Suggestion Create

https://api.sigopt.com/v1/experiments/EXPERIMENT_ID/suggestions

When you are ready to start working, create a Suggestion. The response object will contain the assignments that SigOpt recommends in order to optimize your metric.

Request Method: POST

Parameters

Name	Type	Required?	Description
assignments	Assignments	N	Allows you to specify the assignments of this suggestion. You must specify exactly one value for each parameter in the experiment.
metadata	Metadata	N	Optional user-provided object. See Using Metadata for more information.

Response

Suggestion object.

Examples

Create a suggestion

Python

suggestion = conn.experiments(EXPERIMENT_ID).suggestions().create()

Bash

SUGGESTION=`curl -s -X POST https://api.sigopt.com/v1/experiments/EXPERIMENT_ID/suggestions -u "$SIGOPT_API_TOKEN":`

Java

Suggestion suggestion = new Experiment(EXPERIMENT_ID).suggestions().create().call();

Response

{
  "assignments": {
    "degree": 2,
    "gamma": 3.6,
    "kernel": "rbf"
  },
  "created": 1414800000,
  "experiment": "1",
  "id": "1",
  "object": "queued_suggestion"
}

Create a manual suggestion with custom parameter values

Python

suggestion = conn.experiments(EXPERIMENT_ID).suggestions().create(
  assignments=dict(
    degree=2,
    gamma=3.6,
    kernel="rbf"
    )
  )

Bash

SUGGESTION=`curl -s -X POST https://api.sigopt.com/v1/experiments/EXPERIMENT_ID/suggestions -u "$SIGOPT_API_TOKEN": \
  -H 'Content-Type: application/json' \
  -d "{\"assignments\":{\"degree\":2,\"gamma"\:3.6,\"kernel\":\"rbf\"}}"`

Java

Suggestion suggestion = new Experiment(EXPERIMENT_ID).suggestions().create()
  .data(
    new Suggestion.Builder()
      .assignments(new Assignments.Builder()
        .set("degree", 2)
        .set("gamma", 3.6)
        .set("kernel", "rbf")
        .build())
      .build()
    )
  .call();

Response

{
  "assignments": {
    "degree": 2,
    "gamma": 3.6,
    "kernel": "rbf"
  },
  "created": 1414800000,
  "deleted": null,
  "experiment": "1",
  "id": "1",
  "metadata": null,
  "object": "suggestion",
  "state": "open"
}