Model Outputs
Your model produces forecast data by writing an output file to the platform.
During a model run, the container uploads its results to the URL specified by
the OUTPUT_URL environment variable using an HTTP PUT request. The platform
processes this file, stores the forecast data, and makes it available in pdView.
How output works
When your container finishes its forecast computation, it must upload the result
to the OUTPUT_URL environment variable. This is a standard HTTP PUT request
with the output file as the request body.
The output file format is configured at the model level using the
outputFileFormat field in .pd4castrrc.json. Supported formats are json,
csv, and parquet. If you don’t specify a format, JSON is used by default.
Required columns
Every output file must contain a forecast_datetime column. This column holds
the datetime values for each forecast data point in the output. All other
columns are defined by the model author in the outputs array.
Output column configuration
The outputs array in .pd4castrrc.json defines the schema of your output
data. Each entry describes one column in the output file.
| Field | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Column name in the output data. Must include forecast_datetime. |
type | string | Yes | Data type: float, integer, string, date, boolean, or unknown. |
seriesKey | boolean | Yes | Whether this column is a categorical series key. Series keys split data into separate chart lines. |
colour | string | No | Hex colour code (#RRGGBB) for this series in the forecast chart. |
Series keys
Columns marked with "seriesKey": true act as categorical identifiers that
determine how the data is split into chart series in pdView. For example, a
price forecast model covering multiple energy regions might define each region
(NSW1, QLD1, SA1) as a series key. Each unique value in a series key column
becomes a separate line on the forecast chart.
Columns with "seriesKey": false contain the actual forecast values (for
example, the predicted price for each region at each datetime).
How outputs appear in the platform
Output columns map directly to what users see in pdView:
- Series key columns create separate lines or categories on the forecast chart. Each unique value gets its own line with the specified colour.
- Value columns provide the data points plotted on the chart.
- The forecast chart displays data over time, using
forecast_datetimeas the x-axis.
Example
Here’s a complete outputs configuration for a price forecast model that covers
five Australian energy regions:
{
"outputs": [
{
"name": "forecast_datetime",
"type": "date",
"seriesKey": false
},
{
"name": "NSW1",
"type": "float",
"seriesKey": true,
"colour": "#84EDDC"
},
{
"name": "QLD1",
"type": "float",
"seriesKey": true,
"colour": "#FD4E4E"
},
{
"name": "SA1",
"type": "float",
"seriesKey": true,
"colour": "#FED600"
},
{
"name": "TAS1",
"type": "float",
"seriesKey": true,
"colour": "#40A967"
},
{
"name": "VIC1",
"type": "float",
"seriesKey": true,
"colour": "#1965C6"
}
]
}In this example, each region column is a series key with a distinct colour. pdView renders five separate lines on the forecast chart, one per region, each in the specified colour.
Next steps
- See the Configuration file reference for all output field details.
- Learn about Sensitivities and scenarios to run alternative versions of your model with modified inputs.