Identify duplicate forecasts, i.e. instances where there is more than one forecast for the same prediction target.
Uses get_forecast_type_ids() to determine the type-specific columns
(beyond the forecast unit) that identify a unique row. For forecast
objects the type is detected automatically. For plain data.frames
you should pass type (e.g. "quantile", "sample") so that the
correct columns are used. Calling on a plain data.frame without
type is deprecated; it falls back to column-name detection but
this behaviour will be removed in a future version.
get_duplicate_forecasts(
data,
forecast_unit = NULL,
type = NULL,
counts = FALSE
)A data.frame with all rows for which a duplicate forecast was found
A data.frame (or similar) with predicted and observed values. See the "Target format" section in Details for additional information on the required input format.
(optional) Name of the columns in data (after
any renaming of columns) that denote the unit of a
single forecast. See get_forecast_unit() for details.
If NULL (the default), all columns that are not required columns are
assumed to form the unit of a single forecast. If specified, all columns
that are not part of the forecast unit (or required columns) will be removed.
Character string naming the forecast type, corresponding
to the class suffix after forecast_ (e.g. "quantile" for
class forecast_quantile, "sample" for forecast_sample).
Used to determine type-specific ID columns when data is not
already a forecast object. Ignored when data already
inherits from forecast.
Should the output show the number of duplicates per
forecast unit instead of the individual duplicated rows?
Default is FALSE.
example <- rbind(example_quantile, example_quantile[1000:1010])
get_duplicate_forecasts(example, type = "quantile")
Run the code above in your browser using DataLab