×

Predict outcome

Launches a task that predicts outcome for an unlabeled dataset using a model found by a finished analysis.

Request:

POST /api/public/v1/analysis/:analysisId/predict/:datasetId
{ modelKey: string, signatureIndex: number }

The analysisId identifies the analysis. The datasetId identifies a dataset containing unlabeled data. The two must belong to the same project, and the user must have read and execute permissions to that project. The modelKey must be a model identifier present in models of analysis result e.g. "best" or "interpretable". The signatureIndex is the zero-based index of the model signature to use for the predictions.

Response:

{ payload: { predictionId: string }, status: "success" }

The predictionId can be used to query about the status of the prediction task which is performed asynchronously by the server. It also provides access to the predicted results, once available.

Example

$ http --body https://jadapi.jadbio.com/api/public/v1/analysis/79/predict/109 \
       "Authorization: Bearer $(cat ~/.jadtoken)" \
       modelKey=best \
       signatureIndex:=0
{
    "payload": {
        "predictionId": "314",
    },
    "status": "success"
}

---

Note of appreciation to JADBio users

We constantly make changes in the software and do our best to update these materials, but you may notice some differences. We welcome your feedback on how to make this more useful for you and requests for future tutorials.