Catalyst QuickML

Catalyst QuickML is a no-code machine learning pipeline builder service that lets you implement a host of pre-built ML algorithms, operations, and data preprocessing techniques, and connect with datasets to build and publish ML models. After you publish the ML pipeline, you can access the models you created with authenticated endpoints.

Execute QuickML Endpoint

The code snippet given below allows you to pass input data to a published QuickML endpoint, and predict the outcome based on the ML model’s processing. The output returns the prediction of the values of the target column that is defined while creating the ML pipeline.

Note: You will need to have the ML pipeline and the model's endpoint configured and published in your project using the Catalyst console, before you execute this code to predict the outcome with the code snippet below.

The quickml component instance is created as shown below, which will not fire a server-side call. You will need to create a data dictionary through which you can pass the input data to the model’s endpoint as key-value pairs. The endpoint_key mentioned below is the unique ID of the endpoint published for the ML model configured in your project. The endpoint key and the input data are passed to the predict() method for execution. The app reference used in the code below is the Python object returned as a response during SDK initialization.

# input data dictionary input_data = { // Give column name and value as per your data set "column_name1": "value1", "column_name2": "value2", "column_name3": "value3" } // create quickml instance quickml = app.quick_ml() // execute method result = quickml.predict("{endpoint_key}",input_data) // Replace {endpoint_key} with the endpoint key copied from the catalyst console print(result)

The syntax of the output received is shown below:

{ 'status': 'success', 'result': ["results....."] }

Last Updated 2024-01-02 17:38:02 +0530 +0530