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 extract_subseries(series: TimeSeries, min_gap_size: Optional[int] = 1) -> List[TimeSeries]:
"""
Partitions the series into a sequence of sub-series by using significant gaps of missing values
Parameters
----------
series
The TimeSeries to partition into sub-series
min_gap_size
The minimum number of contiguous missing values to consider a gap as significant. Defaults to 1.
Returns
-------
subseries
A list of TimeSeries, sub-series without significant gaps of missing values
"""
# Remove null values from the series extremes
series = series.strip()
freq = series.freq
if series.pd_dataframe().isna().sum().sum() == 0:
return [series]
# Get start/end times of sub-series without gaps of missing values
gaps_df = series.gaps().query(f'gap_size>={min_gap_size}')
start_times = [series.start_time()] + (gaps_df['gap_end'] + freq).to_list()
end_times = (gaps_df['gap_start'] - freq).to_list() + [series.end_time() + freq]
subseries = []
for start, end in zip(start_times, end_times):
subseries.append(series[start:end])
return subseries