Work with Datasets
Working with Datasets on Evidently Platform.
Last updated
Working with Datasets on Evidently Platform.
Last updated
To access or upload your Datasets, navigate to the in the user interface.
You will be able to view all Datasets: created from traces, uploaded directly to the platform, or generated as a result of an evaluation.
Once you go to the Datasets page, you can upload any existing dataset as a CSV file directly there. Click on "Add dataset".
When you upload the Dataset, you must also add a . This allows Evidently to understand the meaning of specific columns and prepare your Dataset for future evaluations.
To work with Datasets programmatically from Python, you must first .
Prepare your dataset as a Pandas DataFrame. To upload a dataframe df to the specified Project in workspace ws, use the add_dataset method:
You must always specify the "dataset_name" you want to see in the UI. The description is optional.
You can also download the Dataset from Evidently platform to your local environment. For example, if you store the test dataset on the platform and want to pull it into your local evaluation script.
Use the load_dataset method:
You can also include Datasets when you upload Reports or Test Suites to the platform. This way, after running an evaluation locally you simultaneously upload the evaluation result and the Dataset it was generated for, with added scores if applicable.
Use include_data parameter (False by default):
To get a Project ID, grab it from the existing Project page or create a new Project first. (How to .)
This is optional. Check the docs on for details.