Amazon Machine Learning 2014-12-12
- Client: Aws\MachineLearning\MachineLearningClient
- Service ID: machinelearning
- Version: 2014-12-12
This page describes the parameters and results for the operations of the Amazon Machine Learning (2014-12-12), and shows how to use the Aws\MachineLearning\MachineLearningClient object to call the described operations. This documentation is specific to the 2014-12-12 API version of the service.
Operation Summary
Each of the following operations can be created from a client using
$client->getCommand('CommandName')
, where "CommandName" is the
name of one of the following operations. Note: a command is a value that
encapsulates an operation and the parameters used to create an HTTP request.
You can also create and send a command immediately using the magic methods
available on a client object: $client->commandName(/* parameters */)
.
You can send the command asynchronously (returning a promise) by appending the
word "Async" to the operation name: $client->commandNameAsync(/* parameters */)
.
- AddTags ( array $params = [] )
- Adds one or more tags to an object, up to a limit of 10.
- CreateBatchPrediction ( array $params = [] )
- Generates predictions for a group of observations.
- CreateDataSourceFromRDS ( array $params = [] )
- Creates a DataSource object from an Amazon Relational Database Service (Amazon RDS).
- CreateDataSourceFromRedshift ( array $params = [] )
- Creates a DataSource from a database hosted on an Amazon Redshift cluster.
- CreateDataSourceFromS3 ( array $params = [] )
- Creates a DataSource object.
- CreateEvaluation ( array $params = [] )
- Creates a new Evaluation of an MLModel.
- CreateMLModel ( array $params = [] )
- Creates a new MLModel using the DataSource and the recipe as information sources.
- CreateRealtimeEndpoint ( array $params = [] )
- Creates a real-time endpoint for the MLModel.
- DeleteBatchPrediction ( array $params = [] )
- Assigns the DELETED status to a BatchPrediction, rendering it unusable.
- DeleteDataSource ( array $params = [] )
- Assigns the DELETED status to a DataSource, rendering it unusable.
- DeleteEvaluation ( array $params = [] )
- Assigns the DELETED status to an Evaluation, rendering it unusable.
- DeleteMLModel ( array $params = [] )
- Assigns the DELETED status to an MLModel, rendering it unusable.
- DeleteRealtimeEndpoint ( array $params = [] )
- Deletes a real time endpoint of an MLModel.
- DeleteTags ( array $params = [] )
- Deletes the specified tags associated with an ML object.
- DescribeBatchPredictions ( array $params = [] )
- Returns a list of BatchPrediction operations that match the search criteria in the request.
- DescribeDataSources ( array $params = [] )
- Returns a list of DataSource that match the search criteria in the request.
- DescribeEvaluations ( array $params = [] )
- Returns a list of DescribeEvaluations that match the search criteria in the request.
- DescribeMLModels ( array $params = [] )
- Returns a list of MLModel that match the search criteria in the request.
- DescribeTags ( array $params = [] )
- Describes one or more of the tags for your Amazon ML object.
- GetBatchPrediction ( array $params = [] )
- Returns a BatchPrediction that includes detailed metadata, status, and data file information for a Batch Prediction request.
- GetDataSource ( array $params = [] )
- Returns a DataSource that includes metadata and data file information, as well as the current status of the DataSource.
- GetEvaluation ( array $params = [] )
- Returns an Evaluation that includes metadata as well as the current status of the Evaluation.
- GetMLModel ( array $params = [] )
- Returns an MLModel that includes detailed metadata, data source information, and the current status of the MLModel.
- Predict ( array $params = [] )
- Generates a prediction for the observation using the specified ML Model.
- UpdateBatchPrediction ( array $params = [] )
- Updates the BatchPredictionName of a BatchPrediction.
- UpdateDataSource ( array $params = [] )
- Updates the DataSourceName of a DataSource.
- UpdateEvaluation ( array $params = [] )
- Updates the EvaluationName of an Evaluation.
- UpdateMLModel ( array $params = [] )
- Updates the MLModelName and the ScoreThreshold of an MLModel.
Paginators
Paginators handle automatically iterating over paginated API results. Paginators are associated with specific API operations, and they accept the parameters that the corresponding API operation accepts. You can get a paginator from a client class using getPaginator($paginatorName, $operationParameters). This client supports the following paginators:
Waiters
Waiters allow you to poll a resource until it enters into a desired state. A waiter has a name used to describe what it does, and is associated with an API operation. When creating a waiter, you can provide the API operation parameters associated with the corresponding operation. Waiters can be accessed using the getWaiter($waiterName, $operationParameters) method of a client object. This client supports the following waiters:
Waiter name | API Operation | Delay | Max Attempts |
---|---|---|---|
DataSourceAvailable | DescribeDataSources | 30 | 60 |
MLModelAvailable | DescribeMLModels | 30 | 60 |
EvaluationAvailable | DescribeEvaluations | 30 | 60 |
BatchPredictionAvailable | DescribeBatchPredictions | 30 | 60 |
Operations
AddTags
$result = $client->addTags
([/* ... */]); $promise = $client->addTagsAsync
([/* ... */]);
Adds one or more tags to an object, up to a limit of 10. Each tag consists of a key and an optional value. If you add a tag using a key that is already associated with the ML object, AddTags
updates the tag's value.
Parameter Syntax
$result = $client->addTags([ 'ResourceId' => '<string>', // REQUIRED 'ResourceType' => 'BatchPrediction|DataSource|Evaluation|MLModel', // REQUIRED 'Tags' => [ // REQUIRED [ 'Key' => '<string>', 'Value' => '<string>', ], // ... ], ]);
Parameter Details
Members
- ResourceId
-
- Required: Yes
- Type: string
The ID of the ML object to tag. For example,
exampleModelId
. - ResourceType
-
- Required: Yes
- Type: string
The type of the ML object to tag.
- Tags
-
- Required: Yes
- Type: Array of Tag structures
The key-value pairs to use to create tags. If you specify a key without specifying a value, Amazon ML creates a tag with the specified key and a value of null.
Result Syntax
[ 'ResourceId' => '<string>', 'ResourceType' => 'BatchPrediction|DataSource|Evaluation|MLModel', ]
Result Details
Members
- ResourceId
-
- Type: string
The ID of the ML object that was tagged.
- ResourceType
-
- Type: string
The type of the ML object that was tagged.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InvalidTagException:
- This error does not currently have a description.
- TagLimitExceededException:
- This error does not currently have a description.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
CreateBatchPrediction
$result = $client->createBatchPrediction
([/* ... */]); $promise = $client->createBatchPredictionAsync
([/* ... */]);
Generates predictions for a group of observations. The observations to process exist in one or more data files referenced by a DataSource
. This operation creates a new BatchPrediction
, and uses an MLModel
and the data files referenced by the DataSource
as information sources.
CreateBatchPrediction
is an asynchronous operation. In response to CreateBatchPrediction
, Amazon Machine Learning (Amazon ML) immediately returns and sets the BatchPrediction
status to PENDING
. After the BatchPrediction
completes, Amazon ML sets the status to COMPLETED
.
You can poll for status updates by using the GetBatchPrediction operation and checking the Status
parameter of the result. After the COMPLETED
status appears, the results are available in the location specified by the OutputUri
parameter.
Parameter Syntax
$result = $client->createBatchPrediction([ 'BatchPredictionDataSourceId' => '<string>', // REQUIRED 'BatchPredictionId' => '<string>', // REQUIRED 'BatchPredictionName' => '<string>', 'MLModelId' => '<string>', // REQUIRED 'OutputUri' => '<string>', // REQUIRED ]);
Parameter Details
Members
- BatchPredictionDataSourceId
-
- Required: Yes
- Type: string
The ID of the
DataSource
that points to the group of observations to predict. - BatchPredictionId
-
- Required: Yes
- Type: string
A user-supplied ID that uniquely identifies the
BatchPrediction
. - BatchPredictionName
-
- Type: string
A user-supplied name or description of the
BatchPrediction
.BatchPredictionName
can only use the UTF-8 character set. - MLModelId
-
- Required: Yes
- Type: string
The ID of the
MLModel
that will generate predictions for the group of observations. - OutputUri
-
- Required: Yes
- Type: string
The location of an Amazon Simple Storage Service (Amazon S3) bucket or directory to store the batch prediction results. The following substrings are not allowed in the
s3 key
portion of theoutputURI
field: ':', '//', '/./', '/../'.Amazon ML needs permissions to store and retrieve the logs on your behalf. For information about how to set permissions, see the Amazon Machine Learning Developer Guide.
Result Syntax
[ 'BatchPredictionId' => '<string>', ]
Result Details
Members
- BatchPredictionId
-
- Type: string
A user-supplied ID that uniquely identifies the
BatchPrediction
. This value is identical to the value of theBatchPredictionId
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
- IdempotentParameterMismatchException:
A second request to use or change an object was not allowed. This can result from retrying a request using a parameter that was not present in the original request.
CreateDataSourceFromRDS
$result = $client->createDataSourceFromRDS
([/* ... */]); $promise = $client->createDataSourceFromRDSAsync
([/* ... */]);
Creates a DataSource
object from an Amazon Relational Database Service (Amazon RDS). A DataSource
references data that can be used to perform CreateMLModel
, CreateEvaluation
, or CreateBatchPrediction
operations.
CreateDataSourceFromRDS
is an asynchronous operation. In response to CreateDataSourceFromRDS
, Amazon Machine Learning (Amazon ML) immediately returns and sets the DataSource
status to PENDING
. After the DataSource
is created and ready for use, Amazon ML sets the Status
parameter to COMPLETED
. DataSource
in the COMPLETED
or PENDING
state can be used only to perform >CreateMLModel
>, CreateEvaluation
, or CreateBatchPrediction
operations.
If Amazon ML cannot accept the input source, it sets the Status
parameter to FAILED
and includes an error message in the Message
attribute of the GetDataSource
operation response.
Parameter Syntax
$result = $client->createDataSourceFromRDS([ 'ComputeStatistics' => true || false, 'DataSourceId' => '<string>', // REQUIRED 'DataSourceName' => '<string>', 'RDSData' => [ // REQUIRED 'DataRearrangement' => '<string>', 'DataSchema' => '<string>', 'DataSchemaUri' => '<string>', 'DatabaseCredentials' => [ // REQUIRED 'Password' => '<string>', // REQUIRED 'Username' => '<string>', // REQUIRED ], 'DatabaseInformation' => [ // REQUIRED 'DatabaseName' => '<string>', // REQUIRED 'InstanceIdentifier' => '<string>', // REQUIRED ], 'ResourceRole' => '<string>', // REQUIRED 'S3StagingLocation' => '<string>', // REQUIRED 'SecurityGroupIds' => ['<string>', ...], // REQUIRED 'SelectSqlQuery' => '<string>', // REQUIRED 'ServiceRole' => '<string>', // REQUIRED 'SubnetId' => '<string>', // REQUIRED ], 'RoleARN' => '<string>', // REQUIRED ]);
Parameter Details
Members
- ComputeStatistics
-
- Type: boolean
The compute statistics for a
DataSource
. The statistics are generated from the observation data referenced by aDataSource
. Amazon ML uses the statistics internally duringMLModel
training. This parameter must be set totrue
if theDataSource
needs to be used for
MLModel
training. - DataSourceId
-
- Required: Yes
- Type: string
A user-supplied ID that uniquely identifies the
DataSource
. Typically, an Amazon Resource Number (ARN) becomes the ID for aDataSource
. - DataSourceName
-
- Type: string
A user-supplied name or description of the
DataSource
. - RDSData
-
- Required: Yes
- Type: RDSDataSpec structure
The data specification of an Amazon RDS
DataSource
:-
DatabaseInformation -
-
DatabaseName
- The name of the Amazon RDS database. -
InstanceIdentifier
- A unique identifier for the Amazon RDS database instance.
-
-
DatabaseCredentials - AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon RDS database.
-
ResourceRole - A role (DataPipelineDefaultResourceRole) assumed by an EC2 instance to carry out the copy task from Amazon RDS to Amazon Simple Storage Service (Amazon S3). For more information, see Role templates for data pipelines.
-
ServiceRole - A role (DataPipelineDefaultRole) assumed by the AWS Data Pipeline service to monitor the progress of the copy task from Amazon RDS to Amazon S3. For more information, see Role templates for data pipelines.
-
SecurityInfo - The security information to use to access an RDS DB instance. You need to set up appropriate ingress rules for the security entity IDs provided to allow access to the Amazon RDS instance. Specify a [
SubnetId
,SecurityGroupIds
] pair for a VPC-based RDS DB instance. -
SelectSqlQuery - A query that is used to retrieve the observation data for the
Datasource
. -
S3StagingLocation - The Amazon S3 location for staging Amazon RDS data. The data retrieved from Amazon RDS using
SelectSqlQuery
is stored in this location. -
DataSchemaUri - The Amazon S3 location of the
DataSchema
. -
DataSchema - A JSON string representing the schema. This is not required if
DataSchemaUri
is specified. -
DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the
Datasource
.Sample -
"{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"
- RoleARN
-
- Required: Yes
- Type: string
The role that Amazon ML assumes on behalf of the user to create and activate a data pipeline in the user's account and copy data using the
SelectSqlQuery
query from Amazon RDS to Amazon S3.
Result Syntax
[ 'DataSourceId' => '<string>', ]
Result Details
Members
- DataSourceId
-
- Type: string
A user-supplied ID that uniquely identifies the datasource. This value should be identical to the value of the
DataSourceID
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
- IdempotentParameterMismatchException:
A second request to use or change an object was not allowed. This can result from retrying a request using a parameter that was not present in the original request.
CreateDataSourceFromRedshift
$result = $client->createDataSourceFromRedshift
([/* ... */]); $promise = $client->createDataSourceFromRedshiftAsync
([/* ... */]);
Creates a DataSource
from a database hosted on an Amazon Redshift cluster. A DataSource
references data that can be used to perform either CreateMLModel
, CreateEvaluation
, or CreateBatchPrediction
operations.
CreateDataSourceFromRedshift
is an asynchronous operation. In response to CreateDataSourceFromRedshift
, Amazon Machine Learning (Amazon ML) immediately returns and sets the DataSource
status to PENDING
. After the DataSource
is created and ready for use, Amazon ML sets the Status
parameter to COMPLETED
. DataSource
in COMPLETED
or PENDING
states can be used to perform only CreateMLModel
, CreateEvaluation
, or CreateBatchPrediction
operations.
If Amazon ML can't accept the input source, it sets the Status
parameter to FAILED
and includes an error message in the Message
attribute of the GetDataSource
operation response.
The observations should be contained in the database hosted on an Amazon Redshift cluster and should be specified by a SelectSqlQuery
query. Amazon ML executes an Unload
command in Amazon Redshift to transfer the result set of the SelectSqlQuery
query to S3StagingLocation
.
After the DataSource
has been created, it's ready for use in evaluations and batch predictions. If you plan to use the DataSource
to train an MLModel
, the DataSource
also requires a recipe. A recipe describes how each input variable will be used in training an MLModel
. Will the variable be included or excluded from training? Will the variable be manipulated; for example, will it be combined with another variable or will it be split apart into word combinations? The recipe provides answers to these questions.
You can't change an existing datasource, but you can copy and modify the settings from an existing Amazon Redshift datasource to create a new datasource. To do so, call GetDataSource
for an existing datasource and copy the values to a CreateDataSource
call. Change the settings that you want to change and make sure that all required fields have the appropriate values.
Parameter Syntax
$result = $client->createDataSourceFromRedshift([ 'ComputeStatistics' => true || false, 'DataSourceId' => '<string>', // REQUIRED 'DataSourceName' => '<string>', 'DataSpec' => [ // REQUIRED 'DataRearrangement' => '<string>', 'DataSchema' => '<string>', 'DataSchemaUri' => '<string>', 'DatabaseCredentials' => [ // REQUIRED 'Password' => '<string>', // REQUIRED 'Username' => '<string>', // REQUIRED ], 'DatabaseInformation' => [ // REQUIRED 'ClusterIdentifier' => '<string>', // REQUIRED 'DatabaseName' => '<string>', // REQUIRED ], 'S3StagingLocation' => '<string>', // REQUIRED 'SelectSqlQuery' => '<string>', // REQUIRED ], 'RoleARN' => '<string>', // REQUIRED ]);
Parameter Details
Members
- ComputeStatistics
-
- Type: boolean
The compute statistics for a
DataSource
. The statistics are generated from the observation data referenced by aDataSource
. Amazon ML uses the statistics internally duringMLModel
training. This parameter must be set totrue
if theDataSource
needs to be used forMLModel
training. - DataSourceId
-
- Required: Yes
- Type: string
A user-supplied ID that uniquely identifies the
DataSource
. - DataSourceName
-
- Type: string
A user-supplied name or description of the
DataSource
. - DataSpec
-
- Required: Yes
- Type: RedshiftDataSpec structure
The data specification of an Amazon Redshift
DataSource
:-
DatabaseInformation -
-
DatabaseName
- The name of the Amazon Redshift database. -
ClusterIdentifier
- The unique ID for the Amazon Redshift cluster.
-
-
DatabaseCredentials - The AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon Redshift database.
-
SelectSqlQuery - The query that is used to retrieve the observation data for the
Datasource
. -
S3StagingLocation - The Amazon Simple Storage Service (Amazon S3) location for staging Amazon Redshift data. The data retrieved from Amazon Redshift using the
SelectSqlQuery
query is stored in this location. -
DataSchemaUri - The Amazon S3 location of the
DataSchema
. -
DataSchema - A JSON string representing the schema. This is not required if
DataSchemaUri
is specified. -
DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the
DataSource
.Sample -
"{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"
- RoleARN
-
- Required: Yes
- Type: string
A fully specified role Amazon Resource Name (ARN). Amazon ML assumes the role on behalf of the user to create the following:
-
A security group to allow Amazon ML to execute the
SelectSqlQuery
query on an Amazon Redshift cluster -
An Amazon S3 bucket policy to grant Amazon ML read/write permissions on the
S3StagingLocation
Result Syntax
[ 'DataSourceId' => '<string>', ]
Result Details
Members
- DataSourceId
-
- Type: string
A user-supplied ID that uniquely identifies the datasource. This value should be identical to the value of the
DataSourceID
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
- IdempotentParameterMismatchException:
A second request to use or change an object was not allowed. This can result from retrying a request using a parameter that was not present in the original request.
CreateDataSourceFromS3
$result = $client->createDataSourceFromS3
([/* ... */]); $promise = $client->createDataSourceFromS3Async
([/* ... */]);
Creates a DataSource
object. A DataSource
references data that can be used to perform CreateMLModel
, CreateEvaluation
, or CreateBatchPrediction
operations.
CreateDataSourceFromS3
is an asynchronous operation. In response to CreateDataSourceFromS3
, Amazon Machine Learning (Amazon ML) immediately returns and sets the DataSource
status to PENDING
. After the DataSource
has been created and is ready for use, Amazon ML sets the Status
parameter to COMPLETED
. DataSource
in the COMPLETED
or PENDING
state can be used to perform only CreateMLModel
, CreateEvaluation
or CreateBatchPrediction
operations.
If Amazon ML can't accept the input source, it sets the Status
parameter to FAILED
and includes an error message in the Message
attribute of the GetDataSource
operation response.
The observation data used in a DataSource
should be ready to use; that is, it should have a consistent structure, and missing data values should be kept to a minimum. The observation data must reside in one or more .csv files in an Amazon Simple Storage Service (Amazon S3) location, along with a schema that describes the data items by name and type. The same schema must be used for all of the data files referenced by the DataSource
.
After the DataSource
has been created, it's ready to use in evaluations and batch predictions. If you plan to use the DataSource
to train an MLModel
, the DataSource
also needs a recipe. A recipe describes how each input variable will be used in training an MLModel
. Will the variable be included or excluded from training? Will the variable be manipulated; for example, will it be combined with another variable or will it be split apart into word combinations? The recipe provides answers to these questions.
Parameter Syntax
$result = $client->createDataSourceFromS3([ 'ComputeStatistics' => true || false, 'DataSourceId' => '<string>', // REQUIRED 'DataSourceName' => '<string>', 'DataSpec' => [ // REQUIRED 'DataLocationS3' => '<string>', // REQUIRED 'DataRearrangement' => '<string>', 'DataSchema' => '<string>', 'DataSchemaLocationS3' => '<string>', ], ]);
Parameter Details
Members
- ComputeStatistics
-
- Type: boolean
The compute statistics for a
DataSource
. The statistics are generated from the observation data referenced by aDataSource
. Amazon ML uses the statistics internally duringMLModel
training. This parameter must be set totrue
if theDataSource
needs to be used for
MLModel
training. - DataSourceId
-
- Required: Yes
- Type: string
A user-supplied identifier that uniquely identifies the
DataSource
. - DataSourceName
-
- Type: string
A user-supplied name or description of the
DataSource
. - DataSpec
-
- Required: Yes
- Type: S3DataSpec structure
The data specification of a
DataSource
:-
DataLocationS3 - The Amazon S3 location of the observation data.
-
DataSchemaLocationS3 - The Amazon S3 location of the
DataSchema
. -
DataSchema - A JSON string representing the schema. This is not required if
DataSchemaUri
is specified. -
DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the
Datasource
.Sample -
"{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"
Result Syntax
[ 'DataSourceId' => '<string>', ]
Result Details
Members
- DataSourceId
-
- Type: string
A user-supplied ID that uniquely identifies the
DataSource
. This value should be identical to the value of theDataSourceID
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
- IdempotentParameterMismatchException:
A second request to use or change an object was not allowed. This can result from retrying a request using a parameter that was not present in the original request.
CreateEvaluation
$result = $client->createEvaluation
([/* ... */]); $promise = $client->createEvaluationAsync
([/* ... */]);
Creates a new Evaluation
of an MLModel
. An MLModel
is evaluated on a set of observations associated to a DataSource
. Like a DataSource
for an MLModel
, the DataSource
for an Evaluation
contains values for the Target Variable
. The Evaluation
compares the predicted result for each observation to the actual outcome and provides a summary so that you know how effective the MLModel
functions on the test data. Evaluation generates a relevant performance metric, such as BinaryAUC, RegressionRMSE or MulticlassAvgFScore based on the corresponding MLModelType
: BINARY
, REGRESSION
or MULTICLASS
.
CreateEvaluation
is an asynchronous operation. In response to CreateEvaluation
, Amazon Machine Learning (Amazon ML) immediately returns and sets the evaluation status to PENDING
. After the Evaluation
is created and ready for use, Amazon ML sets the status to COMPLETED
.
You can use the GetEvaluation
operation to check progress of the evaluation during the creation operation.
Parameter Syntax
$result = $client->createEvaluation([ 'EvaluationDataSourceId' => '<string>', // REQUIRED 'EvaluationId' => '<string>', // REQUIRED 'EvaluationName' => '<string>', 'MLModelId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- EvaluationDataSourceId
-
- Required: Yes
- Type: string
The ID of the
DataSource
for the evaluation. The schema of theDataSource
must match the schema used to create theMLModel
. - EvaluationId
-
- Required: Yes
- Type: string
A user-supplied ID that uniquely identifies the
Evaluation
. - EvaluationName
-
- Type: string
A user-supplied name or description of the
Evaluation
. - MLModelId
-
- Required: Yes
- Type: string
The ID of the
MLModel
to evaluate.The schema used in creating the
MLModel
must match the schema of theDataSource
used in theEvaluation
.
Result Syntax
[ 'EvaluationId' => '<string>', ]
Result Details
Members
- EvaluationId
-
- Type: string
The user-supplied ID that uniquely identifies the
Evaluation
. This value should be identical to the value of theEvaluationId
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
- IdempotentParameterMismatchException:
A second request to use or change an object was not allowed. This can result from retrying a request using a parameter that was not present in the original request.
CreateMLModel
$result = $client->createMLModel
([/* ... */]); $promise = $client->createMLModelAsync
([/* ... */]);
Creates a new MLModel
using the DataSource
and the recipe as information sources.
An MLModel
is nearly immutable. Users can update only the MLModelName
and the ScoreThreshold
in an MLModel
without creating a new MLModel
.
CreateMLModel
is an asynchronous operation. In response to CreateMLModel
, Amazon Machine Learning (Amazon ML) immediately returns and sets the MLModel
status to PENDING
. After the MLModel
has been created and ready is for use, Amazon ML sets the status to COMPLETED
.
You can use the GetMLModel
operation to check the progress of the MLModel
during the creation operation.
CreateMLModel
requires a DataSource
with computed statistics, which can be created by setting ComputeStatistics
to true
in CreateDataSourceFromRDS
, CreateDataSourceFromS3
, or CreateDataSourceFromRedshift
operations.
Parameter Syntax
$result = $client->createMLModel([ 'MLModelId' => '<string>', // REQUIRED 'MLModelName' => '<string>', 'MLModelType' => 'REGRESSION|BINARY|MULTICLASS', // REQUIRED 'Parameters' => ['<string>', ...], 'Recipe' => '<string>', 'RecipeUri' => '<string>', 'TrainingDataSourceId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- MLModelId
-
- Required: Yes
- Type: string
A user-supplied ID that uniquely identifies the
MLModel
. - MLModelName
-
- Type: string
A user-supplied name or description of the
MLModel
. - MLModelType
-
- Required: Yes
- Type: string
The category of supervised learning that this
MLModel
will address. Choose from the following types:-
Choose
REGRESSION
if theMLModel
will be used to predict a numeric value. -
Choose
BINARY
if theMLModel
result has two possible values. -
Choose
MULTICLASS
if theMLModel
result has a limited number of values.
For more information, see the Amazon Machine Learning Developer Guide.
- Parameters
-
- Type: Associative array of custom strings keys (StringType) to strings
A list of the training parameters in the
MLModel
. The list is implemented as a map of key-value pairs.The following is the current set of training parameters:
-
sgd.maxMLModelSizeInBytes
- The maximum allowed size of the model. Depending on the input data, the size of the model might affect its performance.The value is an integer that ranges from
100000
to2147483648
. The default value is33554432
. -
sgd.maxPasses
- The number of times that the training process traverses the observations to build theMLModel
. The value is an integer that ranges from1
to10000
. The default value is10
. -
sgd.shuffleType
- Whether Amazon ML shuffles the training data. Shuffling the data improves a model's ability to find the optimal solution for a variety of data types. The valid values areauto
andnone
. The default value isnone
. We strongly recommend that you shuffle your data. -
sgd.l1RegularizationAmount
- The coefficient regularization L1 norm. It controls overfitting the data by penalizing large coefficients. This tends to drive coefficients to zero, resulting in a sparse feature set. If you use this parameter, start by specifying a small value, such as1.0E-08
.The value is a double that ranges from
0
toMAX_DOUBLE
. The default is to not use L1 normalization. This parameter can't be used whenL2
is specified. Use this parameter sparingly. -
sgd.l2RegularizationAmount
- The coefficient regularization L2 norm. It controls overfitting the data by penalizing large coefficients. This tends to drive coefficients to small, nonzero values. If you use this parameter, start by specifying a small value, such as1.0E-08
.The value is a double that ranges from
0
toMAX_DOUBLE
. The default is to not use L2 normalization. This parameter can't be used whenL1
is specified. Use this parameter sparingly.
- Recipe
-
- Type: string
The data recipe for creating the
MLModel
. You must specify either the recipe or its URI. If you don't specify a recipe or its URI, Amazon ML creates a default. - RecipeUri
-
- Type: string
The Amazon Simple Storage Service (Amazon S3) location and file name that contains the
MLModel
recipe. You must specify either the recipe or its URI. If you don't specify a recipe or its URI, Amazon ML creates a default. - TrainingDataSourceId
-
- Required: Yes
- Type: string
The
DataSource
that points to the training data.
Result Syntax
[ 'MLModelId' => '<string>', ]
Result Details
Members
- MLModelId
-
- Type: string
A user-supplied ID that uniquely identifies the
MLModel
. This value should be identical to the value of theMLModelId
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
- IdempotentParameterMismatchException:
A second request to use or change an object was not allowed. This can result from retrying a request using a parameter that was not present in the original request.
CreateRealtimeEndpoint
$result = $client->createRealtimeEndpoint
([/* ... */]); $promise = $client->createRealtimeEndpointAsync
([/* ... */]);
Creates a real-time endpoint for the MLModel
. The endpoint contains the URI of the MLModel
; that is, the location to send real-time prediction requests for the specified MLModel
.
Parameter Syntax
$result = $client->createRealtimeEndpoint([ 'MLModelId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- MLModelId
-
- Required: Yes
- Type: string
The ID assigned to the
MLModel
during creation.
Result Syntax
[ 'MLModelId' => '<string>', 'RealtimeEndpointInfo' => [ 'CreatedAt' => <DateTime>, 'EndpointStatus' => 'NONE|READY|UPDATING|FAILED', 'EndpointUrl' => '<string>', 'PeakRequestsPerSecond' => <integer>, ], ]
Result Details
Members
- MLModelId
-
- Type: string
A user-supplied ID that uniquely identifies the
MLModel
. This value should be identical to the value of theMLModelId
in the request. - RealtimeEndpointInfo
-
- Type: RealtimeEndpointInfo structure
The endpoint information of the
MLModel
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
DeleteBatchPrediction
$result = $client->deleteBatchPrediction
([/* ... */]); $promise = $client->deleteBatchPredictionAsync
([/* ... */]);
Assigns the DELETED status to a BatchPrediction
, rendering it unusable.
After using the DeleteBatchPrediction
operation, you can use the GetBatchPrediction operation to verify that the status of the BatchPrediction
changed to DELETED.
Caution: The result of the DeleteBatchPrediction
operation is irreversible.
Parameter Syntax
$result = $client->deleteBatchPrediction([ 'BatchPredictionId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- BatchPredictionId
-
- Required: Yes
- Type: string
A user-supplied ID that uniquely identifies the
BatchPrediction
.
Result Syntax
[ 'BatchPredictionId' => '<string>', ]
Result Details
Members
- BatchPredictionId
-
- Type: string
A user-supplied ID that uniquely identifies the
BatchPrediction
. This value should be identical to the value of theBatchPredictionID
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
DeleteDataSource
$result = $client->deleteDataSource
([/* ... */]); $promise = $client->deleteDataSourceAsync
([/* ... */]);
Assigns the DELETED status to a DataSource
, rendering it unusable.
After using the DeleteDataSource
operation, you can use the GetDataSource operation to verify that the status of the DataSource
changed to DELETED.
Caution: The results of the DeleteDataSource
operation are irreversible.
Parameter Syntax
$result = $client->deleteDataSource([ 'DataSourceId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- DataSourceId
-
- Required: Yes
- Type: string
A user-supplied ID that uniquely identifies the
DataSource
.
Result Syntax
[ 'DataSourceId' => '<string>', ]
Result Details
Members
- DataSourceId
-
- Type: string
A user-supplied ID that uniquely identifies the
DataSource
. This value should be identical to the value of theDataSourceID
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
DeleteEvaluation
$result = $client->deleteEvaluation
([/* ... */]); $promise = $client->deleteEvaluationAsync
([/* ... */]);
Assigns the DELETED
status to an Evaluation
, rendering it unusable.
After invoking the DeleteEvaluation
operation, you can use the GetEvaluation
operation to verify that the status of the Evaluation
changed to DELETED
.
Caution: The results of the DeleteEvaluation
operation are irreversible.
Parameter Syntax
$result = $client->deleteEvaluation([ 'EvaluationId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- EvaluationId
-
- Required: Yes
- Type: string
A user-supplied ID that uniquely identifies the
Evaluation
to delete.
Result Syntax
[ 'EvaluationId' => '<string>', ]
Result Details
Members
- EvaluationId
-
- Type: string
A user-supplied ID that uniquely identifies the
Evaluation
. This value should be identical to the value of theEvaluationId
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
DeleteMLModel
$result = $client->deleteMLModel
([/* ... */]); $promise = $client->deleteMLModelAsync
([/* ... */]);
Assigns the DELETED
status to an MLModel
, rendering it unusable.
After using the DeleteMLModel
operation, you can use the GetMLModel
operation to verify that the status of the MLModel
changed to DELETED.
Caution: The result of the DeleteMLModel
operation is irreversible.
Parameter Syntax
$result = $client->deleteMLModel([ 'MLModelId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- MLModelId
-
- Required: Yes
- Type: string
A user-supplied ID that uniquely identifies the
MLModel
.
Result Syntax
[ 'MLModelId' => '<string>', ]
Result Details
Members
- MLModelId
-
- Type: string
A user-supplied ID that uniquely identifies the
MLModel
. This value should be identical to the value of theMLModelID
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
DeleteRealtimeEndpoint
$result = $client->deleteRealtimeEndpoint
([/* ... */]); $promise = $client->deleteRealtimeEndpointAsync
([/* ... */]);
Deletes a real time endpoint of an MLModel
.
Parameter Syntax
$result = $client->deleteRealtimeEndpoint([ 'MLModelId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- MLModelId
-
- Required: Yes
- Type: string
The ID assigned to the
MLModel
during creation.
Result Syntax
[ 'MLModelId' => '<string>', 'RealtimeEndpointInfo' => [ 'CreatedAt' => <DateTime>, 'EndpointStatus' => 'NONE|READY|UPDATING|FAILED', 'EndpointUrl' => '<string>', 'PeakRequestsPerSecond' => <integer>, ], ]
Result Details
Members
- MLModelId
-
- Type: string
A user-supplied ID that uniquely identifies the
MLModel
. This value should be identical to the value of theMLModelId
in the request. - RealtimeEndpointInfo
-
- Type: RealtimeEndpointInfo structure
The endpoint information of the
MLModel
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
DeleteTags
$result = $client->deleteTags
([/* ... */]); $promise = $client->deleteTagsAsync
([/* ... */]);
Deletes the specified tags associated with an ML object. After this operation is complete, you can't recover deleted tags.
If you specify a tag that doesn't exist, Amazon ML ignores it.
Parameter Syntax
$result = $client->deleteTags([ 'ResourceId' => '<string>', // REQUIRED 'ResourceType' => 'BatchPrediction|DataSource|Evaluation|MLModel', // REQUIRED 'TagKeys' => ['<string>', ...], // REQUIRED ]);
Parameter Details
Members
- ResourceId
-
- Required: Yes
- Type: string
The ID of the tagged ML object. For example,
exampleModelId
. - ResourceType
-
- Required: Yes
- Type: string
The type of the tagged ML object.
- TagKeys
-
- Required: Yes
- Type: Array of strings
One or more tags to delete.
Result Syntax
[ 'ResourceId' => '<string>', 'ResourceType' => 'BatchPrediction|DataSource|Evaluation|MLModel', ]
Result Details
Members
- ResourceId
-
- Type: string
The ID of the ML object from which tags were deleted.
- ResourceType
-
- Type: string
The type of the ML object from which tags were deleted.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InvalidTagException:
- This error does not currently have a description.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
DescribeBatchPredictions
$result = $client->describeBatchPredictions
([/* ... */]); $promise = $client->describeBatchPredictionsAsync
([/* ... */]);
Returns a list of BatchPrediction
operations that match the search criteria in the request.
Parameter Syntax
$result = $client->describeBatchPredictions([ 'EQ' => '<string>', 'FilterVariable' => 'CreatedAt|LastUpdatedAt|Status|Name|IAMUser|MLModelId|DataSourceId|DataURI', 'GE' => '<string>', 'GT' => '<string>', 'LE' => '<string>', 'LT' => '<string>', 'Limit' => <integer>, 'NE' => '<string>', 'NextToken' => '<string>', 'Prefix' => '<string>', 'SortOrder' => 'asc|dsc', ]);
Parameter Details
Members
- EQ
-
- Type: string
The equal to operator. The
BatchPrediction
results will haveFilterVariable
values that exactly match the value specified withEQ
. - FilterVariable
-
- Type: string
Use one of the following variables to filter a list of
BatchPrediction
:-
CreatedAt
- Sets the search criteria to theBatchPrediction
creation date. -
Status
- Sets the search criteria to theBatchPrediction
status. -
Name
- Sets the search criteria to the contents of theBatchPrediction
Name
. -
IAMUser
- Sets the search criteria to the user account that invoked theBatchPrediction
creation. -
MLModelId
- Sets the search criteria to theMLModel
used in theBatchPrediction
. -
DataSourceId
- Sets the search criteria to theDataSource
used in theBatchPrediction
. -
DataURI
- Sets the search criteria to the data file(s) used in theBatchPrediction
. The URL can identify either a file or an Amazon Simple Storage Solution (Amazon S3) bucket or directory.
- GE
-
- Type: string
The greater than or equal to operator. The
BatchPrediction
results will haveFilterVariable
values that are greater than or equal to the value specified withGE
. - GT
-
- Type: string
The greater than operator. The
BatchPrediction
results will haveFilterVariable
values that are greater than the value specified withGT
. - LE
-
- Type: string
The less than or equal to operator. The
BatchPrediction
results will haveFilterVariable
values that are less than or equal to the value specified withLE
. - LT
-
- Type: string
The less than operator. The
BatchPrediction
results will haveFilterVariable
values that are less than the value specified withLT
. - Limit
-
- Type: int
The number of pages of information to include in the result. The range of acceptable values is
1
through100
. The default value is100
. - NE
-
- Type: string
The not equal to operator. The
BatchPrediction
results will haveFilterVariable
values not equal to the value specified withNE
. - NextToken
-
- Type: string
An ID of the page in the paginated results.
- Prefix
-
- Type: string
A string that is found at the beginning of a variable, such as
Name
orId
.For example, a
Batch Prediction
operation could have theName
2014-09-09-HolidayGiftMailer
. To search for thisBatchPrediction
, selectName
for theFilterVariable
and any of the following strings for thePrefix
:-
2014-09
-
2014-09-09
-
2014-09-09-Holiday
- SortOrder
-
- Type: string
A two-value parameter that determines the sequence of the resulting list of
MLModel
s.-
asc
- Arranges the list in ascending order (A-Z, 0-9). -
dsc
- Arranges the list in descending order (Z-A, 9-0).
Results are sorted by
FilterVariable
.
Result Syntax
[ 'NextToken' => '<string>', 'Results' => [ [ 'BatchPredictionDataSourceId' => '<string>', 'BatchPredictionId' => '<string>', 'ComputeTime' => <integer>, 'CreatedAt' => <DateTime>, 'CreatedByIamUser' => '<string>', 'FinishedAt' => <DateTime>, 'InputDataLocationS3' => '<string>', 'InvalidRecordCount' => <integer>, 'LastUpdatedAt' => <DateTime>, 'MLModelId' => '<string>', 'Message' => '<string>', 'Name' => '<string>', 'OutputUri' => '<string>', 'StartedAt' => <DateTime>, 'Status' => 'PENDING|INPROGRESS|FAILED|COMPLETED|DELETED', 'TotalRecordCount' => <integer>, ], // ... ], ]
Result Details
Members
- NextToken
-
- Type: string
The ID of the next page in the paginated results that indicates at least one more page follows.
- Results
-
- Type: Array of BatchPrediction structures
A list of
BatchPrediction
objects that meet the search criteria.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
DescribeDataSources
$result = $client->describeDataSources
([/* ... */]); $promise = $client->describeDataSourcesAsync
([/* ... */]);
Returns a list of DataSource
that match the search criteria in the request.
Parameter Syntax
$result = $client->describeDataSources([ 'EQ' => '<string>', 'FilterVariable' => 'CreatedAt|LastUpdatedAt|Status|Name|DataLocationS3|IAMUser', 'GE' => '<string>', 'GT' => '<string>', 'LE' => '<string>', 'LT' => '<string>', 'Limit' => <integer>, 'NE' => '<string>', 'NextToken' => '<string>', 'Prefix' => '<string>', 'SortOrder' => 'asc|dsc', ]);
Parameter Details
Members
- EQ
-
- Type: string
The equal to operator. The
DataSource
results will haveFilterVariable
values that exactly match the value specified withEQ
. - FilterVariable
-
- Type: string
Use one of the following variables to filter a list of
DataSource
:-
CreatedAt
- Sets the search criteria toDataSource
creation dates. -
Status
- Sets the search criteria toDataSource
statuses. -
Name
- Sets the search criteria to the contents ofDataSource
Name
. -
DataUri
- Sets the search criteria to the URI of data files used to create theDataSource
. The URI can identify either a file or an Amazon Simple Storage Service (Amazon S3) bucket or directory. -
IAMUser
- Sets the search criteria to the user account that invoked theDataSource
creation.
- GE
-
- Type: string
The greater than or equal to operator. The
DataSource
results will haveFilterVariable
values that are greater than or equal to the value specified withGE
. - GT
-
- Type: string
The greater than operator. The
DataSource
results will haveFilterVariable
values that are greater than the value specified withGT
. - LE
-
- Type: string
The less than or equal to operator. The
DataSource
results will haveFilterVariable
values that are less than or equal to the value specified withLE
. - LT
-
- Type: string
The less than operator. The
DataSource
results will haveFilterVariable
values that are less than the value specified withLT
. - Limit
-
- Type: int
The maximum number of
DataSource
to include in the result. - NE
-
- Type: string
The not equal to operator. The
DataSource
results will haveFilterVariable
values not equal to the value specified withNE
. - NextToken
-
- Type: string
The ID of the page in the paginated results.
- Prefix
-
- Type: string
A string that is found at the beginning of a variable, such as
Name
orId
.For example, a
DataSource
could have theName
2014-09-09-HolidayGiftMailer
. To search for thisDataSource
, selectName
for theFilterVariable
and any of the following strings for thePrefix
:-
2014-09
-
2014-09-09
-
2014-09-09-Holiday
- SortOrder
-
- Type: string
A two-value parameter that determines the sequence of the resulting list of
DataSource
.-
asc
- Arranges the list in ascending order (A-Z, 0-9). -
dsc
- Arranges the list in descending order (Z-A, 9-0).
Results are sorted by
FilterVariable
.
Result Syntax
[ 'NextToken' => '<string>', 'Results' => [ [ 'ComputeStatistics' => true || false, 'ComputeTime' => <integer>, 'CreatedAt' => <DateTime>, 'CreatedByIamUser' => '<string>', 'DataLocationS3' => '<string>', 'DataRearrangement' => '<string>', 'DataSizeInBytes' => <integer>, 'DataSourceId' => '<string>', 'FinishedAt' => <DateTime>, 'LastUpdatedAt' => <DateTime>, 'Message' => '<string>', 'Name' => '<string>', 'NumberOfFiles' => <integer>, 'RDSMetadata' => [ 'DataPipelineId' => '<string>', 'Database' => [ 'DatabaseName' => '<string>', 'InstanceIdentifier' => '<string>', ], 'DatabaseUserName' => '<string>', 'ResourceRole' => '<string>', 'SelectSqlQuery' => '<string>', 'ServiceRole' => '<string>', ], 'RedshiftMetadata' => [ 'DatabaseUserName' => '<string>', 'RedshiftDatabase' => [ 'ClusterIdentifier' => '<string>', 'DatabaseName' => '<string>', ], 'SelectSqlQuery' => '<string>', ], 'RoleARN' => '<string>', 'StartedAt' => <DateTime>, 'Status' => 'PENDING|INPROGRESS|FAILED|COMPLETED|DELETED', ], // ... ], ]
Result Details
Members
- NextToken
-
- Type: string
An ID of the next page in the paginated results that indicates at least one more page follows.
- Results
-
- Type: Array of DataSource structures
A list of
DataSource
that meet the search criteria.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
DescribeEvaluations
$result = $client->describeEvaluations
([/* ... */]); $promise = $client->describeEvaluationsAsync
([/* ... */]);
Returns a list of DescribeEvaluations
that match the search criteria in the request.
Parameter Syntax
$result = $client->describeEvaluations([ 'EQ' => '<string>', 'FilterVariable' => 'CreatedAt|LastUpdatedAt|Status|Name|IAMUser|MLModelId|DataSourceId|DataURI', 'GE' => '<string>', 'GT' => '<string>', 'LE' => '<string>', 'LT' => '<string>', 'Limit' => <integer>, 'NE' => '<string>', 'NextToken' => '<string>', 'Prefix' => '<string>', 'SortOrder' => 'asc|dsc', ]);
Parameter Details
Members
- EQ
-
- Type: string
The equal to operator. The
Evaluation
results will haveFilterVariable
values that exactly match the value specified withEQ
. - FilterVariable
-
- Type: string
Use one of the following variable to filter a list of
Evaluation
objects:-
CreatedAt
- Sets the search criteria to theEvaluation
creation date. -
Status
- Sets the search criteria to theEvaluation
status. -
Name
- Sets the search criteria to the contents ofEvaluation
Name
. -
IAMUser
- Sets the search criteria to the user account that invoked anEvaluation
. -
MLModelId
- Sets the search criteria to theMLModel
that was evaluated. -
DataSourceId
- Sets the search criteria to theDataSource
used inEvaluation
. -
DataUri
- Sets the search criteria to the data file(s) used inEvaluation
. The URL can identify either a file or an Amazon Simple Storage Solution (Amazon S3) bucket or directory.
- GE
-
- Type: string
The greater than or equal to operator. The
Evaluation
results will haveFilterVariable
values that are greater than or equal to the value specified withGE
. - GT
-
- Type: string
The greater than operator. The
Evaluation
results will haveFilterVariable
values that are greater than the value specified withGT
. - LE
-
- Type: string
The less than or equal to operator. The
Evaluation
results will haveFilterVariable
values that are less than or equal to the value specified withLE
. - LT
-
- Type: string
The less than operator. The
Evaluation
results will haveFilterVariable
values that are less than the value specified withLT
. - Limit
-
- Type: int
The maximum number of
Evaluation
to include in the result. - NE
-
- Type: string
The not equal to operator. The
Evaluation
results will haveFilterVariable
values not equal to the value specified withNE
. - NextToken
-
- Type: string
The ID of the page in the paginated results.
- Prefix
-
- Type: string
A string that is found at the beginning of a variable, such as
Name
orId
.For example, an
Evaluation
could have theName
2014-09-09-HolidayGiftMailer
. To search for thisEvaluation
, selectName
for theFilterVariable
and any of the following strings for thePrefix
:-
2014-09
-
2014-09-09
-
2014-09-09-Holiday
- SortOrder
-
- Type: string
A two-value parameter that determines the sequence of the resulting list of
Evaluation
.-
asc
- Arranges the list in ascending order (A-Z, 0-9). -
dsc
- Arranges the list in descending order (Z-A, 9-0).
Results are sorted by
FilterVariable
.
Result Syntax
[ 'NextToken' => '<string>', 'Results' => [ [ 'ComputeTime' => <integer>, 'CreatedAt' => <DateTime>, 'CreatedByIamUser' => '<string>', 'EvaluationDataSourceId' => '<string>', 'EvaluationId' => '<string>', 'FinishedAt' => <DateTime>, 'InputDataLocationS3' => '<string>', 'LastUpdatedAt' => <DateTime>, 'MLModelId' => '<string>', 'Message' => '<string>', 'Name' => '<string>', 'PerformanceMetrics' => [ 'Properties' => ['<string>', ...], ], 'StartedAt' => <DateTime>, 'Status' => 'PENDING|INPROGRESS|FAILED|COMPLETED|DELETED', ], // ... ], ]
Result Details
Members
- NextToken
-
- Type: string
The ID of the next page in the paginated results that indicates at least one more page follows.
- Results
-
- Type: Array of Evaluation structures
A list of
Evaluation
that meet the search criteria.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
DescribeMLModels
$result = $client->describeMLModels
([/* ... */]); $promise = $client->describeMLModelsAsync
([/* ... */]);
Returns a list of MLModel
that match the search criteria in the request.
Parameter Syntax
$result = $client->describeMLModels([ 'EQ' => '<string>', 'FilterVariable' => 'CreatedAt|LastUpdatedAt|Status|Name|IAMUser|TrainingDataSourceId|RealtimeEndpointStatus|MLModelType|Algorithm|TrainingDataURI', 'GE' => '<string>', 'GT' => '<string>', 'LE' => '<string>', 'LT' => '<string>', 'Limit' => <integer>, 'NE' => '<string>', 'NextToken' => '<string>', 'Prefix' => '<string>', 'SortOrder' => 'asc|dsc', ]);
Parameter Details
Members
- EQ
-
- Type: string
The equal to operator. The
MLModel
results will haveFilterVariable
values that exactly match the value specified withEQ
. - FilterVariable
-
- Type: string
Use one of the following variables to filter a list of
MLModel
:-
CreatedAt
- Sets the search criteria toMLModel
creation date. -
Status
- Sets the search criteria toMLModel
status. -
Name
- Sets the search criteria to the contents ofMLModel
Name
. -
IAMUser
- Sets the search criteria to the user account that invoked theMLModel
creation. -
TrainingDataSourceId
- Sets the search criteria to theDataSource
used to train one or moreMLModel
. -
RealtimeEndpointStatus
- Sets the search criteria to theMLModel
real-time endpoint status. -
MLModelType
- Sets the search criteria toMLModel
type: binary, regression, or multi-class. -
Algorithm
- Sets the search criteria to the algorithm that theMLModel
uses. -
TrainingDataURI
- Sets the search criteria to the data file(s) used in training aMLModel
. The URL can identify either a file or an Amazon Simple Storage Service (Amazon S3) bucket or directory.
- GE
-
- Type: string
The greater than or equal to operator. The
MLModel
results will haveFilterVariable
values that are greater than or equal to the value specified withGE
. - GT
-
- Type: string
The greater than operator. The
MLModel
results will haveFilterVariable
values that are greater than the value specified withGT
. - LE
-
- Type: string
The less than or equal to operator. The
MLModel
results will haveFilterVariable
values that are less than or equal to the value specified withLE
. - LT
-
- Type: string
The less than operator. The
MLModel
results will haveFilterVariable
values that are less than the value specified withLT
. - Limit
-
- Type: int
The number of pages of information to include in the result. The range of acceptable values is
1
through100
. The default value is100
. - NE
-
- Type: string
The not equal to operator. The
MLModel
results will haveFilterVariable
values not equal to the value specified withNE
. - NextToken
-
- Type: string
The ID of the page in the paginated results.
- Prefix
-
- Type: string
A string that is found at the beginning of a variable, such as
Name
orId
.For example, an
MLModel
could have theName
2014-09-09-HolidayGiftMailer
. To search for thisMLModel
, selectName
for theFilterVariable
and any of the following strings for thePrefix
:-
2014-09
-
2014-09-09
-
2014-09-09-Holiday
- SortOrder
-
- Type: string
A two-value parameter that determines the sequence of the resulting list of
MLModel
.-
asc
- Arranges the list in ascending order (A-Z, 0-9). -
dsc
- Arranges the list in descending order (Z-A, 9-0).
Results are sorted by
FilterVariable
.
Result Syntax
[ 'NextToken' => '<string>', 'Results' => [ [ 'Algorithm' => 'sgd', 'ComputeTime' => <integer>, 'CreatedAt' => <DateTime>, 'CreatedByIamUser' => '<string>', 'EndpointInfo' => [ 'CreatedAt' => <DateTime>, 'EndpointStatus' => 'NONE|READY|UPDATING|FAILED', 'EndpointUrl' => '<string>', 'PeakRequestsPerSecond' => <integer>, ], 'FinishedAt' => <DateTime>, 'InputDataLocationS3' => '<string>', 'LastUpdatedAt' => <DateTime>, 'MLModelId' => '<string>', 'MLModelType' => 'REGRESSION|BINARY|MULTICLASS', 'Message' => '<string>', 'Name' => '<string>', 'ScoreThreshold' => <float>, 'ScoreThresholdLastUpdatedAt' => <DateTime>, 'SizeInBytes' => <integer>, 'StartedAt' => <DateTime>, 'Status' => 'PENDING|INPROGRESS|FAILED|COMPLETED|DELETED', 'TrainingDataSourceId' => '<string>', 'TrainingParameters' => ['<string>', ...], ], // ... ], ]
Result Details
Members
- NextToken
-
- Type: string
The ID of the next page in the paginated results that indicates at least one more page follows.
- Results
-
- Type: Array of MLModel structures
A list of
MLModel
that meet the search criteria.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- InternalServerException:
An error on the server occurred when trying to process a request.
DescribeTags
$result = $client->describeTags
([/* ... */]); $promise = $client->describeTagsAsync
([/* ... */]);
Describes one or more of the tags for your Amazon ML object.
Parameter Syntax
$result = $client->describeTags([ 'ResourceId' => '<string>', // REQUIRED 'ResourceType' => 'BatchPrediction|DataSource|Evaluation|MLModel', // REQUIRED ]);
Parameter Details
Members
- ResourceId
-
- Required: Yes
- Type: string
The ID of the ML object. For example,
exampleModelId
. - ResourceType
-
- Required: Yes
- Type: string
The type of the ML object.
Result Syntax
[ 'ResourceId' => '<string>', 'ResourceType' => 'BatchPrediction|DataSource|Evaluation|MLModel', 'Tags' => [ [ 'Key' => '<string>', 'Value' => '<string>', ], // ... ], ]
Result Details
Members
- ResourceId
-
- Type: string
The ID of the tagged ML object.
- ResourceType
-
- Type: string
The type of the tagged ML object.
- Tags
-
- Type: Array of Tag structures
A list of tags associated with the ML object.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
GetBatchPrediction
$result = $client->getBatchPrediction
([/* ... */]); $promise = $client->getBatchPredictionAsync
([/* ... */]);
Returns a BatchPrediction
that includes detailed metadata, status, and data file information for a Batch Prediction
request.
Parameter Syntax
$result = $client->getBatchPrediction([ 'BatchPredictionId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- BatchPredictionId
-
- Required: Yes
- Type: string
An ID assigned to the
BatchPrediction
at creation.
Result Syntax
[ 'BatchPredictionDataSourceId' => '<string>', 'BatchPredictionId' => '<string>', 'ComputeTime' => <integer>, 'CreatedAt' => <DateTime>, 'CreatedByIamUser' => '<string>', 'FinishedAt' => <DateTime>, 'InputDataLocationS3' => '<string>', 'InvalidRecordCount' => <integer>, 'LastUpdatedAt' => <DateTime>, 'LogUri' => '<string>', 'MLModelId' => '<string>', 'Message' => '<string>', 'Name' => '<string>', 'OutputUri' => '<string>', 'StartedAt' => <DateTime>, 'Status' => 'PENDING|INPROGRESS|FAILED|COMPLETED|DELETED', 'TotalRecordCount' => <integer>, ]
Result Details
Members
- BatchPredictionDataSourceId
-
- Type: string
The ID of the
DataSource
that was used to create theBatchPrediction
. - BatchPredictionId
-
- Type: string
An ID assigned to the
BatchPrediction
at creation. This value should be identical to the value of theBatchPredictionID
in the request. - ComputeTime
-
- Type: long (int|float)
The approximate CPU time in milliseconds that Amazon Machine Learning spent processing the
BatchPrediction
, normalized and scaled on computation resources.ComputeTime
is only available if theBatchPrediction
is in theCOMPLETED
state. - CreatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time when the
BatchPrediction
was created. The time is expressed in epoch time. - CreatedByIamUser
-
- Type: string
The AWS user account that invoked the
BatchPrediction
. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account. - FinishedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The epoch time when Amazon Machine Learning marked the
BatchPrediction
asCOMPLETED
orFAILED
.FinishedAt
is only available when theBatchPrediction
is in theCOMPLETED
orFAILED
state. - InputDataLocationS3
-
- Type: string
The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).
- InvalidRecordCount
-
- Type: long (int|float)
The number of invalid records that Amazon Machine Learning saw while processing the
BatchPrediction
. - LastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to
BatchPrediction
. The time is expressed in epoch time. - LogUri
-
- Type: string
A link to the file that contains logs of the
CreateBatchPrediction
operation. - MLModelId
-
- Type: string
The ID of the
MLModel
that generated predictions for theBatchPrediction
request. - Message
-
- Type: string
A description of the most recent details about processing the batch prediction request.
- Name
-
- Type: string
A user-supplied name or description of the
BatchPrediction
. - OutputUri
-
- Type: string
The location of an Amazon S3 bucket or directory to receive the operation results.
- StartedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The epoch time when Amazon Machine Learning marked the
BatchPrediction
asINPROGRESS
.StartedAt
isn't available if theBatchPrediction
is in thePENDING
state. - Status
-
- Type: string
The status of the
BatchPrediction
, which can be one of the following values:-
PENDING
- Amazon Machine Learning (Amazon ML) submitted a request to generate batch predictions. -
INPROGRESS
- The batch predictions are in progress. -
FAILED
- The request to perform a batch prediction did not run to completion. It is not usable. -
COMPLETED
- The batch prediction process completed successfully. -
DELETED
- TheBatchPrediction
is marked as deleted. It is not usable.
- TotalRecordCount
-
- Type: long (int|float)
The number of total records that Amazon Machine Learning saw while processing the
BatchPrediction
.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
GetDataSource
$result = $client->getDataSource
([/* ... */]); $promise = $client->getDataSourceAsync
([/* ... */]);
Returns a DataSource
that includes metadata and data file information, as well as the current status of the DataSource
.
GetDataSource
provides results in normal or verbose format. The verbose format adds the schema description and the list of files pointed to by the DataSource to the normal format.
Parameter Syntax
$result = $client->getDataSource([ 'DataSourceId' => '<string>', // REQUIRED 'Verbose' => true || false, ]);
Parameter Details
Members
- DataSourceId
-
- Required: Yes
- Type: string
The ID assigned to the
DataSource
at creation. - Verbose
-
- Type: boolean
Specifies whether the
GetDataSource
operation should returnDataSourceSchema
.If true,
DataSourceSchema
is returned.If false,
DataSourceSchema
is not returned.
Result Syntax
[ 'ComputeStatistics' => true || false, 'ComputeTime' => <integer>, 'CreatedAt' => <DateTime>, 'CreatedByIamUser' => '<string>', 'DataLocationS3' => '<string>', 'DataRearrangement' => '<string>', 'DataSizeInBytes' => <integer>, 'DataSourceId' => '<string>', 'DataSourceSchema' => '<string>', 'FinishedAt' => <DateTime>, 'LastUpdatedAt' => <DateTime>, 'LogUri' => '<string>', 'Message' => '<string>', 'Name' => '<string>', 'NumberOfFiles' => <integer>, 'RDSMetadata' => [ 'DataPipelineId' => '<string>', 'Database' => [ 'DatabaseName' => '<string>', 'InstanceIdentifier' => '<string>', ], 'DatabaseUserName' => '<string>', 'ResourceRole' => '<string>', 'SelectSqlQuery' => '<string>', 'ServiceRole' => '<string>', ], 'RedshiftMetadata' => [ 'DatabaseUserName' => '<string>', 'RedshiftDatabase' => [ 'ClusterIdentifier' => '<string>', 'DatabaseName' => '<string>', ], 'SelectSqlQuery' => '<string>', ], 'RoleARN' => '<string>', 'StartedAt' => <DateTime>, 'Status' => 'PENDING|INPROGRESS|FAILED|COMPLETED|DELETED', ]
Result Details
Members
- ComputeStatistics
-
- Type: boolean
The parameter is
true
if statistics need to be generated from the observation data. - ComputeTime
-
- Type: long (int|float)
The approximate CPU time in milliseconds that Amazon Machine Learning spent processing the
DataSource
, normalized and scaled on computation resources.ComputeTime
is only available if theDataSource
is in theCOMPLETED
state and theComputeStatistics
is set to true. - CreatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time that the
DataSource
was created. The time is expressed in epoch time. - CreatedByIamUser
-
- Type: string
The AWS user account from which the
DataSource
was created. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account. - DataLocationS3
-
- Type: string
The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).
- DataRearrangement
-
- Type: string
A JSON string that represents the splitting and rearrangement requirement used when this
DataSource
was created. - DataSizeInBytes
-
- Type: long (int|float)
The total size of observations in the data files.
- DataSourceId
-
- Type: string
The ID assigned to the
DataSource
at creation. This value should be identical to the value of theDataSourceId
in the request. - DataSourceSchema
-
- Type: string
The schema used by all of the data files of this
DataSource
.Note: This parameter is provided as part of the verbose format.
- FinishedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The epoch time when Amazon Machine Learning marked the
DataSource
asCOMPLETED
orFAILED
.FinishedAt
is only available when theDataSource
is in theCOMPLETED
orFAILED
state. - LastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to the
DataSource
. The time is expressed in epoch time. - LogUri
-
- Type: string
A link to the file containing logs of
CreateDataSourceFrom*
operations. - Message
-
- Type: string
The user-supplied description of the most recent details about creating the
DataSource
. - Name
-
- Type: string
A user-supplied name or description of the
DataSource
. - NumberOfFiles
-
- Type: long (int|float)
The number of data files referenced by the
DataSource
. - RDSMetadata
-
- Type: RDSMetadata structure
The datasource details that are specific to Amazon RDS.
- RedshiftMetadata
-
- Type: RedshiftMetadata structure
Describes the
DataSource
details specific to Amazon Redshift. - RoleARN
-
- Type: string
The Amazon Resource Name (ARN) of an AWS IAM Role, such as the following: arn:aws:iam::account:role/rolename.
- StartedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The epoch time when Amazon Machine Learning marked the
DataSource
asINPROGRESS
.StartedAt
isn't available if theDataSource
is in thePENDING
state. - Status
-
- Type: string
The current status of the
DataSource
. This element can have one of the following values:-
PENDING
- Amazon ML submitted a request to create aDataSource
. -
INPROGRESS
- The creation process is underway. -
FAILED
- The request to create aDataSource
did not run to completion. It is not usable. -
COMPLETED
- The creation process completed successfully. -
DELETED
- TheDataSource
is marked as deleted. It is not usable.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
GetEvaluation
$result = $client->getEvaluation
([/* ... */]); $promise = $client->getEvaluationAsync
([/* ... */]);
Returns an Evaluation
that includes metadata as well as the current status of the Evaluation
.
Parameter Syntax
$result = $client->getEvaluation([ 'EvaluationId' => '<string>', // REQUIRED ]);
Parameter Details
Members
- EvaluationId
-
- Required: Yes
- Type: string
The ID of the
Evaluation
to retrieve. The evaluation of eachMLModel
is recorded and cataloged. The ID provides the means to access the information.
Result Syntax
[ 'ComputeTime' => <integer>, 'CreatedAt' => <DateTime>, 'CreatedByIamUser' => '<string>', 'EvaluationDataSourceId' => '<string>', 'EvaluationId' => '<string>', 'FinishedAt' => <DateTime>, 'InputDataLocationS3' => '<string>', 'LastUpdatedAt' => <DateTime>, 'LogUri' => '<string>', 'MLModelId' => '<string>', 'Message' => '<string>', 'Name' => '<string>', 'PerformanceMetrics' => [ 'Properties' => ['<string>', ...], ], 'StartedAt' => <DateTime>, 'Status' => 'PENDING|INPROGRESS|FAILED|COMPLETED|DELETED', ]
Result Details
Members
- ComputeTime
-
- Type: long (int|float)
The approximate CPU time in milliseconds that Amazon Machine Learning spent processing the
Evaluation
, normalized and scaled on computation resources.ComputeTime
is only available if theEvaluation
is in theCOMPLETED
state. - CreatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time that the
Evaluation
was created. The time is expressed in epoch time. - CreatedByIamUser
-
- Type: string
The AWS user account that invoked the evaluation. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account.
- EvaluationDataSourceId
-
- Type: string
The
DataSource
used for this evaluation. - EvaluationId
-
- Type: string
The evaluation ID which is same as the
EvaluationId
in the request. - FinishedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The epoch time when Amazon Machine Learning marked the
Evaluation
asCOMPLETED
orFAILED
.FinishedAt
is only available when theEvaluation
is in theCOMPLETED
orFAILED
state. - InputDataLocationS3
-
- Type: string
The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).
- LastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to the
Evaluation
. The time is expressed in epoch time. - LogUri
-
- Type: string
A link to the file that contains logs of the
CreateEvaluation
operation. - MLModelId
-
- Type: string
The ID of the
MLModel
that was the focus of the evaluation. - Message
-
- Type: string
A description of the most recent details about evaluating the
MLModel
. - Name
-
- Type: string
A user-supplied name or description of the
Evaluation
. - PerformanceMetrics
-
- Type: PerformanceMetrics structure
Measurements of how well the
MLModel
performed using observations referenced by theDataSource
. One of the following metric is returned based on the type of theMLModel
:-
BinaryAUC: A binary
MLModel
uses the Area Under the Curve (AUC) technique to measure performance. -
RegressionRMSE: A regression
MLModel
uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable. -
MulticlassAvgFScore: A multiclass
MLModel
uses the F1 score technique to measure performance.
For more information about performance metrics, please see the Amazon Machine Learning Developer Guide.
- StartedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The epoch time when Amazon Machine Learning marked the
Evaluation
asINPROGRESS
.StartedAt
isn't available if theEvaluation
is in thePENDING
state. - Status
-
- Type: string
The status of the evaluation. This element can have one of the following values:
-
PENDING
- Amazon Machine Language (Amazon ML) submitted a request to evaluate anMLModel
. -
INPROGRESS
- The evaluation is underway. -
FAILED
- The request to evaluate anMLModel
did not run to completion. It is not usable. -
COMPLETED
- The evaluation process completed successfully. -
DELETED
- TheEvaluation
is marked as deleted. It is not usable.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
GetMLModel
$result = $client->getMLModel
([/* ... */]); $promise = $client->getMLModelAsync
([/* ... */]);
Returns an MLModel
that includes detailed metadata, data source information, and the current status of the MLModel
.
GetMLModel
provides results in normal or verbose format.
Parameter Syntax
$result = $client->getMLModel([ 'MLModelId' => '<string>', // REQUIRED 'Verbose' => true || false, ]);
Parameter Details
Members
- MLModelId
-
- Required: Yes
- Type: string
The ID assigned to the
MLModel
at creation. - Verbose
-
- Type: boolean
Specifies whether the
GetMLModel
operation should returnRecipe
.If true,
Recipe
is returned.If false,
Recipe
is not returned.
Result Syntax
[ 'ComputeTime' => <integer>, 'CreatedAt' => <DateTime>, 'CreatedByIamUser' => '<string>', 'EndpointInfo' => [ 'CreatedAt' => <DateTime>, 'EndpointStatus' => 'NONE|READY|UPDATING|FAILED', 'EndpointUrl' => '<string>', 'PeakRequestsPerSecond' => <integer>, ], 'FinishedAt' => <DateTime>, 'InputDataLocationS3' => '<string>', 'LastUpdatedAt' => <DateTime>, 'LogUri' => '<string>', 'MLModelId' => '<string>', 'MLModelType' => 'REGRESSION|BINARY|MULTICLASS', 'Message' => '<string>', 'Name' => '<string>', 'Recipe' => '<string>', 'Schema' => '<string>', 'ScoreThreshold' => <float>, 'ScoreThresholdLastUpdatedAt' => <DateTime>, 'SizeInBytes' => <integer>, 'StartedAt' => <DateTime>, 'Status' => 'PENDING|INPROGRESS|FAILED|COMPLETED|DELETED', 'TrainingDataSourceId' => '<string>', 'TrainingParameters' => ['<string>', ...], ]
Result Details
Members
- ComputeTime
-
- Type: long (int|float)
The approximate CPU time in milliseconds that Amazon Machine Learning spent processing the
MLModel
, normalized and scaled on computation resources.ComputeTime
is only available if theMLModel
is in theCOMPLETED
state. - CreatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time that the
MLModel
was created. The time is expressed in epoch time. - CreatedByIamUser
-
- Type: string
The AWS user account from which the
MLModel
was created. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account. - EndpointInfo
-
- Type: RealtimeEndpointInfo structure
The current endpoint of the
MLModel
- FinishedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The epoch time when Amazon Machine Learning marked the
MLModel
asCOMPLETED
orFAILED
.FinishedAt
is only available when theMLModel
is in theCOMPLETED
orFAILED
state. - InputDataLocationS3
-
- Type: string
The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).
- LastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to the
MLModel
. The time is expressed in epoch time. - LogUri
-
- Type: string
A link to the file that contains logs of the
CreateMLModel
operation. - MLModelId
-
- Type: string
The MLModel ID, which is same as the
MLModelId
in the request. - MLModelType
-
- Type: string
Identifies the
MLModel
category. The following are the available types:-
REGRESSION -- Produces a numeric result. For example, "What price should a house be listed at?"
-
BINARY -- Produces one of two possible results. For example, "Is this an e-commerce website?"
-
MULTICLASS -- Produces one of several possible results. For example, "Is this a HIGH, LOW or MEDIUM risk trade?"
- Message
-
- Type: string
A description of the most recent details about accessing the
MLModel
. - Name
-
- Type: string
A user-supplied name or description of the
MLModel
. - Recipe
-
- Type: string
The recipe to use when training the
MLModel
. TheRecipe
provides detailed information about the observation data to use during training, and manipulations to perform on the observation data during training.Note: This parameter is provided as part of the verbose format.
- Schema
-
- Type: string
The schema used by all of the data files referenced by the
DataSource
.Note: This parameter is provided as part of the verbose format.
- ScoreThreshold
-
- Type: float
The scoring threshold is used in binary classification
MLModel
models. It marks the boundary between a positive prediction and a negative prediction.Output values greater than or equal to the threshold receive a positive result from the MLModel, such as
true
. Output values less than the threshold receive a negative response from the MLModel, such asfalse
. - ScoreThresholdLastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to the
ScoreThreshold
. The time is expressed in epoch time. - SizeInBytes
-
- Type: long (int|float)
Long integer type that is a 64-bit signed number.
- StartedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The epoch time when Amazon Machine Learning marked the
MLModel
asINPROGRESS
.StartedAt
isn't available if theMLModel
is in thePENDING
state. - Status
-
- Type: string
The current status of the
MLModel
. This element can have one of the following values:-
PENDING
- Amazon Machine Learning (Amazon ML) submitted a request to describe aMLModel
. -
INPROGRESS
- The request is processing. -
FAILED
- The request did not run to completion. The ML model isn't usable. -
COMPLETED
- The request completed successfully. -
DELETED
- TheMLModel
is marked as deleted. It isn't usable.
- TrainingDataSourceId
-
- Type: string
The ID of the training
DataSource
. - TrainingParameters
-
- Type: Associative array of custom strings keys (StringType) to strings
A list of the training parameters in the
MLModel
. The list is implemented as a map of key-value pairs.The following is the current set of training parameters:
-
sgd.maxMLModelSizeInBytes
- The maximum allowed size of the model. Depending on the input data, the size of the model might affect its performance.The value is an integer that ranges from
100000
to2147483648
. The default value is33554432
. -
sgd.maxPasses
- The number of times that the training process traverses the observations to build theMLModel
. The value is an integer that ranges from1
to10000
. The default value is10
. -
sgd.shuffleType
- Whether Amazon ML shuffles the training data. Shuffling data improves a model's ability to find the optimal solution for a variety of data types. The valid values areauto
andnone
. The default value isnone
. We strongly recommend that you shuffle your data. -
sgd.l1RegularizationAmount
- The coefficient regularization L1 norm. It controls overfitting the data by penalizing large coefficients. This tends to drive coefficients to zero, resulting in a sparse feature set. If you use this parameter, start by specifying a small value, such as1.0E-08
.The value is a double that ranges from
0
toMAX_DOUBLE
. The default is to not use L1 normalization. This parameter can't be used whenL2
is specified. Use this parameter sparingly. -
sgd.l2RegularizationAmount
- The coefficient regularization L2 norm. It controls overfitting the data by penalizing large coefficients. This tends to drive coefficients to small, nonzero values. If you use this parameter, start by specifying a small value, such as1.0E-08
.The value is a double that ranges from
0
toMAX_DOUBLE
. The default is to not use L2 normalization. This parameter can't be used whenL1
is specified. Use this parameter sparingly.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
Predict
$result = $client->predict
([/* ... */]); $promise = $client->predictAsync
([/* ... */]);
Generates a prediction for the observation using the specified ML Model
.
Note: Not all response parameters will be populated. Whether a response parameter is populated depends on the type of model requested.
Parameter Syntax
$result = $client->predict([ 'MLModelId' => '<string>', // REQUIRED 'PredictEndpoint' => '<string>', // REQUIRED 'Record' => ['<string>', ...], // REQUIRED ]);
Parameter Details
Members
- MLModelId
-
- Required: Yes
- Type: string
A unique identifier of the
MLModel
. - PredictEndpoint
-
- Required: Yes
- Type: string
- Record
-
- Required: Yes
- Type: Associative array of custom strings keys (VariableName) to strings
A map of variable name-value pairs that represent an observation.
Result Syntax
[ 'Prediction' => [ 'details' => ['<string>', ...], 'predictedLabel' => '<string>', 'predictedScores' => [<float>, ...], 'predictedValue' => <float>, ], ]
Result Details
Members
- Prediction
-
- Type: Prediction structure
The output from a
Predict
operation:-
Details
- Contains the following attributes:DetailsAttributes.PREDICTIVE_MODEL_TYPE - REGRESSION | BINARY | MULTICLASS
DetailsAttributes.ALGORITHM - SGD
-
PredictedLabel
- Present for either aBINARY
orMULTICLASS
MLModel
request. -
PredictedScores
- Contains the raw classification score corresponding to each label. -
PredictedValue
- Present for aREGRESSION
MLModel
request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- LimitExceededException:
The subscriber exceeded the maximum number of operations. This exception can occur when listing objects such as
DataSource
.- InternalServerException:
An error on the server occurred when trying to process a request.
- PredictorNotMountedException:
The exception is thrown when a predict request is made to an unmounted
MLModel
.
UpdateBatchPrediction
$result = $client->updateBatchPrediction
([/* ... */]); $promise = $client->updateBatchPredictionAsync
([/* ... */]);
Updates the BatchPredictionName
of a BatchPrediction
.
You can use the GetBatchPrediction
operation to view the contents of the updated data element.
Parameter Syntax
$result = $client->updateBatchPrediction([ 'BatchPredictionId' => '<string>', // REQUIRED 'BatchPredictionName' => '<string>', // REQUIRED ]);
Parameter Details
Members
- BatchPredictionId
-
- Required: Yes
- Type: string
The ID assigned to the
BatchPrediction
during creation. - BatchPredictionName
-
- Required: Yes
- Type: string
A new user-supplied name or description of the
BatchPrediction
.
Result Syntax
[ 'BatchPredictionId' => '<string>', ]
Result Details
Members
- BatchPredictionId
-
- Type: string
The ID assigned to the
BatchPrediction
during creation. This value should be identical to the value of theBatchPredictionId
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
UpdateDataSource
$result = $client->updateDataSource
([/* ... */]); $promise = $client->updateDataSourceAsync
([/* ... */]);
Updates the DataSourceName
of a DataSource
.
You can use the GetDataSource
operation to view the contents of the updated data element.
Parameter Syntax
$result = $client->updateDataSource([ 'DataSourceId' => '<string>', // REQUIRED 'DataSourceName' => '<string>', // REQUIRED ]);
Parameter Details
Members
- DataSourceId
-
- Required: Yes
- Type: string
The ID assigned to the
DataSource
during creation. - DataSourceName
-
- Required: Yes
- Type: string
A new user-supplied name or description of the
DataSource
that will replace the current description.
Result Syntax
[ 'DataSourceId' => '<string>', ]
Result Details
Members
- DataSourceId
-
- Type: string
The ID assigned to the
DataSource
during creation. This value should be identical to the value of theDataSourceID
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
UpdateEvaluation
$result = $client->updateEvaluation
([/* ... */]); $promise = $client->updateEvaluationAsync
([/* ... */]);
Updates the EvaluationName
of an Evaluation
.
You can use the GetEvaluation
operation to view the contents of the updated data element.
Parameter Syntax
$result = $client->updateEvaluation([ 'EvaluationId' => '<string>', // REQUIRED 'EvaluationName' => '<string>', // REQUIRED ]);
Parameter Details
Members
- EvaluationId
-
- Required: Yes
- Type: string
The ID assigned to the
Evaluation
during creation. - EvaluationName
-
- Required: Yes
- Type: string
A new user-supplied name or description of the
Evaluation
that will replace the current content.
Result Syntax
[ 'EvaluationId' => '<string>', ]
Result Details
Members
- EvaluationId
-
- Type: string
The ID assigned to the
Evaluation
during creation. This value should be identical to the value of theEvaluation
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
UpdateMLModel
$result = $client->updateMLModel
([/* ... */]); $promise = $client->updateMLModelAsync
([/* ... */]);
Updates the MLModelName
and the ScoreThreshold
of an MLModel
.
You can use the GetMLModel
operation to view the contents of the updated data element.
Parameter Syntax
$result = $client->updateMLModel([ 'MLModelId' => '<string>', // REQUIRED 'MLModelName' => '<string>', 'ScoreThreshold' => <float>, ]);
Parameter Details
Members
- MLModelId
-
- Required: Yes
- Type: string
The ID assigned to the
MLModel
during creation. - MLModelName
-
- Type: string
A user-supplied name or description of the
MLModel
. - ScoreThreshold
-
- Type: float
The
ScoreThreshold
used in binary classificationMLModel
that marks the boundary between a positive prediction and a negative prediction.Output values greater than or equal to the
ScoreThreshold
receive a positive result from theMLModel
, such astrue
. Output values less than theScoreThreshold
receive a negative response from theMLModel
, such asfalse
.
Result Syntax
[ 'MLModelId' => '<string>', ]
Result Details
Members
- MLModelId
-
- Type: string
The ID assigned to the
MLModel
during creation. This value should be identical to the value of theMLModelID
in the request.
Errors
- InvalidInputException:
An error on the client occurred. Typically, the cause is an invalid input value.
- ResourceNotFoundException:
A specified resource cannot be located.
- InternalServerException:
An error on the server occurred when trying to process a request.
Shapes
BatchPrediction
Description
Represents the output of a GetBatchPrediction
operation.
The content consists of the detailed metadata, the status, and the data file information of a Batch Prediction
.
Members
- BatchPredictionDataSourceId
-
- Type: string
The ID of the
DataSource
that points to the group of observations to predict. - BatchPredictionId
-
- Type: string
The ID assigned to the
BatchPrediction
at creation. This value should be identical to the value of theBatchPredictionID
in the request. - ComputeTime
-
- Type: long (int|float)
Long integer type that is a 64-bit signed number.
- CreatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time that the
BatchPrediction
was created. The time is expressed in epoch time. - CreatedByIamUser
-
- Type: string
The AWS user account that invoked the
BatchPrediction
. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account. - FinishedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
A timestamp represented in epoch time.
- InputDataLocationS3
-
- Type: string
The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).
- InvalidRecordCount
-
- Type: long (int|float)
Long integer type that is a 64-bit signed number.
- LastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to the
BatchPrediction
. The time is expressed in epoch time. - MLModelId
-
- Type: string
The ID of the
MLModel
that generated predictions for theBatchPrediction
request. - Message
-
- Type: string
A description of the most recent details about processing the batch prediction request.
- Name
-
- Type: string
A user-supplied name or description of the
BatchPrediction
. - OutputUri
-
- Type: string
The location of an Amazon S3 bucket or directory to receive the operation results. The following substrings are not allowed in the
s3 key
portion of theoutputURI
field: ':', '//', '/./', '/../'. - StartedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
A timestamp represented in epoch time.
- Status
-
- Type: string
The status of the
BatchPrediction
. This element can have one of the following values:-
PENDING
- Amazon Machine Learning (Amazon ML) submitted a request to generate predictions for a batch of observations. -
INPROGRESS
- The process is underway. -
FAILED
- The request to perform a batch prediction did not run to completion. It is not usable. -
COMPLETED
- The batch prediction process completed successfully. -
DELETED
- TheBatchPrediction
is marked as deleted. It is not usable.
- TotalRecordCount
-
- Type: long (int|float)
Long integer type that is a 64-bit signed number.
DataSource
Description
Represents the output of the GetDataSource
operation.
The content consists of the detailed metadata and data file information and the current status of the DataSource
.
Members
- ComputeStatistics
-
- Type: boolean
The parameter is
true
if statistics need to be generated from the observation data. - ComputeTime
-
- Type: long (int|float)
Long integer type that is a 64-bit signed number.
- CreatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time that the
DataSource
was created. The time is expressed in epoch time. - CreatedByIamUser
-
- Type: string
The AWS user account from which the
DataSource
was created. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account. - DataLocationS3
-
- Type: string
The location and name of the data in Amazon Simple Storage Service (Amazon S3) that is used by a
DataSource
. - DataRearrangement
-
- Type: string
A JSON string that represents the splitting and rearrangement requirement used when this
DataSource
was created. - DataSizeInBytes
-
- Type: long (int|float)
The total number of observations contained in the data files that the
DataSource
references. - DataSourceId
-
- Type: string
The ID that is assigned to the
DataSource
during creation. - FinishedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
A timestamp represented in epoch time.
- LastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to the
BatchPrediction
. The time is expressed in epoch time. - Message
-
- Type: string
A description of the most recent details about creating the
DataSource
. - Name
-
- Type: string
A user-supplied name or description of the
DataSource
. - NumberOfFiles
-
- Type: long (int|float)
The number of data files referenced by the
DataSource
. - RDSMetadata
-
- Type: RDSMetadata structure
The datasource details that are specific to Amazon RDS.
- RedshiftMetadata
-
- Type: RedshiftMetadata structure
Describes the
DataSource
details specific to Amazon Redshift. - RoleARN
-
- Type: string
The Amazon Resource Name (ARN) of an AWS IAM Role, such as the following: arn:aws:iam::account:role/rolename.
- StartedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
A timestamp represented in epoch time.
- Status
-
- Type: string
The current status of the
DataSource
. This element can have one of the following values:-
PENDING - Amazon Machine Learning (Amazon ML) submitted a request to create a
DataSource
. -
INPROGRESS - The creation process is underway.
-
FAILED - The request to create a
DataSource
did not run to completion. It is not usable. -
COMPLETED - The creation process completed successfully.
-
DELETED - The
DataSource
is marked as deleted. It is not usable.
Evaluation
Description
Represents the output of GetEvaluation
operation.
The content consists of the detailed metadata and data file information and the current status of the Evaluation
.
Members
- ComputeTime
-
- Type: long (int|float)
Long integer type that is a 64-bit signed number.
- CreatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time that the
Evaluation
was created. The time is expressed in epoch time. - CreatedByIamUser
-
- Type: string
The AWS user account that invoked the evaluation. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account.
- EvaluationDataSourceId
-
- Type: string
The ID of the
DataSource
that is used to evaluate theMLModel
. - EvaluationId
-
- Type: string
The ID that is assigned to the
Evaluation
at creation. - FinishedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
A timestamp represented in epoch time.
- InputDataLocationS3
-
- Type: string
The location and name of the data in Amazon Simple Storage Server (Amazon S3) that is used in the evaluation.
- LastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to the
Evaluation
. The time is expressed in epoch time. - MLModelId
-
- Type: string
The ID of the
MLModel
that is the focus of the evaluation. - Message
-
- Type: string
A description of the most recent details about evaluating the
MLModel
. - Name
-
- Type: string
A user-supplied name or description of the
Evaluation
. - PerformanceMetrics
-
- Type: PerformanceMetrics structure
Measurements of how well the
MLModel
performed, using observations referenced by theDataSource
. One of the following metrics is returned, based on the type of theMLModel
:-
BinaryAUC: A binary
MLModel
uses the Area Under the Curve (AUC) technique to measure performance. -
RegressionRMSE: A regression
MLModel
uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable. -
MulticlassAvgFScore: A multiclass
MLModel
uses the F1 score technique to measure performance.
For more information about performance metrics, please see the Amazon Machine Learning Developer Guide.
- StartedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
A timestamp represented in epoch time.
- Status
-
- Type: string
The status of the evaluation. This element can have one of the following values:
-
PENDING
- Amazon Machine Learning (Amazon ML) submitted a request to evaluate anMLModel
. -
INPROGRESS
- The evaluation is underway. -
FAILED
- The request to evaluate anMLModel
did not run to completion. It is not usable. -
COMPLETED
- The evaluation process completed successfully. -
DELETED
- TheEvaluation
is marked as deleted. It is not usable.
IdempotentParameterMismatchException
Description
A second request to use or change an object was not allowed. This can result from retrying a request using a parameter that was not present in the original request.
Members
- code
-
- Type: int
- message
-
- Type: string
InternalServerException
Description
An error on the server occurred when trying to process a request.
Members
- code
-
- Type: int
- message
-
- Type: string
InvalidInputException
Description
An error on the client occurred. Typically, the cause is an invalid input value.
Members
- code
-
- Type: int
- message
-
- Type: string
InvalidTagException
Members
- message
-
- Type: string
LimitExceededException
Description
The subscriber exceeded the maximum number of operations. This exception can occur when listing objects such as DataSource
.
Members
- code
-
- Type: int
- message
-
- Type: string
MLModel
Description
Represents the output of a GetMLModel
operation.
The content consists of the detailed metadata and the current status of the MLModel
.
Members
- Algorithm
-
- Type: string
The algorithm used to train the
MLModel
. The following algorithm is supported:-
SGD
-- Stochastic gradient descent. The goal ofSGD
is to minimize the gradient of the loss function.
- ComputeTime
-
- Type: long (int|float)
Long integer type that is a 64-bit signed number.
- CreatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time that the
MLModel
was created. The time is expressed in epoch time. - CreatedByIamUser
-
- Type: string
The AWS user account from which the
MLModel
was created. The account type can be either an AWS root account or an AWS Identity and Access Management (IAM) user account. - EndpointInfo
-
- Type: RealtimeEndpointInfo structure
The current endpoint of the
MLModel
. - FinishedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
A timestamp represented in epoch time.
- InputDataLocationS3
-
- Type: string
The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).
- LastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to the
MLModel
. The time is expressed in epoch time. - MLModelId
-
- Type: string
The ID assigned to the
MLModel
at creation. - MLModelType
-
- Type: string
Identifies the
MLModel
category. The following are the available types:-
REGRESSION
- Produces a numeric result. For example, "What price should a house be listed at?" -
BINARY
- Produces one of two possible results. For example, "Is this a child-friendly web site?". -
MULTICLASS
- Produces one of several possible results. For example, "Is this a HIGH-, LOW-, or MEDIUM-risk trade?".
- Message
-
- Type: string
A description of the most recent details about accessing the
MLModel
. - Name
-
- Type: string
A user-supplied name or description of the
MLModel
. - ScoreThreshold
-
- Type: float
- ScoreThresholdLastUpdatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time of the most recent edit to the
ScoreThreshold
. The time is expressed in epoch time. - SizeInBytes
-
- Type: long (int|float)
Long integer type that is a 64-bit signed number.
- StartedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
A timestamp represented in epoch time.
- Status
-
- Type: string
The current status of an
MLModel
. This element can have one of the following values:-
PENDING
- Amazon Machine Learning (Amazon ML) submitted a request to create anMLModel
. -
INPROGRESS
- The creation process is underway. -
FAILED
- The request to create anMLModel
didn't run to completion. The model isn't usable. -
COMPLETED
- The creation process completed successfully. -
DELETED
- TheMLModel
is marked as deleted. It isn't usable.
- TrainingDataSourceId
-
- Type: string
The ID of the training
DataSource
. TheCreateMLModel
operation uses theTrainingDataSourceId
. - TrainingParameters
-
- Type: Associative array of custom strings keys (StringType) to strings
A list of the training parameters in the
MLModel
. The list is implemented as a map of key-value pairs.The following is the current set of training parameters:
-
sgd.maxMLModelSizeInBytes
- The maximum allowed size of the model. Depending on the input data, the size of the model might affect its performance.The value is an integer that ranges from
100000
to2147483648
. The default value is33554432
. -
sgd.maxPasses
- The number of times that the training process traverses the observations to build theMLModel
. The value is an integer that ranges from1
to10000
. The default value is10
. -
sgd.shuffleType
- Whether Amazon ML shuffles the training data. Shuffling the data improves a model's ability to find the optimal solution for a variety of data types. The valid values areauto
andnone
. The default value isnone
. -
sgd.l1RegularizationAmount
- The coefficient regularization L1 norm, which controls overfitting the data by penalizing large coefficients. This parameter tends to drive coefficients to zero, resulting in sparse feature set. If you use this parameter, start by specifying a small value, such as1.0E-08
.The value is a double that ranges from
0
toMAX_DOUBLE
. The default is to not use L1 normalization. This parameter can't be used whenL2
is specified. Use this parameter sparingly. -
sgd.l2RegularizationAmount
- The coefficient regularization L2 norm, which controls overfitting the data by penalizing large coefficients. This tends to drive coefficients to small, nonzero values. If you use this parameter, start by specifying a small value, such as1.0E-08
.The value is a double that ranges from
0
toMAX_DOUBLE
. The default is to not use L2 normalization. This parameter can't be used whenL1
is specified. Use this parameter sparingly.
PerformanceMetrics
Description
Measurements of how well the MLModel
performed on known observations. One of the following metrics is returned, based on the type of the MLModel
:
-
BinaryAUC: The binary
MLModel
uses the Area Under the Curve (AUC) technique to measure performance. -
RegressionRMSE: The regression
MLModel
uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable. -
MulticlassAvgFScore: The multiclass
MLModel
uses the F1 score technique to measure performance.
For more information about performance metrics, please see the Amazon Machine Learning Developer Guide.
Members
- Properties
-
- Type: Associative array of custom strings keys (PerformanceMetricsPropertyKey) to strings
Prediction
Description
The output from a Predict
operation:
-
Details
- Contains the following attributes:DetailsAttributes.PREDICTIVE_MODEL_TYPE - REGRESSION | BINARY | MULTICLASS
DetailsAttributes.ALGORITHM - SGD
-
PredictedLabel
- Present for either aBINARY
orMULTICLASS
MLModel
request. -
PredictedScores
- Contains the raw classification score corresponding to each label. -
PredictedValue
- Present for aREGRESSION
MLModel
request.
Members
- details
-
- Type: Associative array of custom strings keys (DetailsAttributes) to strings
Provides any additional details regarding the prediction.
- predictedLabel
-
- Type: string
The prediction label for either a
BINARY
orMULTICLASS
MLModel
. - predictedScores
-
- Type: Associative array of custom strings keys (Label) to floats
Provides the raw classification score corresponding to each label.
- predictedValue
-
- Type: float
The prediction value for
REGRESSION
MLModel
.
PredictorNotMountedException
Description
The exception is thrown when a predict request is made to an unmounted MLModel
.
Members
- message
-
- Type: string
RDSDataSpec
Description
The data specification of an Amazon Relational Database Service (Amazon RDS) DataSource
.
Members
- DataRearrangement
-
- Type: string
A JSON string that represents the splitting and rearrangement processing to be applied to a
DataSource
. If theDataRearrangement
parameter is not provided, all of the input data is used to create theDatasource
.There are multiple parameters that control what data is used to create a datasource:
-
percentBegin
Use
percentBegin
to indicate the beginning of the range of the data used to create the Datasource. If you do not includepercentBegin
andpercentEnd
, Amazon ML includes all of the data when creating the datasource. -
percentEnd
Use
percentEnd
to indicate the end of the range of the data used to create the Datasource. If you do not includepercentBegin
andpercentEnd
, Amazon ML includes all of the data when creating the datasource. -
complement
The
complement
parameter instructs Amazon ML to use the data that is not included in the range ofpercentBegin
topercentEnd
to create a datasource. Thecomplement
parameter is useful if you need to create complementary datasources for training and evaluation. To create a complementary datasource, use the same values forpercentBegin
andpercentEnd
, along with thecomplement
parameter.For example, the following two datasources do not share any data, and can be used to train and evaluate a model. The first datasource has 25 percent of the data, and the second one has 75 percent of the data.
Datasource for evaluation:
{"splitting":{"percentBegin":0, "percentEnd":25}}
Datasource for training:
{"splitting":{"percentBegin":0, "percentEnd":25, "complement":"true"}}
-
strategy
To change how Amazon ML splits the data for a datasource, use the
strategy
parameter.The default value for the
strategy
parameter issequential
, meaning that Amazon ML takes all of the data records between thepercentBegin
andpercentEnd
parameters for the datasource, in the order that the records appear in the input data.The following two
DataRearrangement
lines are examples of sequentially ordered training and evaluation datasources:Datasource for evaluation:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential"}}
Datasource for training:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential", "complement":"true"}}
To randomly split the input data into the proportions indicated by the percentBegin and percentEnd parameters, set the
strategy
parameter torandom
and provide a string that is used as the seed value for the random data splitting (for example, you can use the S3 path to your data as the random seed string). If you choose the random split strategy, Amazon ML assigns each row of data a pseudo-random number between 0 and 100, and then selects the rows that have an assigned number betweenpercentBegin
andpercentEnd
. Pseudo-random numbers are assigned using both the input seed string value and the byte offset as a seed, so changing the data results in a different split. Any existing ordering is preserved. The random splitting strategy ensures that variables in the training and evaluation data are distributed similarly. It is useful in the cases where the input data may have an implicit sort order, which would otherwise result in training and evaluation datasources containing non-similar data records.The following two
DataRearrangement
lines are examples of non-sequentially ordered training and evaluation datasources:Datasource for evaluation:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv"}}
Datasource for training:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv", "complement":"true"}}
- DataSchema
-
- Type: string
A JSON string that represents the schema for an Amazon RDS
DataSource
. TheDataSchema
defines the structure of the observation data in the data file(s) referenced in theDataSource
.A
DataSchema
is not required if you specify aDataSchemaUri
Define your
DataSchema
as a series of key-value pairs.attributes
andexcludedVariableNames
have an array of key-value pairs for their value. Use the following format to define yourDataSchema
.{ "version": "1.0",
"recordAnnotationFieldName": "F1",
"recordWeightFieldName": "F2",
"targetFieldName": "F3",
"dataFormat": "CSV",
"dataFileContainsHeader": true,
"attributes": [
{ "fieldName": "F1", "fieldType": "TEXT" }, { "fieldName": "F2", "fieldType": "NUMERIC" }, { "fieldName": "F3", "fieldType": "CATEGORICAL" }, { "fieldName": "F4", "fieldType": "NUMERIC" }, { "fieldName": "F5", "fieldType": "CATEGORICAL" }, { "fieldName": "F6", "fieldType": "TEXT" }, { "fieldName": "F7", "fieldType": "WEIGHTED_INT_SEQUENCE" }, { "fieldName": "F8", "fieldType": "WEIGHTED_STRING_SEQUENCE" } ],
"excludedVariableNames": [ "F6" ] }
- DataSchemaUri
-
- Type: string
The Amazon S3 location of the
DataSchema
. - DatabaseCredentials
-
- Required: Yes
- Type: RDSDatabaseCredentials structure
The AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon RDS database.
- DatabaseInformation
-
- Required: Yes
- Type: RDSDatabase structure
Describes the
DatabaseName
andInstanceIdentifier
of an Amazon RDS database. - ResourceRole
-
- Required: Yes
- Type: string
The role (DataPipelineDefaultResourceRole) assumed by an Amazon Elastic Compute Cloud (Amazon EC2) instance to carry out the copy operation from Amazon RDS to an Amazon S3 task. For more information, see Role templates for data pipelines.
- S3StagingLocation
-
- Required: Yes
- Type: string
The Amazon S3 location for staging Amazon RDS data. The data retrieved from Amazon RDS using
SelectSqlQuery
is stored in this location. - SecurityGroupIds
-
- Required: Yes
- Type: Array of strings
The security group IDs to be used to access a VPC-based RDS DB instance. Ensure that there are appropriate ingress rules set up to allow access to the RDS DB instance. This attribute is used by Data Pipeline to carry out the copy operation from Amazon RDS to an Amazon S3 task.
- SelectSqlQuery
-
- Required: Yes
- Type: string
The query that is used to retrieve the observation data for the
DataSource
. - ServiceRole
-
- Required: Yes
- Type: string
The role (DataPipelineDefaultRole) assumed by AWS Data Pipeline service to monitor the progress of the copy task from Amazon RDS to Amazon S3. For more information, see Role templates for data pipelines.
- SubnetId
-
- Required: Yes
- Type: string
The subnet ID to be used to access a VPC-based RDS DB instance. This attribute is used by Data Pipeline to carry out the copy task from Amazon RDS to Amazon S3.
RDSDatabase
Description
The database details of an Amazon RDS database.
Members
- DatabaseName
-
- Required: Yes
- Type: string
The name of a database hosted on an RDS DB instance.
- InstanceIdentifier
-
- Required: Yes
- Type: string
The ID of an RDS DB instance.
RDSDatabaseCredentials
Description
The database credentials to connect to a database on an RDS DB instance.
Members
- Password
-
- Required: Yes
- Type: string
The password to be used by Amazon ML to connect to a database on an RDS DB instance. The password should have sufficient permissions to execute the
RDSSelectQuery
query. - Username
-
- Required: Yes
- Type: string
The username to be used by Amazon ML to connect to database on an Amazon RDS instance. The username should have sufficient permissions to execute an
RDSSelectSqlQuery
query.
RDSMetadata
Description
The datasource details that are specific to Amazon RDS.
Members
- DataPipelineId
-
- Type: string
The ID of the Data Pipeline instance that is used to carry to copy data from Amazon RDS to Amazon S3. You can use the ID to find details about the instance in the Data Pipeline console.
- Database
-
- Type: RDSDatabase structure
The database details required to connect to an Amazon RDS.
- DatabaseUserName
-
- Type: string
The username to be used by Amazon ML to connect to database on an Amazon RDS instance. The username should have sufficient permissions to execute an
RDSSelectSqlQuery
query. - ResourceRole
-
- Type: string
The role (DataPipelineDefaultResourceRole) assumed by an Amazon EC2 instance to carry out the copy task from Amazon RDS to Amazon S3. For more information, see Role templates for data pipelines.
- SelectSqlQuery
-
- Type: string
The SQL query that is supplied during CreateDataSourceFromRDS. Returns only if
Verbose
is true inGetDataSourceInput
. - ServiceRole
-
- Type: string
The role (DataPipelineDefaultRole) assumed by the Data Pipeline service to monitor the progress of the copy task from Amazon RDS to Amazon S3. For more information, see Role templates for data pipelines.
RealtimeEndpointInfo
Description
Describes the real-time endpoint information for an MLModel
.
Members
- CreatedAt
-
- Type: timestamp (string|DateTime or anything parsable by strtotime)
The time that the request to create the real-time endpoint for the
MLModel
was received. The time is expressed in epoch time. - EndpointStatus
-
- Type: string
The current status of the real-time endpoint for the
MLModel
. This element can have one of the following values:-
NONE
- Endpoint does not exist or was previously deleted. -
READY
- Endpoint is ready to be used for real-time predictions. -
UPDATING
- Updating/creating the endpoint.
- EndpointUrl
-
- Type: string
The URI that specifies where to send real-time prediction requests for the
MLModel
.Note: The application must wait until the real-time endpoint is ready before using this URI.
- PeakRequestsPerSecond
-
- Type: int
The maximum processing rate for the real-time endpoint for
MLModel
, measured in incoming requests per second.
RedshiftDataSpec
Description
Describes the data specification of an Amazon Redshift DataSource
.
Members
- DataRearrangement
-
- Type: string
A JSON string that represents the splitting and rearrangement processing to be applied to a
DataSource
. If theDataRearrangement
parameter is not provided, all of the input data is used to create theDatasource
.There are multiple parameters that control what data is used to create a datasource:
-
percentBegin
Use
percentBegin
to indicate the beginning of the range of the data used to create the Datasource. If you do not includepercentBegin
andpercentEnd
, Amazon ML includes all of the data when creating the datasource. -
percentEnd
Use
percentEnd
to indicate the end of the range of the data used to create the Datasource. If you do not includepercentBegin
andpercentEnd
, Amazon ML includes all of the data when creating the datasource. -
complement
The
complement
parameter instructs Amazon ML to use the data that is not included in the range ofpercentBegin
topercentEnd
to create a datasource. Thecomplement
parameter is useful if you need to create complementary datasources for training and evaluation. To create a complementary datasource, use the same values forpercentBegin
andpercentEnd
, along with thecomplement
parameter.For example, the following two datasources do not share any data, and can be used to train and evaluate a model. The first datasource has 25 percent of the data, and the second one has 75 percent of the data.
Datasource for evaluation:
{"splitting":{"percentBegin":0, "percentEnd":25}}
Datasource for training:
{"splitting":{"percentBegin":0, "percentEnd":25, "complement":"true"}}
-
strategy
To change how Amazon ML splits the data for a datasource, use the
strategy
parameter.The default value for the
strategy
parameter issequential
, meaning that Amazon ML takes all of the data records between thepercentBegin
andpercentEnd
parameters for the datasource, in the order that the records appear in the input data.The following two
DataRearrangement
lines are examples of sequentially ordered training and evaluation datasources:Datasource for evaluation:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential"}}
Datasource for training:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential", "complement":"true"}}
To randomly split the input data into the proportions indicated by the percentBegin and percentEnd parameters, set the
strategy
parameter torandom
and provide a string that is used as the seed value for the random data splitting (for example, you can use the S3 path to your data as the random seed string). If you choose the random split strategy, Amazon ML assigns each row of data a pseudo-random number between 0 and 100, and then selects the rows that have an assigned number betweenpercentBegin
andpercentEnd
. Pseudo-random numbers are assigned using both the input seed string value and the byte offset as a seed, so changing the data results in a different split. Any existing ordering is preserved. The random splitting strategy ensures that variables in the training and evaluation data are distributed similarly. It is useful in the cases where the input data may have an implicit sort order, which would otherwise result in training and evaluation datasources containing non-similar data records.The following two
DataRearrangement
lines are examples of non-sequentially ordered training and evaluation datasources:Datasource for evaluation:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv"}}
Datasource for training:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv", "complement":"true"}}
- DataSchema
-
- Type: string
A JSON string that represents the schema for an Amazon Redshift
DataSource
. TheDataSchema
defines the structure of the observation data in the data file(s) referenced in theDataSource
.A
DataSchema
is not required if you specify aDataSchemaUri
.Define your
DataSchema
as a series of key-value pairs.attributes
andexcludedVariableNames
have an array of key-value pairs for their value. Use the following format to define yourDataSchema
.{ "version": "1.0",
"recordAnnotationFieldName": "F1",
"recordWeightFieldName": "F2",
"targetFieldName": "F3",
"dataFormat": "CSV",
"dataFileContainsHeader": true,
"attributes": [
{ "fieldName": "F1", "fieldType": "TEXT" }, { "fieldName": "F2", "fieldType": "NUMERIC" }, { "fieldName": "F3", "fieldType": "CATEGORICAL" }, { "fieldName": "F4", "fieldType": "NUMERIC" }, { "fieldName": "F5", "fieldType": "CATEGORICAL" }, { "fieldName": "F6", "fieldType": "TEXT" }, { "fieldName": "F7", "fieldType": "WEIGHTED_INT_SEQUENCE" }, { "fieldName": "F8", "fieldType": "WEIGHTED_STRING_SEQUENCE" } ],
"excludedVariableNames": [ "F6" ] }
- DataSchemaUri
-
- Type: string
Describes the schema location for an Amazon Redshift
DataSource
. - DatabaseCredentials
-
- Required: Yes
- Type: RedshiftDatabaseCredentials structure
Describes AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon Redshift database.
- DatabaseInformation
-
- Required: Yes
- Type: RedshiftDatabase structure
Describes the
DatabaseName
andClusterIdentifier
for an Amazon RedshiftDataSource
. - S3StagingLocation
-
- Required: Yes
- Type: string
Describes an Amazon S3 location to store the result set of the
SelectSqlQuery
query. - SelectSqlQuery
-
- Required: Yes
- Type: string
Describes the SQL Query to execute on an Amazon Redshift database for an Amazon Redshift
DataSource
.
RedshiftDatabase
Description
Describes the database details required to connect to an Amazon Redshift database.
Members
- ClusterIdentifier
-
- Required: Yes
- Type: string
The ID of an Amazon Redshift cluster.
- DatabaseName
-
- Required: Yes
- Type: string
The name of a database hosted on an Amazon Redshift cluster.
RedshiftDatabaseCredentials
Description
Describes the database credentials for connecting to a database on an Amazon Redshift cluster.
Members
- Password
-
- Required: Yes
- Type: string
A password to be used by Amazon ML to connect to a database on an Amazon Redshift cluster. The password should have sufficient permissions to execute a
RedshiftSelectSqlQuery
query. The password should be valid for an Amazon Redshift USER. - Username
-
- Required: Yes
- Type: string
A username to be used by Amazon Machine Learning (Amazon ML)to connect to a database on an Amazon Redshift cluster. The username should have sufficient permissions to execute the
RedshiftSelectSqlQuery
query. The username should be valid for an Amazon Redshift USER.
RedshiftMetadata
Description
Describes the DataSource
details specific to Amazon Redshift.
Members
- DatabaseUserName
-
- Type: string
A username to be used by Amazon Machine Learning (Amazon ML)to connect to a database on an Amazon Redshift cluster. The username should have sufficient permissions to execute the
RedshiftSelectSqlQuery
query. The username should be valid for an Amazon Redshift USER. - RedshiftDatabase
-
- Type: RedshiftDatabase structure
Describes the database details required to connect to an Amazon Redshift database.
- SelectSqlQuery
-
- Type: string
The SQL query that is specified during CreateDataSourceFromRedshift. Returns only if
Verbose
is true in GetDataSourceInput.
ResourceNotFoundException
Description
A specified resource cannot be located.
Members
- code
-
- Type: int
- message
-
- Type: string
S3DataSpec
Description
Describes the data specification of a DataSource
.
Members
- DataLocationS3
-
- Required: Yes
- Type: string
The location of the data file(s) used by a
DataSource
. The URI specifies a data file or an Amazon Simple Storage Service (Amazon S3) directory or bucket containing data files. - DataRearrangement
-
- Type: string
A JSON string that represents the splitting and rearrangement processing to be applied to a
DataSource
. If theDataRearrangement
parameter is not provided, all of the input data is used to create theDatasource
.There are multiple parameters that control what data is used to create a datasource:
-
percentBegin
Use
percentBegin
to indicate the beginning of the range of the data used to create the Datasource. If you do not includepercentBegin
andpercentEnd
, Amazon ML includes all of the data when creating the datasource. -
percentEnd
Use
percentEnd
to indicate the end of the range of the data used to create the Datasource. If you do not includepercentBegin
andpercentEnd
, Amazon ML includes all of the data when creating the datasource. -
complement
The
complement
parameter instructs Amazon ML to use the data that is not included in the range ofpercentBegin
topercentEnd
to create a datasource. Thecomplement
parameter is useful if you need to create complementary datasources for training and evaluation. To create a complementary datasource, use the same values forpercentBegin
andpercentEnd
, along with thecomplement
parameter.For example, the following two datasources do not share any data, and can be used to train and evaluate a model. The first datasource has 25 percent of the data, and the second one has 75 percent of the data.
Datasource for evaluation:
{"splitting":{"percentBegin":0, "percentEnd":25}}
Datasource for training:
{"splitting":{"percentBegin":0, "percentEnd":25, "complement":"true"}}
-
strategy
To change how Amazon ML splits the data for a datasource, use the
strategy
parameter.The default value for the
strategy
parameter issequential
, meaning that Amazon ML takes all of the data records between thepercentBegin
andpercentEnd
parameters for the datasource, in the order that the records appear in the input data.The following two
DataRearrangement
lines are examples of sequentially ordered training and evaluation datasources:Datasource for evaluation:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential"}}
Datasource for training:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential", "complement":"true"}}
To randomly split the input data into the proportions indicated by the percentBegin and percentEnd parameters, set the
strategy
parameter torandom
and provide a string that is used as the seed value for the random data splitting (for example, you can use the S3 path to your data as the random seed string). If you choose the random split strategy, Amazon ML assigns each row of data a pseudo-random number between 0 and 100, and then selects the rows that have an assigned number betweenpercentBegin
andpercentEnd
. Pseudo-random numbers are assigned using both the input seed string value and the byte offset as a seed, so changing the data results in a different split. Any existing ordering is preserved. The random splitting strategy ensures that variables in the training and evaluation data are distributed similarly. It is useful in the cases where the input data may have an implicit sort order, which would otherwise result in training and evaluation datasources containing non-similar data records.The following two
DataRearrangement
lines are examples of non-sequentially ordered training and evaluation datasources:Datasource for evaluation:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv"}}
Datasource for training:
{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv", "complement":"true"}}
- DataSchema
-
- Type: string
A JSON string that represents the schema for an Amazon S3
DataSource
. TheDataSchema
defines the structure of the observation data in the data file(s) referenced in theDataSource
.You must provide either the
DataSchema
or theDataSchemaLocationS3
.Define your
DataSchema
as a series of key-value pairs.attributes
andexcludedVariableNames
have an array of key-value pairs for their value. Use the following format to define yourDataSchema
.{ "version": "1.0",
"recordAnnotationFieldName": "F1",
"recordWeightFieldName": "F2",
"targetFieldName": "F3",
"dataFormat": "CSV",
"dataFileContainsHeader": true,
"attributes": [
{ "fieldName": "F1", "fieldType": "TEXT" }, { "fieldName": "F2", "fieldType": "NUMERIC" }, { "fieldName": "F3", "fieldType": "CATEGORICAL" }, { "fieldName": "F4", "fieldType": "NUMERIC" }, { "fieldName": "F5", "fieldType": "CATEGORICAL" }, { "fieldName": "F6", "fieldType": "TEXT" }, { "fieldName": "F7", "fieldType": "WEIGHTED_INT_SEQUENCE" }, { "fieldName": "F8", "fieldType": "WEIGHTED_STRING_SEQUENCE" } ],
"excludedVariableNames": [ "F6" ] }
- DataSchemaLocationS3
-
- Type: string
Describes the schema location in Amazon S3. You must provide either the
DataSchema
or theDataSchemaLocationS3
.
Tag
Description
A custom key-value pair associated with an ML object, such as an ML model.
Members
- Key
-
- Type: string
A unique identifier for the tag. Valid characters include Unicode letters, digits, white space, _, ., /, =, +, -, %, and @.
- Value
-
- Type: string
An optional string, typically used to describe or define the tag. Valid characters include Unicode letters, digits, white space, _, ., /, =, +, -, %, and @.
TagLimitExceededException
Members
- message
-
- Type: string