Databricks SDK for JavaScript
    Preparing search index...

    Interface CreateForecastingExperimentRequest

    interface CreateForecastingExperimentRequest {
        customWeightsColumn?: string;
        experimentPath?: string;
        forecastGranularity?: string;
        forecastHorizon?: bigint;
        futureFeatureDataPath?: string;
        holidayRegions?: string[];
        includeFeatures?: string[];
        maxRuntime?: bigint;
        predictionDataPath?: string;
        primaryMetric?: string;
        registerTo?: string;
        splitColumn?: string;
        targetColumn?: string;
        timeColumn?: string;
        timeseriesIdentifierColumns?: string[];
        trainDataPath?: string;
        trainingFrameworks?: string[];
    }
    Index

    Properties

    customWeightsColumn? experimentPath? forecastGranularity? forecastHorizon? futureFeatureDataPath? holidayRegions? includeFeatures? maxRuntime? predictionDataPath? primaryMetric? registerTo? splitColumn? targetColumn? timeColumn? timeseriesIdentifierColumns? trainDataPath? trainingFrameworks?

    Properties

    customWeightsColumn?: string

    The column in the training table used to customize weights for each time series.

    experimentPath?: string

    The path in the workspace to store the created experiment.

    forecastGranularity?: string

    The time interval between consecutive rows in the time series data. Possible values include: '1 second', '1 minute', '5 minutes', '10 minutes', '15 minutes', '30 minutes', 'Hourly', 'Daily', 'Weekly', 'Monthly', 'Quarterly', 'Yearly'.

    forecastHorizon?: bigint

    The number of time steps into the future to make predictions, calculated as a multiple of forecast_granularity. This value represents how far ahead the model should forecast.

    futureFeatureDataPath?: string

    The fully qualified path of a Unity Catalog table, formatted as catalog_name.schema_name.table_name, used to store future feature data for predictions.

    holidayRegions?: string[]

    The region code(s) to automatically add holiday features. Currently supports only one region.

    includeFeatures?: string[]

    Specifies the list of feature columns to include in model training. These columns must exist in the training data and be of type string, numerical, or boolean. If not specified, no additional features will be included. Note: Certain columns are automatically handled:

    • Automatically excluded: split_column, target_column, custom_weights_column.
    • Automatically included: time_column.
    maxRuntime?: bigint

    The maximum duration for the experiment in minutes. The experiment stops automatically if it exceeds this limit.

    predictionDataPath?: string

    The fully qualified path of a Unity Catalog table, formatted as catalog_name.schema_name.table_name, used to store predictions.

    primaryMetric?: string

    The evaluation metric used to optimize the forecasting model.

    registerTo?: string

    The fully qualified path of a Unity Catalog model, formatted as catalog_name.schema_name.model_name, used to store the best model.

    splitColumn?: string

    // The column in the training table used for custom data splits. Values must be 'train', 'validate', or 'test'.

    targetColumn?: string

    The column in the input training table used as the prediction target for model training. The values in this column are used as the ground truth for model training.

    timeColumn?: string

    The column in the input training table that represents each row's timestamp.

    timeseriesIdentifierColumns?: string[]

    The column in the training table used to group the dataset for predicting individual time series.

    trainDataPath?: string

    The fully qualified path of a Unity Catalog table, formatted as catalog_name.schema_name.table_name, used as training data for the forecasting model.

    trainingFrameworks?: string[]

    List of frameworks to include for model tuning. Possible values are 'Prophet', 'ARIMA', 'DeepAR'. An empty list includes all supported frameworks.

    Settings

    Member Visibility

    On This Page

    Properties