def make_and_compare_predictions(
gathered_stats: TimeSeries,
predictions_to_make: ModelsToMake,
prediction_duration_past: pd.Timedelta = _ONE_DAY,
prediction_duration_future: pd.Timedelta = None,
metric: Metric = metrics.coefficient_of_variation,
transform: bool = False,
) -> PredictionEvaluations:
"""Run multiple forecasts and compare their accuracy."""
train, actual = gathered_stats.split_after(
gathered_stats.end_time() - prediction_duration_past, )
n_pred: int = len(actual)
if prediction_duration_future:
n_pred += int(prediction_duration_future / gathered_stats.freq())
if transform:
forecasts = make_forecasts_ensure_positive(
train=train,
n_pred=n_pred,
predictions_to_make=predictions_to_make,
)
else:
forecasts = make_forecasts(
train=train,
n_pred=n_pred,
predictions_to_make=predictions_to_make,
)
return PredictionEvaluations(
predictions=forecasts,
evaluations=compare_predictions(actual, forecasts, metric),
)
def helper_test_split(test_case, test_series: TimeSeries):
seriesA, seriesB = test_series.split_after(pd.Timestamp('20130104'))
test_case.assertEqual(seriesA.end_time(), pd.Timestamp('20130104'))
test_case.assertEqual(seriesB.start_time(), pd.Timestamp('20130105'))
seriesC, seriesD = test_series.split_before(pd.Timestamp('20130104'))
test_case.assertEqual(seriesC.end_time(), pd.Timestamp('20130103'))
test_case.assertEqual(seriesD.start_time(), pd.Timestamp('20130104'))
test_case.assertEqual(test_series.freq_str(), seriesA.freq_str())
test_case.assertEqual(test_series.freq_str(), seriesC.freq_str())
def helper_test_append(test_case, test_series: TimeSeries):
# reconstruct series
seriesA, seriesB = test_series.split_after(pd.Timestamp('20130106'))
test_case.assertEqual(seriesA.append(seriesB), test_series)
test_case.assertEqual(
seriesA.append(seriesB).freq(), test_series.freq())
# Creating a gap is not allowed
seriesC = test_series.drop_before(pd.Timestamp('20130107'))
with test_case.assertRaises(ValueError):
seriesA.append(seriesC)
# Changing frequence is not allowed
seriesM = TimeSeries.from_times_and_values(
pd.date_range('20130107', '20130507', freq='30D'), range(5))
with test_case.assertRaises(ValueError):
seriesA.append(seriesM)
def helper_test_append_values(test_case, test_series: TimeSeries):
# reconstruct series
seriesA, seriesB = test_series.split_after(pd.Timestamp('20130106'))
test_case.assertEqual(
seriesA.append_values(seriesB.values(), seriesB.time_index()),
test_series)
test_case.assertEqual(seriesA.append_values(seriesB.values()),
test_series)
# test for equality
test_case.assertEqual(
test_series.drop_after(pd.Timestamp('20130105')).append_values(
test_series.drop_before(pd.Timestamp('20130104')).values()),
test_series)
test_case.assertEqual(seriesA.append_values([]), seriesA)
# randomize order
rd_order = np.random.permutation(range(len(seriesB.values())))
test_case.assertEqual(
seriesA.append_values(seriesB.values()[rd_order],
seriesB.time_index()[rd_order]), test_series)
# add non consecutive index
with test_case.assertRaises(ValueError):
test_case.assertEqual(
seriesA.append_values(seriesB.values(),
seriesB.time_index() + seriesB.freq()),
test_series)
# add existing indices
with test_case.assertRaises(ValueError):
test_case.assertEqual(
seriesA.append_values(
seriesB.values(),
seriesB.time_index() - 3 * seriesB.freq()), test_series)
# other frequency
with test_case.assertRaises(ValueError):
test_case.assertEqual(
seriesA.append_values(
seriesB.values(),
pd.date_range('20130107', '20130113', freq='2d')),
test_series)