Sample application illustrating use of the Google Prediction API within the Google App Engine environmentTry Prediction (v1.0)
The application presents a simple interactive user experience: select a prediction model, enter a corresponding set of input text and submit your prediction request. For classification models, a graphical response is provided showing the confidence level for each category in the selected model. For regression models, a numerical result is presented.
The set of models supported and the corresponding input fields are entirely dynamic and controlled by a runtime text file (rc/models.json). You can freely add, change or remove models without changing any source code.
Web services in this domain typically provide access to a prediction model via a common set of shared security credentials. In this model, there is no need to force end users to perform the OAuth token granting sequence – authorization of end users is entirely up to the discretion of the application provider. This shared-server authorization model is one of the key elements being illustrated in this sample application.
You can try a live instance of this application at http://try-prediction.appspot.com.