IMLModelTrainer class
The IMLModelTrainer
class implements the IMLModelTrainer
interface. The class trains the prediction model and is responsible for the overall processing of a single model during the training stage. Communication with the service is provided through a proxy to a predictive service.
Methods
StartTrainSession()
Set the training session for the model.
UploadData()
Transfer data according to the model selection in packages of 1000 records. The selection size is limited to 75 000 records.
BeginTraining()
Indicate the completion of data transfer and inform the service about the need to place the model in the training queue.
UpdateModelState()
Query the service for the current model state and update the Status (State
code) field value if needed. If the training is successful, i. e., the Status (State
code) field value is set to "Done," the service returns the properties for the trained instance, particularly the accuracy of the resulting instance. If the precision is greater than or equal to the lower threshold, i. e., the Quality metric lower limit (MetricThreshold
code) field value, the ID of the new instance is written in the Model instance Id (ModelInstanceUId
code).