_data_home(data_sub_dir="daily")
data_name = "daily_female_births"
df = dl.get_df(data_path=data_path, data_name="daily_female_births")
time_col = "Date"
value_col = "Births"
metadata = MetadataParam(time_col=time_col, value_col=value_col, freq="D")
result_silverkite_real = benchmark_silverkite_template(
data_name=data_name,
df=df,
metadata=metadata,
evaluation_metric=evaluation_metric,
forecast_horizons=forecast_horizons,
fit_algorithms=fit_algorithms,
max_cvs=max_cvs)
result_silverkite_real = result_silverkite_real[0]
assert result_silverkite_real["data_name"] == data_name
assert result_silverkite_real["forecast_model_name"] == "silverkite_linear"
assert result_silverkite_real["train_period"] == df.shape[0]
assert result_silverkite_real["forecast_horizon"] == 30
assert result_silverkite_real["cv_folds"] == 3
def test_estimator_plot_components_from_forecaster():
"""Tests estimator's plot_components function after the Forecaster has set everything up at the top most level"""
# Test with real data (Female-births) via model template
dl = DataLoader()
data_path = dl.get_data_home(data_sub_dir="daily")
df = dl.get_df(data_path=data_path, data_name="daily_female_births")
metadata = MetadataParam(time_col="Date", value_col="Births", freq="D")
model_components = ModelComponentsParam(
seasonality={
"yearly_seasonality": True,
"quarterly_seasonality": True,
"weekly_seasonality": True,
"daily_seasonality": False
})
result = Forecaster().run_forecast_config(
df=df,
config=ForecastConfig(
model_template=ModelTemplateEnum.SILVERKITE.name,
forecast_horizon=30, # forecast 1 month
coverage=0.95, # 95% prediction intervals
metadata_param=metadata,
model_components_param=model_components))
estimator = result.model.steps[-1][-1]
assert estimator.plot_components()