Skip to content

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

Notebook reference

FAQ

Are DataRobot Notebooks available in Classic and Workbench?

Yes, DataRobot Notebooks are available in both Workbench and DataRobot Classic.

Why should I use DataRobot Notebooks?

DataRobot Notebooks offer you the flexibility to develop and run code in the language of your choice using both your preferred open-source ML libraries as well as the DataRobot API for streamlining and automating your DataRobot workflows—all within the DataRobot platform. With the fully managed, hosted platform for creating and executing notebooks with auto-scaling capabilities, you can focus on data science work rather than infrastructure management. You can easily organize, collaborate, and share notebooks and related assets among your teams in one unified environment with centralized governance via DataRobot Use Cases.

What’s different about DataRobot Notebooks compared to Jupyter?

Working locally with open-source Jupyter Notebooks can be challenging to scale with an enterprise, whereas DataRobot Notebooks help make data science a team sport by serving as a central repository for notebooks and data science assets, enabling your team to collaborate and make progress on complex problems. Since DataRobot Notebooks is a fully managed solution, you can work with notebooks with scalable resources without having to manage the infrastructure yourself. DataRobot Notebooks also provide enhanced features beyond the classic Jupyter offering, such as built-in revision history, credential management, built-in visualizations, and more. You will be able to have the full flexibility of a code-first environment while also leveraging DataRobot’s suite of other ML offerings, including automated machine learning.

Are DataRobot Notebooks compatible with Jupyter?

Yes, notebooks are Jupyter compatible and utilize Jupyter kernels. DataRobot supports import from and export to the .ipynb standard file format for notebook files, so you can easily bring existing workloads into the platform without concern for vendor lock-in of your IP. The user interface is also closely aligned with Jupyter (e.g. modal editor, keyboard shortcuts), so you can easily onboard without a steep learning curve.

Can I install any packages I need within the notebook environment?

Yes, you can install any additional packages you need into your environment at runtime during your notebook session. You can use Jupyter's magic commands (e.g. !pip install <package-name>) from a notebook cell; however, when your session shuts down, packages installed at runtime do not persist. You must reinstall them the next time you restart the session.

Can I share notebooks?

Although you cannot share notebooks directly with other users, in Workbench, you can share Use Cases that contain notebooks. Therefore, to share a notebook with another user, you must share the entire Use Case so that they have access to all associated assets.

How can I access datasets in my Use Case that I have not yet loaded into my notebook?

Access the dataset you want to include in the notebook from the Use Case dashboard. The ID is included in the dataset URL (after /prepare/); it is the same ID stored for the dataset in the AI Catalog.

Feature considerations

Review the tables below to learn more about the limitations for DataRobot Notebooks.

CPU and memory limits

Review the limits below based on the machine size you are using.

Machine size CPU limit Memory limit
XS 1 CPU 4 GB
S 2 CPU 8 GB
M* 4 CPU 16 GB
L* 8 CPU 32 GB

* M and L machine sizes are available for customers depending on their pricing tier (up to M for Enterprise tier customers, and up to L for Business Critical tier).

Cell limits

The table below outlines limits for cell execution time, cell source, and output sizes

Limit Value
Max cell execution time 8 hours
Max cell output size 10 MB
Max notebook cells count 1000 cells
Max cell source code size 2 MB

Read more

DataRobot offers a library of common use cases that outline data science and machine learning workflows to solve problems. You can view a selection of notebooks below that use v3.0 of DataRobot's Python client.

Topic Describes...
Use cases for version 2.x Notebooks for uses cases that use methods for 2.x versions of DataRobot's Python client.
Identify money laundering with anomaly detection How to use a historical financial transaction dataset and train models that detect instances of money laundering.
Measure price elasticity of demand A use case to identify relationships between price and demand, maximize revenue by properly pricing products, and monitor price elasticities for changes in price and demand.
Insurance claim triage How to evaluate the severity of an insurance claim in order to triage it effectively.
Predict loan defaults A use case that reduces defaults and minimizes risk by predicting the likelihood that a borrower will not repay their loan.
No-show appointment forecasting How to build a model that identifies patients most likely to miss appointments, with correlating reasons.
Predict late shipments A use case that determines whether a shipment will be late or if there will be a shortage of parts.
Reduce 30-Day readmissions rate How to reduce the 30-day readmission rate at a hospital.
Predict steel plate defects A use case that helps manufacturers significantly improve the efficiency and effectiveness of identifying defects of all kinds, including those for steel sheets.
Predict customer churn How to predict customers that are at risk to churn and when to intervene to prevent it.
Large scale demand forecasting An end-to-end demand forecasting use case that uses DataRobot's Python package.
Predictions for fantasy baseball An estimate of a baseball player's true talent level and their likely performance for the coming season.
Lead scoring A binary classification problem of whether a prospect will become a customer.
Forecast sales with multiseries modeling How to forecast future sales for multiple stores using multiseries modeling.
Identify money laundering with anomaly detection How to train anomaly detection models to detect outliers.
Predict CO₂ levels with out-of-time validation modeling How to use out-of-time validation (OTV) modeling with DataRobot's Python client to predict monthly CO₂ levels for one of Hawaii's active volcanoes, Mauna Loa.
Predict equipment failure A use case that that determines whether or not equipment part failure will occur.
Predict fraudulent medical claims The identification of fraudulent medical claims using the DataRobot Python package.
Generate SHAP-based Prediction Explanations How to use DataRobot's SHAP Prediction Explanations to determine what qualities of a home drive sale value.

Updated May 10, 2023
Back to top