Skip to content

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

API documentation home

DataRobot supports REST, Python, and R APIs as a programmatic alternative to the UI for creating and managing DataRobot projects. It allows you to automate processes and iterate more quickly, and lets you use DataRobot with scripted control. The API provides an intuitive modeling and prediction interface. You can use the API with DataRobot-supported clients in either R or Python, or with your own custom code. The clients are supported in Windows, UNIX, and OS X environments. Additionally, you can generate predictions with the prediction and batch prediction APIs, and build DataRobot blueprints in the blueprint workshop.

Review the sections of the API documentation below to find the best resources for your needs:

  • New users can review the API quickstart guide to configure their environments and get started with DataRobot's APIs.

  • The API user guide details common examples of data science and machine learning workflows.

  • The API reference provides documentation on the DataRobot REST API, Python client, R client, blueprint workshop, Prediction API, and Batch Prediction API.

API quickstart

Review the API quickstart guide to configure your environment to use the API and try a sample problem with examples in Python, R, and cURL.

API user guide

Browse user guide topics to find complete examples of common data science and machine learning workflows. The API user guide includes overviews, Jupyter notebooks, and task-based tutorials.

Topic Describes...
Modeling workflow overview Learn how to use DataRobot's clients, both Python and R, to train and experiment with models.
Lead scoring Predict whether a prospect will become a customer. You can frame this use case as a binary classification problem.
Predict fraudulent medical claims Identify fraudulent medical claims using the DataRobot Python package.
Feature Importance Rank Ensembling Learn about the benefits of Feature Importance Rank Ensembling (FIRE)—a method of advanced feature selection that uses a median rank aggregation of feature impacts across several models created during a run of Autopilot.
Advanced feature selection with R Use R to select features by creating aggregated feature impact.
Build a model factory Create a system or a set of procedures that automatically generate predictive models with little to no human intervention.
Prediction Explanation clustering with R Identify and analyze the clusters present in a DataRobot model's Prediction Explanations using the DataRobot R client.
Advanced feature selection with Python Use Python to select features by creating aggregated Feature Impact.
Make Visual AI predictions via the API Configure scripting code for making batch predictions for a Visual AI model via the API.
Get a prediction server ID Learn how to retrieve a prediction server ID using cURL commands from the REST API or by using the DataRobot Python client to make predictions with a deployment.
Make batch predictions with Azure Blob storage Use the DataRobot Python Client package to set up a batch prediction job that reads an input file for scoring from Azure Blob storage and then writes the results back to Azure.
Make batch predictions with Google Cloud Storage Learn how to read input data from and write predictions back to Google Cloud Storage.
Python client troubleshooting Review cases that can cause issues with using the Python client and known fixes.

Reference documentation

DataRobot offers reference documentation available for the following programmatic tools.

Topic Describes...
DataRobot REST API The DataRobot REST API provides a programmatic alternative to the UI for creating and managing DataRobot projects.
Python client Installation, configuration, and reference documentation for working with the Python client library.
R client R client: Installation, configuration, and reference documentation for working with the R client library.
Blueprint workshop Construct and modify DataRobot blueprints and their tasks using a programmatic interface.
Prediction API Generate predictions with a deployment by submitting JSON or CSV input data via a POST request.
Batch Prediction API Score large datasets with flexible options for intake and output using the prediction servers you have deployed via the Batch Prediction API.

Updated June 10, 2022
Back to top