Example model outputs adapted from forecasts submitted to the FluSight
Forecast Hub for the 2022/23 season. Model outputs data include quantile,
median, mean forecasts of future incident influenza hospitalization
admissions, and pmf forecasts of hospitalization intensity,
including “low”, “moderate”, “high”, or “very high” intensities.
Hospitalization intensity categories are determined by thresholds for weekly
hospital admissions per 100,000 population. The example model output data
should be viewed only as illustrations of the data formats, not as realistic
examples of forecasts.
Format
example_model_output
A data frame with 70,064 rows and 9 columns:
- model_id
unique identifier for the model submitting forecasts
- location
FIPS code identifying a location
- reference_date
the starting point of the forecasts
- horizon
number of weeks ahead being forecasted
- target_end_date
the date of occurrence of the outcome of interest; this can be calculated directly from the
reference_dateandhorizonas follows:target_end_date = reference_date + 7*horizon- target
a unique identifier for the target
- output_type
the type of representation of the prediction
- output_type_id
more identifying information specific to the output type
- value
the model’s prediction
See hubverse documentation, for more information about model output formats.