Google Prediction API

Google Cloud Prediction API provides a RESTful API to build Machine Learning models.

https://cloud.google.com/prediction/docs/

follow https://cloud.google.com/prediction/docs/quickstart

steps:

1. create a cloud platform project: predictionapi0
2. enable billing
3. enable API
4. download training data (txt file)
5. create bucket: jychstar-bucket, upload txt file to bucket
6. train model in https://developers.google.com/apis-explorer/#p/prediction/v1.6/prediction.trainedmodels.insert
   project: predicitonapi0
   request body: {
   “id”: “language-identifier”,
   “storageDataLocation”: “jychstar_bucket/language_id.txt”
   }
7. check training status: running or done in https://developers.google.com/apis-explorer/#p/prediction/v1.6/prediction.trainedmodels.get
8. input unseen data in trained model: https://www.googleapis.com/prediction/v1.6/projects/prediction-docs/trainedmodels/language-identifier/predict
9. delete model https://developers.google.com/apis-explorer/#p/prediction/v1.6/prediction.trainedmodels.delete
10. delete bucket https://console.cloud.google.com/storage/
11. delete project https://console.cloud.google.com/iam-admin/projects

It turns out this language-identifier API is only a toy, with 403 input instances and 3-class labels(English, French, Spanish). It is a blackbox that are written for a specific purpose.

The business model for prediction API is $0.50/ 1000 prediction after 10 k free prediction. And they charged the training as well. I think such API is application specific. As a black box, it should generalize well enough to be useful in the changing world.

https://cloud.google.com/products/

Some mature APIs are:

• Natural language analysis: syntax, entity, sentiment
• speech to text
• translation
• image analysis
• video analysis

​