AutoML

Zia AutoML enables you to train models and analyze a set of training data to predict the outcome of a subset of that data. You can build and train Binary Classification, Multi-Class Classification, and Regression Models, and obtain insightful evaluation reports.

Refer to the API documentation for the request and response formats.

You can pass inputs for a model’s columns and values to test it, by providing the model ID of the model. It returns the prediction of the values of a target column.

The zia reference used below is defined in the component instance page. The promise returned here is resolved to a JSON object.

    

        
copy
        

            

        
    
    

         var zia = app.zia();
//Provide the model ID of the model
zia.automl(modelId, {
//Provide inputs for the columns and its values of the model
"column_1" : "column1_value",
"column_2" : "column2_value",
"column_3" : "column3_value",
"column_4" : "column4_value",
"column_5" : "column5_value",
}).then((result) => {
console.log(result);
})
.catch((err) => console.log(err.toString())); //Push errors to Catalyst Logs
  
    

A sample response that you will receive is shown below. The response is the same for both versions of Node.js.

Node js

    

        
copy
        

            

        
    
    

         { 
classification_result: 
{ 
Dollars: 0, 
Percentage: 80, 
"Dollars (millions)": 20 
} 
}