Predicting a Model via REST API

Overview

Description	Predicting a model
Resource Path	`/api/models/{id}/predict?percentile={percentileValue}`
HTTP Method	POST
Request/Response Format	application/json

Parameter description

Parameter	Description
`{id}`	ID of the model that you need to predict.
`{skipDecoding}`	If this property is set to `true`, the predicted value is not decoded. This is an optional parameter.
`{percentileValue}`	The percentile value for the prediction. This should be a double value between 0-100. It is required to specify a percentile value when the ML model uses an algorithm of the `Anomaly Detection` type. This property is optional for other algorithm types. For more information about algorithms of the `Anomaly Detection` type, see Machine Learner Algorithms.

If you are using a deep learning model to make predictions without H2O runtime, see Using Deep Learning Models without H2O Runtime.

Example

POST https://localhost:9443/api/models/{id}/predict
[
[6,148,72,35,0,33.6,0.627,50]
]

Sample cURL command

curl -X POST -H "Content-Type: application/json" -H "Authorization: Basic YWRtaW46YWRtaW4=" -v https://localhost:9443/api/models/1/predict -k -v -d @'prediction-test.json'

Sample output

[0.9176214029664149]

REST API response

HTTP status code

200

For descriptions of the HTTP status codes, see HTTP Status Codes.