Skip to content

Click in-app to access the full platform documentation for your version of DataRobot.

Time series

Batch predictions for time series models work without any additional configuration. However, in most cases you need to either modify the default configuration or prepare the prediction dataset.

Note

Time series batch predictions are not available for cross-series projects or traditional time series models (such as ARIMA).

Time Series Batch Prediction Settings

The default configuration can be overridden using the timeseriesSettings job configuration property:

Parameter Example Description
type forecast Must be either forecast (default) or historical.
forecastPoint 2019-02-04T00:00:00Z Optional. By default, DataRobot infers the forecast point from the dataset. To configure, type must be set to forecast.
predictionsStartDate 2019-01-04T00:00:00Z Optional. By default, DataRobot infers the start date from the dataset. To configure, type must be set to historical.
predictionsEndDate 2019-02-04T00:00:00Z Optional. By default, DataRobot infers the end date from the dataset. To configure, type must be set to historical.
relaxKnownInAdvanceFeaturesCheck false Optional. If activated, missing values in the known in advance features are allowed in the forecast window at prediction time. If omitted or false, missing values are not allowed. Default: false.

Here is a complete example job:

{
    "deploymentId": "5f22ba7ade0f435ba7217bcf",
    "intakeSettings": {"type": "localFile"},
    "outputSettings": {"type": "localFile"},
    "timeseriesSettings": {
        "type": "historical",
        "predictionsStartDate": "2020-01-01",
        "predictionsEndDate": "2020-03-31"
    }
}

An example using Python SDK:

import datarobot as dr

dr.Client(
    endpoint="https://app.datarobot.com/api/v2",
    token="...",
)

deployment_id = "..."

input_file = "to_predict.csv"
output_file = "predicted.csv"

job = dr.BatchPredictionJob.score_to_file(
    deployment_id,
    input_file,
    output_file,
    timeseries_settings={
        "type": "historical",
        "predictions_start_date": "2020-01-01",
        "predictions_end_date": "2020-03-31",
    },
)

print("started scoring...", job)
job.wait_for_completion()

Prediction type

When using forecast mode, DataRobot makes predictions using forecastPoint or rows in the dataset without a target. In historical mode, DataRobot enables bulk predictions, which calculates predictions for all possible forecast points and forecast distances within predictionsStartDate and predictionsEndDate range.

Requirements for the scoring dataset

To ensure the Batch Prediction API can process your time series dataset, you must configure the following:

  • Sort prediction rows by their timestamps, with the earliest row first.
    • If using multiseries, the prediction rows must be sorted by series ID then timestamp.
  • If requesting forecast predictions, your dataset must contain rows without a target for the desired forecast window
  • There is no limit on the number of series DataRobot supports. The only limit is the job timeout as mentioned in Limits.

Single series forecast dataset example

The following is an example forecast dataset for a single series:

date y
2020-01-01 9342.85
2020-01-02 4951.33
24 more historical rows
2020-01-27 4180.92
2020-01-28 5943.11
2020-01-29
2020-01-30
2020-01-31
2020-02-01
2020-02-02
2020-02-03
2020-02-04

Multiseries forecast dataset example

If scoring multiple series, the data must be ordered by series and timestamp:

date series y
2020-01-01 A 9342.85
2020-01-02 A 4951.33
24 more historical rows
2020-01-27 A 4180.92
2020-01-28 A 5943.11
2020-01-29 A
2020-01-30 A
2020-01-31 A
2020-02-01 A
2020-02-02 A
2020-02-03 A
2020-02-04 A
2020-01-01 B 8477.22
2020-01-02 B 7210.29
24 more historical rows
2020-01-27 B 7400.21
2020-01-28 B 8844.71
2020-01-29 B
2020-01-30 B
2020-01-31 B
2020-02-01 B
2020-02-02 B
2020-02-03 B
2020-02-04 B

Updated October 27, 2021
Back to top