Make predictions¶

After you create an experiment and train models, you can make predictions to validate those models.

To make predictions with a model in a Workbench experiment:

1. Select the model from the Models list and then click Model actions > Make predictions.

   

2. On the Make Predictions page, upload a Prediction source:

   • Click, drag, and drop a file into the Prediction source group box.

   • Click Choose file to upload a Local file or a dataset stored in the AI Catalog.

   

   Note

   When you upload a prediction dataset, it is automatically stored in the AI Catalog once the upload is complete. Be sure not to navigate away from the page during the upload, or the dataset will not be stored in the catalog. If the dataset is still processing after the upload, that means DataRobot is running EDA on the dataset before it becomes available for use.

3. In the Prediction options section, to write input features (columns) to the prediction results file alongside the predictions, enable Include input features:

   • To filter for and include specific features from the dataset, select Specific features and enter one or more feature names to add them.

   • To include every feature from the dataset, select All features.

   

   Note

   You can only append a feature (column) present in the original dataset, although the feature does not have to have been part of the feature list used to build the model. Derived features are not included.

4. After you configure the Prediction options, click Compute and download predictions to start scoring the data.

5. When scoring completes, under Your recent predictions:

   • If scoring is successful, click the download icon () to download a predictions file.

     

   • If the prediction job fails, click View logs to view and optionally copy the run details.

   Note

   Predictions are available for download for the next 48 hours.