MachineLearning / Client / create_evaluation
create_evaluation#
- MachineLearning.Client.create_evaluation(**kwargs)#
Creates a new
Evaluation
of anMLModel
. AnMLModel
is evaluated on a set of observations associated to aDataSource
. Like aDataSource
for anMLModel
, theDataSource
for anEvaluation
contains values for theTarget Variable
. TheEvaluation
compares the predicted result for each observation to the actual outcome and provides a summary so that you know how effective theMLModel
functions on the test data. Evaluation generates a relevant performance metric, such as BinaryAUC, RegressionRMSE or MulticlassAvgFScore based on the correspondingMLModelType
:BINARY
,REGRESSION
orMULTICLASS
.CreateEvaluation
is an asynchronous operation. In response toCreateEvaluation
, Amazon Machine Learning (Amazon ML) immediately returns and sets the evaluation status toPENDING
. After theEvaluation
is created and ready for use, Amazon ML sets the status toCOMPLETED
.You can use the
GetEvaluation
operation to check progress of the evaluation during the creation operation.See also: AWS API Documentation
Request Syntax
response = client.create_evaluation( EvaluationId='string', EvaluationName='string', MLModelId='string', EvaluationDataSourceId='string' )
- Parameters:
EvaluationId (string) –
[REQUIRED]
A user-supplied ID that uniquely identifies the
Evaluation
.EvaluationName (string) – A user-supplied name or description of the
Evaluation
.MLModelId (string) –
[REQUIRED]
The ID of the
MLModel
to evaluate.The schema used in creating the
MLModel
must match the schema of theDataSource
used in theEvaluation
.EvaluationDataSourceId (string) –
[REQUIRED]
The ID of the
DataSource
for the evaluation. The schema of theDataSource
must match the schema used to create theMLModel
.
- Return type:
dict
- Returns:
Response Syntax
{ 'EvaluationId': 'string' }
Response Structure
(dict) –
Represents the output of a
CreateEvaluation
operation, and is an acknowledgement that Amazon ML received the request.CreateEvaluation
operation is asynchronous. You can poll for status updates by using theGetEvcaluation
operation and checking theStatus
parameter.EvaluationId (string) –
The user-supplied ID that uniquely identifies the
Evaluation
. This value should be identical to the value of theEvaluationId
in the request.
Exceptions
MachineLearning.Client.exceptions.InvalidInputException
MachineLearning.Client.exceptions.InternalServerException
MachineLearning.Client.exceptions.IdempotentParameterMismatchException