IMLServiceProxy class

Level: advanced

note

The functionality is relevant to Classic UI.

The IMLServiceProxy class implements the IMLServiceProxy interface. It is the proxy to the prediction service and a wrapper class for HTTP requests to a prediction service.

Methods

UploadData()

Send a data package for the training session.

---

BeginTraining()

Call the service to place the model in the training queue.

---

GetTrainingSessionInfo()

Query the current model state from the service for the training session.

---

Classify(
    Guid modelInstanceUId,
    Dictionary<string, object> data
)

Call the prediction service of the field value based on a single set of field values. Uses a previously trained model instance. If the result is successful, the method returns a list of values whose type is ClassificationResult.

Parameters

modelInstanceUId	The unique ID of the previously trained model instance. Used to specify which model to apply for classification.
Dictionary<string, object> data	A dictionary that includes the input field values for classification. The key is the field name. It must match the name defined in the Query metadata for selecting additional training data (MetaData code) field of the ML model (MLModel code) lookup. The value is the actual field value provided for prediction.

ClassificationResult properties

Value	Field value.
Probability	The probability of a received value in the [0:1] range. The sum of the probabilities for one list of results is close to 1. Values ​​of about 0 can be omitted.
Significance	The importance level of the prediction. Available values High A distinct advantage over other values ​​from the list. Only one element in the prediction list can have this level. Medium The value of the field is close to several other high values ​​in the list. For example, two values ​​in the list have a probability of 0.41 and 0.39, and all the others are significantly smaller. None Irrelevant values ​​that have low probabilities.