Skip to content

On-premise users: click in-app to access the full platform documentation for your version of DataRobot.

Platform (V9.0)

The following table lists each new feature.

Name GA Preview
Platform enhancements
DataRobot Notebooks
API enhancements
Access DataRobot REST API documentation from
Python client v3.0
Python client v3.1
R client v2.29
Calculate Feature Impact for each backtest
Deprecation announcements

Platform enhancements

  • With DataRobot release version 9.0, deployments are now only supported by Kubernetes. Version 9.0 supports OpenShift 4.10 and AWS EKS with K8s v1.23. Older installation options (i.e., Dockerized, RPM, and Hadoop) are no longer supported. If you are not on a supported version of Kubernetes, you will need to use the 8.x versions of DataRobot with Dockerized, RPM, or Hadoop installs.

  • Minio will not be packaged with the DataRobot installation. You will need to provide and manage an S3 API-compatible object store to use with DataRobot.

  • DataRobot will no longer package a container registry. You will need to provide a docker registry for DataRobot containers.

Preview: DataRobot Notebooks

The DataRobot application now includes an in-browser editor to create and execute notebooks for data science analysis and modeling. Notebooks display computation results in various formats, including text, images, graphs, plots, tables, and more. You can customize output display by using open-source plugins. Cells can also contain Markdown rich text for commentary and explanation of the coding workflow. As you develop and edit a notebook, DataRobot stores a history of revisions that you can return to at any time.

DataRobot Notebooks offer a dashboard that hosts notebook creation, upload, and management. Individual notebooks have containerized, built-in environments with commonly used machine learning libraries that you can easily set up in a few clicks. Notebook environments seamlessly integrate with DataRobot's API, allowing a robust coding experience supported by keyboard shortcuts for cell functions, in-line documentation, and saved environment variables for secrets management and automatic authentication.

Preview documentation.

API enhancements

The following is a summary of API new features and enhancements. Go to the API Documentation home for more information on each client.


DataRobot highly recommends updating to the latest API client for Python and R.

Access DataRobot REST API documentation from

DataRobot now offers REST API documentation available directly from the public documentation hub. Previously, REST API docs were only accessible through the application. Now, you can access information about REST endpoints and parameters in the API reference section of the public documentation site.

Python client v3.0

Now generally available, DataRobot has released version 3.0 of the Python client. This version introduces significant changes to common methods and usage of the client. Many prominent changes are listed below, but view the changelog for a complete list of changes introduced in version 3.0.

Python client v3.0 new features

A summary of some new features for version 3.0 are outlined below:

  • Version 3.0 of the Python client does not support Python 3.6 and earlier versions. Version 3.0 currently supports Python 3.7+.
  • The default Autopilot mode for the project.start_autopilot method has changed to AUTOPILOT_MODE.QUICK.
  • Pass a file, file path, or DataFrame to a deployment to easily make batch predictions and return the results as a DataFrame using the new method Deployment.predict_batch.
  • You can use a new method to retrieve the canonical URI for a project, model, deployment, or dataset:
    • Project.get_uri
    • Model.get_uri
    • Deployment.get_uri
    • Dataset.get_uri

New methods for DataRobot projects

Review the new methods available for datarobot.models.Project:

  • Project.get_options allows you to retrieve saved modeling options.
  • Project.set_options saves AdvancedOptions values for use in modeling.
  • Project.analyze_and_model initiates Autopilot or data analysis using data that has been uploaded to DataRobot.
  • Project.get_dataset retrieves the dataset used to create the project.
  • Project.set_partitioning_method creates the correct Partition class for a regular project based on input arguments.
  • Project.set_datetime_partitioning creates the correct Partition class for a time series project.
  • Project.get_top_model returns the highest scoring model for a metric of your choice.

Python client v3.1

The following API enhancements are introduced with version 3.1 of DataRobot's Python client:

  • Added new methods BatchPredictionJob.apply_time_series_data_prep_and_score and BatchPredictionJob.apply_time_series_data_prep_and_score_to_file that apply time series data prep to a file or dataset and make batch predictions with a deployment.

  • Added new methods DataEngineQueryGenerator.prepare_prediction_dataset and DataEngineQueryGenerator.prepare_prediction_dataset_from_catalog that apply time series data prep to a file or catalog dataset and upload the prediction dataset to a project.

  • Added new max_wait parameter to the method Project.create_from_dataset. Values larger than the default can be specified to avoid timeouts when creating a project from Dataset.

  • Added new method for creating a segmented modeling project from an existing clustering project and model Project.create_segmented_project_from_clustering_model. Switch to this function if you are previously using ModelPackage for segmented modeling purposes.

  • Added new method is_unsupervised_clustering_or_multiclass for checking whether the clustering or multiclass parameters are used, quick and efficient without extra API calls.


  • Added two new methods to the ImageAugmentationList class: ImageAugmentationList.list and ImageAugmentationList.update.

  • Added format key to Batch Prediction intake and output settings for S3, GCP and Azure.

  • The method PredictionExplanations.is_multiclass now adds an additional API call to check for multiclass target validity, which adds a small delay.

  • AdvancedOptions parameter blend_best_models defaults to false.

  • AdvancedOptions <datarobot.helpers.AdvancedOptions> parameter consider_blenders_in_recommendation defaults to false.

  • DatetimePartitioning now has the parameter unsupervised_mode.

Preview: R client v2.29

Now available for preview, DataRobot has released version 2.29 of the R client. This version brings parity between the R client and version 2.29 of the Public API. As a result, it introduces significant changes to common methods and usage of the client. These changes are encapsulated in a new library (in addition to the datarobot library): datarobot.apicore, which provides auto-generated functions to access the Public API. The datarobot package provides a number of API wrapper functions around the apicore package to make it easier to use.

Reference the v2.29 documentation for more details on the new R client, including installation instructions, detailed method overviews, and reference documentation.

New R Functions

  • Generated API wrapper functions are organized into categories based on their tags from the OpenAPI specification, which were themselves redone for the entire DataRobot Public API in v2.27.
  • API wrapper functions use camel-cased argument names to be consistent with the rest of the package.
  • Most function names follow a VerbObject pattern based on the OpenAPI specification.
  • Some function names match "legacy" functions that existed in v2.18 of the R Client if they invoked the same underlying endpoint. For example, the wrapper function is called GetModel, not RetrieveProjectsModels, since the latter is what was implemented in the R client for the endpoint /projects/{mId}/models/{mId}.
  • Similarly, these functions use the same arguments as the corresponding "legacy" functions to ensure DataRobot does not break existing code calling those functions.
  • The R client (both datarobot and datarobot.apicore packages) outputs a warning when you attempt to access certain resources (projects, models, deployments, etc.) that are deprecated or disabled by the DataRobot platform migration to Python 3.
  • Added the helper function EditConfig that allows you to interactively modify drconfig.yaml.
  • Added the DownloadDatasetAsCsv function to retrieve a dataset as a CSV file using catalogId.
  • Added the GetFeatureDiscoveryRelationships function to get the feature discovery relationships for a project.
  • The R client (both datarobot and datarobot.apicore packages) will output a warning when you attempt to access certain resources (projects, models, deployments, etc.) that are deprecated or disabled by the DataRobot platform migration to Python 3.

R enhancements

  • The function RequestFeatureImpact now accepts a rowCount argument, which will change the sample size used for Feature Impact calculations.
  • The internal helper function ValidateModel was renamed to ValidateAndReturnModel and now works with model classes from the apicore package.
  • The quickrun argument has been removed from the function SetTarget. Set mode = AutopilotMode.Quick instead.
  • The Transferable Models family of functions (ListTransferableModels, GetTransferableModel, RequestTransferableModel, DownloadTransferableModel, UploadTransferableModel, UpdateTransferableModel, DeleteTransferableModel) have been removed. The underlying endpoints—long deprecated—were removed from the Public API with the removal of the Standalone Scoring Engine (SSE).
  • Removed files (code, tests, doc) representing parts of the Public API not present in v2.27-2.29.

Calculate Feature Impact for each backtest

Feature Impact provides a transparent overview of a model, especially in a model's compliance documentation. Time-dependent models trained on different backtests and holdout partitions can have different Feature Impact calculations for each backtest. Now generally available, you can calculate Feature Impact for each backtest using DataRobot's REST API, allowing you to inspect model stability over time by comparing Feature Impact scores from different backtests.

Deprecation announcements

API deprecations

R deprecations

Review the breaking changes introduced in version 2.29:

  • The quickrun argument has been removed from the function SetTarget. Set mode = AutopilotMode.Quick instead.
  • The Transferable Models functions have been removed. Note that the underlying endpoints were also removed from the Public API with the removal of the Standalone Scoring Engine (SSE). The affected functions are listed below:

    • ListTransferableModels
    • GetTransferableModel
    • RequestTransferableModel
    • DownloadTransferableModel
    • UploadTransferableModel
    • UpdateTransferableModel
    • DeleteTransferableModel

Review the deprecations introduced in version 2.29:

  • Compliance Documentation API is deprecated. Instead use the Automated Documentation API.

Python deprecations

Review the deprecations introduced in version 3.0:

  • Project.set_target has been removed. Use Project.analyze_and_model instead.
  • PredictJob.create has been removed. Use Model.request_predictions instead.
  • Model.get_leaderboard_ui_permalink has been removed. Use Model.get_uri instead.
  • Project.open_leaderboard_browser has been removed. Use Project.open_in_browser instead.
  • ComplianceDocumentation has been removed. Use AutomatedDocument instead.

The following deprecations are introduced in version 3.1:

  • Deprecated method Project.create_from_hdfs.
  • Deprecated method DatetimePartitioning.generate.
  • Deprecated parameter in_use from ImageAugmentationList.create as DataRobot will take care of it automatically.
  • Deprecated property Deployment.capabilities from Deployment.
  • ImageAugmentationSample.compute was removed in v3.1. You can get the same information with the method ImageAugmentationList.compute_samples.
  • The sample_id parameter is now removed from ImageAugmentationSample.list. Please use auglist_id instead.

Hadoop is no longer available

Starting with version 9.0, you can only install DataRobot on Kubernetes. Dockerized, RPM, and Hadoop installations will no longer be available. Also, the ability to directly ingest data from HDFS for modeling and prediction is deprecated.

Updated March 26, 2024