AutoML

Description

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.

This API is used to pass input for an AutoML model's prediction as key-value pairs. You must pass the data in a JSON format in the request as described below.

Note:
  • The AutoML model must already be created. You can create and configure a model from the console.
  • You can specify the target column, or the column in the dataset whose value needs to be predicted, while configuring the model from the console.

Request URL

https://api.catalyst.zoho.com/baas/v1/project/{project_id}/ml/automl/model/{model_id}

project_id - The unique ID of the project

model_id - The unique ID of the model

Request Headers

Authorization: Zoho-oauthtoken 1000.910***************************16.2f****************************57
Content-Type: application/json

Request Method

POST

Scope

scope=ZohoCatalyst.mlkit.READ

Request JSON Format

You must send the column names and the corresponding column values in a JSON format like this:

{
"column1_name": "column1_value",
"column2_name": "column2_value",
"column3_name": "column3_value"
}

where column_name is a key in the dataset required for predicting the target, and column_value is the data you provide for the corresponding column.

Note:
  • If you enter a value in a format that does not match the data type of the column, such as a numerical value for the date type, the value will not be parsed. Ensure that you provide the data in the right format.
  • You must provide the value for atleast one valid column while testing the prediction.
  • If you don't enter the value for an input field, a default value will be entered for the column by Zia automatically. However, this will affect the accuracy of the prediction.

SDK documentation

AutoML- Java SDK

AutoML- Node.js SDK

Curl

Sample Request: Regression model


				curl -X POST \
  https://api.catalyst.zoho.com/baas/v1/project/4000000006007/ml/automl/model/105000000124001 \
  -H "Authorization: Zoho-oauthtoken 1000.8cb99dxxxxxxxxxxxxx9be93.9b8xxxxxxxxxxxxxxxf" \
  -H "Content-Type: application/json" \
  -d '{
        "country": "Armenia",
        "year": "2016",
        "sex": "female",
        "age": "25-34",
        "population": "277452",
        "GDP_for_year": "10,546,135,160"
      }'

Sample Response: Regression model


				{
  "status":"success",
  "data":{
        "regression_result":3.41
             }
}

Sample Request: Binary-class classification model


				curl -X POST \
  https://api.catalyst.zoho.com/baas/v1/project/4000000006007/ml/automl/model/105000000124001 \
  -H "Authorization: Zoho-oauthtoken 1000.8cb99dxxxxxxxxxxxxx9be93.9b8xxxxxxxxxxxxxxxf" \
  -H "Content-Type: application/json" \
  -d '{
        "year_film": "2019",
        "year_award": "2020",
        "ceremony": "77",
        "category": "Best Director - Motion Picture",
        "nominee": "Todd Phillips",
        "film": "Joker"
      }'

Sample Response: Binary-class classification model


				{
  "status":"success",
  "data":{
       "classification_result":
                {
                "True":20,
                "False":80
                }
              }
}

Sample Request: Multi-class classification model


				curl -X POST \
  https://api.catalyst.zoho.com/baas/v1/project/4000000006007/ml/automl/model/105000000124001 \
  -H "Authorization: Zoho-oauthtoken 1000.8cb99dxxxxxxxxxxxxx9be93.9b8xxxxxxxxxxxxxxxf" \
  -H "Content-Type: application/json" \
  -d '{
        "Transaction_date": "1/2/09 4:53",
        "Product": "RAM",
        "Price": "120",
        "City": "Parkville",
        "State": "MO",
        "Country": "United States",
        "Account_Created": "12/4/08 4:42",
        "Last_Login": "1/2/09 7:49"
      }'

Sample Response: Multi-class classification model


				{
  "status":"success",
  "data":{
        "classification_result":
                {
                 "Amex":10,
                 "Diner":20,
                 "Mastercard": 30,
                 "Visa":40
                }
              }
}