Module Smaws_Client_MachineLearning.Types

type nonrec float_label = float
type nonrec vip_ur_l = string
type nonrec verbose = bool
type nonrec variable_value = string
type nonrec variable_name = string
type nonrec entity_id = string
type nonrec update_ml_model_output = {
  1. ml_model_id : entity_id option;
    (*

    The ID assigned to the MLModel during creation. This value should be identical to the value of the MLModelID in the request.

    *)
}

Represents the output of an UpdateMLModel operation.

You can see the updated content by using the GetMLModel operation.

type nonrec entity_name = string
type nonrec score_threshold = float
type nonrec update_ml_model_input = {
  1. score_threshold : score_threshold option;
    (*

    The ScoreThreshold used in binary classification MLModel 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 the MLModel, such as true. Output values less than the ScoreThreshold receive a negative response from the MLModel, such as false.

    *)
  2. ml_model_name : entity_name option;
    (*

    A user-supplied name or description of the MLModel.

    *)
  3. ml_model_id : entity_id;
    (*

    The ID assigned to the MLModel during creation.

    *)
}
type nonrec error_message = string
type nonrec error_code = int
type nonrec resource_not_found_exception = {
  1. code : error_code option;
  2. message : error_message option;
}

A specified resource cannot be located.

type nonrec invalid_input_exception = {
  1. code : error_code option;
  2. message : error_message option;
}

An error on the client occurred. Typically, the cause is an invalid input value.

type nonrec internal_server_exception = {
  1. code : error_code option;
  2. message : error_message option;
}

An error on the server occurred when trying to process a request.

type nonrec update_evaluation_output = {
  1. evaluation_id : entity_id option;
    (*

    The ID assigned to the Evaluation during creation. This value should be identical to the value of the Evaluation in the request.

    *)
}

Represents the output of an UpdateEvaluation operation.

You can see the updated content by using the GetEvaluation operation.

type nonrec update_evaluation_input = {
  1. evaluation_name : entity_name;
    (*

    A new user-supplied name or description of the Evaluation that will replace the current content.

    *)
  2. evaluation_id : entity_id;
    (*

    The ID assigned to the Evaluation during creation.

    *)
}
type nonrec update_data_source_output = {
  1. data_source_id : entity_id option;
    (*

    The ID assigned to the DataSource during creation. This value should be identical to the value of the DataSourceID in the request.

    *)
}

Represents the output of an UpdateDataSource operation.

You can see the updated content by using the GetBatchPrediction operation.

type nonrec update_data_source_input = {
  1. data_source_name : entity_name;
    (*

    A new user-supplied name or description of the DataSource that will replace the current description.

    *)
  2. data_source_id : entity_id;
    (*

    The ID assigned to the DataSource during creation.

    *)
}
type nonrec update_batch_prediction_output = {
  1. batch_prediction_id : entity_id option;
    (*

    The ID assigned to the BatchPrediction during creation. This value should be identical to the value of the BatchPredictionId in the request.

    *)
}

Represents the output of an UpdateBatchPrediction operation.

You can see the updated content by using the GetBatchPrediction operation.

type nonrec update_batch_prediction_input = {
  1. batch_prediction_name : entity_name;
    (*

    A new user-supplied name or description of the BatchPrediction.

    *)
  2. batch_prediction_id : entity_id;
    (*

    The ID assigned to the BatchPrediction during creation.

    *)
}
type nonrec string_type = string
type nonrec training_parameters = (string_type * string_type) list
type nonrec taggable_resource_type =
  1. | ML_MODEL
  2. | EVALUATION
  3. | DATASOURCE
  4. | BATCH_PREDICTION
type nonrec tag_value = string
type nonrec tag_key = string
type nonrec tag = {
  1. value : tag_value option;
    (*

    An optional string, typically used to describe or define the tag. Valid characters include Unicode letters, digits, white space, _, ., /, =, +, -, %, and @.

    *)
  2. key : tag_key option;
    (*

    A unique identifier for the tag. Valid characters include Unicode letters, digits, white space, _, ., /, =, +, -, %, and @.

    *)
}

A custom key-value pair associated with an ML object, such as an ML model.

type nonrec tag_list = tag list
type nonrec tag_limit_exceeded_exception = {
  1. message : error_message option;
}
type nonrec tag_key_list = tag_key list
type nonrec sort_order =
  1. | DSC
  2. | ASC

The sort order specified in a listing condition. Possible values include the following:

  • asc - Present the information in ascending order (from A-Z).
  • dsc - Present the information in descending order (from Z-A).
type nonrec score_value = float
type nonrec label = string
type nonrec score_value_per_label_map = (label * score_value) list

Provides the raw classification score corresponding to each label.

type nonrec s3_url = string
type nonrec data_rearrangement = string
type nonrec data_schema = string
type nonrec s3_data_spec = {
  1. data_schema_location_s3 : s3_url option;
    (*

    Describes the schema location in Amazon S3. You must provide either the DataSchema or the DataSchemaLocationS3.

    *)
  2. data_schema : data_schema option;
    (*

    A JSON string that represents the schema for an Amazon S3 DataSource. The DataSchema defines the structure of the observation data in the data file(s) referenced in the DataSource.

    You must provide either the DataSchema or the DataSchemaLocationS3.

    Define your DataSchema as a series of key-value pairs. attributes and excludedVariableNames have an array of key-value pairs for their value. Use the following format to define your DataSchema.

    { "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" ] }

    *)
  3. data_rearrangement : data_rearrangement option;
    (*

    A JSON string that represents the splitting and rearrangement processing to be applied to a DataSource. If the DataRearrangement parameter is not provided, all of the input data is used to create the Datasource.

    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 include percentBegin and percentEnd, 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 include percentBegin and percentEnd, 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 of percentBegin to percentEnd to create a datasource. The complement parameter is useful if you need to create complementary datasources for training and evaluation. To create a complementary datasource, use the same values for percentBegin and percentEnd, along with the complement 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 is sequential, meaning that Amazon ML takes all of the data records between the percentBegin and percentEnd 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 to random 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 between percentBegin and percentEnd. 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"}}

    *)
  4. data_location_s3 : s3_url;
    (*

    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.

    *)
}

Describes the data specification of a DataSource.

type nonrec role_ar_n = string
type nonrec redshift_select_sql_query = string
type nonrec redshift_database_name = string
type nonrec redshift_cluster_identifier = string
type nonrec redshift_database = {
  1. cluster_identifier : redshift_cluster_identifier;
  2. database_name : redshift_database_name;
}

Describes the database details required to connect to an Amazon Redshift database.

type nonrec redshift_database_username = string
type nonrec redshift_metadata = {
  1. select_sql_query : redshift_select_sql_query option;
    (*

    The SQL query that is specified during CreateDataSourceFromRedshift. Returns only if Verbose is true in GetDataSourceInput.

    *)
  2. database_user_name : redshift_database_username option;
  3. redshift_database : redshift_database option;
}

Describes the DataSource details specific to Amazon Redshift.

type nonrec redshift_database_password = string
type nonrec redshift_database_credentials = {
  1. password : redshift_database_password;
  2. username : redshift_database_username;
}

Describes the database credentials for connecting to a database on an Amazon Redshift cluster.

type nonrec redshift_data_spec = {
  1. data_schema_uri : s3_url option;
    (*

    Describes the schema location for an Amazon Redshift DataSource.

    *)
  2. data_schema : data_schema option;
    (*

    A JSON string that represents the schema for an Amazon Redshift DataSource. The DataSchema defines the structure of the observation data in the data file(s) referenced in the DataSource.

    A DataSchema is not required if you specify a DataSchemaUri.

    Define your DataSchema as a series of key-value pairs. attributes and excludedVariableNames have an array of key-value pairs for their value. Use the following format to define your DataSchema.

    { "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" ] }

    *)
  3. data_rearrangement : data_rearrangement option;
    (*

    A JSON string that represents the splitting and rearrangement processing to be applied to a DataSource. If the DataRearrangement parameter is not provided, all of the input data is used to create the Datasource.

    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 include percentBegin and percentEnd, 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 include percentBegin and percentEnd, 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 of percentBegin to percentEnd to create a datasource. The complement parameter is useful if you need to create complementary datasources for training and evaluation. To create a complementary datasource, use the same values for percentBegin and percentEnd, along with the complement 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 is sequential, meaning that Amazon ML takes all of the data records between the percentBegin and percentEnd 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 to random 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 between percentBegin and percentEnd. 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"}}

    *)
  4. s3_staging_location : s3_url;
    (*

    Describes an Amazon S3 location to store the result set of the SelectSqlQuery query.

    *)
  5. database_credentials : redshift_database_credentials;
    (*

    Describes AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon Redshift database.

    *)
  6. select_sql_query : redshift_select_sql_query;
    (*

    Describes the SQL Query to execute on an Amazon Redshift database for an Amazon Redshift DataSource.

    *)
  7. database_information : redshift_database;
    (*

    Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift DataSource.

    *)
}

Describes the data specification of an Amazon Redshift DataSource.

type nonrec record = (variable_name * variable_value) list

A map of variable name-value pairs that represent an observation.

type nonrec recipe = string
type nonrec realtime_endpoint_status =
  1. | FAILED
  2. | UPDATING
  3. | READY
  4. | NONE
type nonrec integer_type = int
type nonrec epoch_time = Smaws_Lib.CoreTypes.Timestamp.t
type nonrec realtime_endpoint_info = {
  1. endpoint_status : realtime_endpoint_status option;
    (*

    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.
    *)
  2. endpoint_url : vip_ur_l option;
    (*

    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.

    *)
  3. created_at : epoch_time option;
    (*

    The time that the request to create the real-time endpoint for the MLModel was received. The time is expressed in epoch time.

    *)
  4. peak_requests_per_second : integer_type option;
    (*

    The maximum processing rate for the real-time endpoint for MLModel, measured in incoming requests per second.

    *)
}

Describes the real-time endpoint information for an MLModel.

type nonrec rds_select_sql_query = string
type nonrec rds_instance_identifier = string
type nonrec rds_database_name = string
type nonrec rds_database = {
  1. database_name : rds_database_name;
  2. instance_identifier : rds_instance_identifier;
    (*

    The ID of an RDS DB instance.

    *)
}

The database details of an Amazon RDS database.

type nonrec rds_database_username = string
type nonrec edp_resource_role = string
type nonrec edp_service_role = string
type nonrec edp_pipeline_id = string
type nonrec rds_metadata = {
  1. data_pipeline_id : edp_pipeline_id option;
    (*

    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.

    *)
  2. service_role : edp_service_role option;
    (*

    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.

    *)
  3. resource_role : edp_resource_role option;
    (*

    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.

    *)
  4. select_sql_query : rds_select_sql_query option;
    (*

    The SQL query that is supplied during CreateDataSourceFromRDS. Returns only if Verbose is true in GetDataSourceInput.

    *)
  5. database_user_name : rds_database_username option;
  6. database : rds_database option;
    (*

    The database details required to connect to an Amazon RDS.

    *)
}

The datasource details that are specific to Amazon RDS.

type nonrec rds_database_password = string
type nonrec rds_database_credentials = {
  1. password : rds_database_password;
  2. username : rds_database_username;
}

The database credentials to connect to a database on an RDS DB instance.

type nonrec edp_subnet_id = string
type nonrec edp_security_group_id = string
type nonrec edp_security_group_ids = edp_security_group_id list
type nonrec rds_data_spec = {
  1. security_group_ids : edp_security_group_ids;
    (*

    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.

    *)
  2. subnet_id : edp_subnet_id;
    (*

    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.

    *)
  3. service_role : edp_service_role;
    (*

    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.

    *)
  4. resource_role : edp_resource_role;
    (*

    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.

    *)
  5. data_schema_uri : s3_url option;
    (*

    The Amazon S3 location of the DataSchema.

    *)
  6. data_schema : data_schema option;
    (*

    A JSON string that represents the schema for an Amazon RDS DataSource. The DataSchema defines the structure of the observation data in the data file(s) referenced in the DataSource.

    A DataSchema is not required if you specify a DataSchemaUri

    Define your DataSchema as a series of key-value pairs. attributes and excludedVariableNames have an array of key-value pairs for their value. Use the following format to define your DataSchema.

    { "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" ] }

    *)
  7. data_rearrangement : data_rearrangement option;
    (*

    A JSON string that represents the splitting and rearrangement processing to be applied to a DataSource. If the DataRearrangement parameter is not provided, all of the input data is used to create the Datasource.

    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 include percentBegin and percentEnd, 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 include percentBegin and percentEnd, 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 of percentBegin to percentEnd to create a datasource. The complement parameter is useful if you need to create complementary datasources for training and evaluation. To create a complementary datasource, use the same values for percentBegin and percentEnd, along with the complement 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 is sequential, meaning that Amazon ML takes all of the data records between the percentBegin and percentEnd 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 to random 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 between percentBegin and percentEnd. 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"}}

    *)
  8. s3_staging_location : s3_url;
    (*

    The Amazon S3 location for staging Amazon RDS data. The data retrieved from Amazon RDS using SelectSqlQuery is stored in this location.

    *)
  9. database_credentials : rds_database_credentials;
    (*

    The AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon RDS database.

    *)
  10. select_sql_query : rds_select_sql_query;
    (*

    The query that is used to retrieve the observation data for the DataSource.

    *)
  11. database_information : rds_database;
    (*

    Describes the DatabaseName and InstanceIdentifier of an Amazon RDS database.

    *)
}

The data specification of an Amazon Relational Database Service (Amazon RDS) DataSource.

type nonrec presigned_s3_url = string
type nonrec predictor_not_mounted_exception = {
  1. message : error_message option;
}

The exception is thrown when a predict request is made to an unmounted MLModel.

type nonrec details_value = string
type nonrec details_attributes =
  1. | ALGORITHM
  2. | PREDICTIVE_MODEL_TYPE

Contains the key values of DetailsMap:

  • PredictiveModelType - Indicates the type of the MLModel.
  • Algorithm - Indicates the algorithm that was used for the MLModel.
type nonrec details_map = (details_attributes * details_value) list

Provides any additional details regarding the prediction.

type nonrec prediction = {
  1. details : details_map option;
  2. predicted_scores : score_value_per_label_map option;
  3. predicted_value : float_label option;
    (*

    The prediction value for REGRESSION MLModel.

    *)
  4. predicted_label : label option;
    (*

    The prediction label for either a BINARY or MULTICLASS MLModel.

    *)
}

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 a BINARY or MULTICLASS MLModel request.
  • PredictedScores - Contains the raw classification score corresponding to each label.
  • PredictedValue - Present for a REGRESSION MLModel request.
type nonrec predict_output = {
  1. prediction : prediction option;
}
type nonrec predict_input = {
  1. predict_endpoint : vip_ur_l;
  2. record : record;
  3. ml_model_id : entity_id;
    (*

    A unique identifier of the MLModel.

    *)
}
type nonrec limit_exceeded_exception = {
  1. code : error_code option;
  2. message : error_message option;
}

The subscriber exceeded the maximum number of operations. This exception can occur when listing objects such as DataSource.

type nonrec performance_metrics_property_value = string
type nonrec performance_metrics_property_key = string
type nonrec performance_metrics_properties = (performance_metrics_property_key * performance_metrics_property_value) list
type nonrec performance_metrics = {
  1. properties : performance_metrics_properties option;
}

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.

type nonrec page_limit = int
type nonrec message = string
type nonrec aws_user_arn = string
type nonrec ml_model_name = string
type nonrec entity_status =
  1. | DELETED
  2. | COMPLETED
  3. | FAILED
  4. | INPROGRESS
  5. | PENDING

Object status with the following possible values:

  • PENDING
  • INPROGRESS
  • FAILED
  • COMPLETED
  • DELETED
type nonrec long_type = Smaws_Lib.CoreTypes.Int64.t
type nonrec algorithm =
  1. | SGD

The function used to train an MLModel. Training choices supported by Amazon ML include the following:

  • SGD - Stochastic Gradient Descent.
  • RandomForest - Random forest of decision trees.
type nonrec ml_model_type =
  1. | MULTICLASS
  2. | BINARY
  3. | REGRESSION
type nonrec ml_model = {
  1. started_at : epoch_time option;
  2. finished_at : epoch_time option;
  3. compute_time : long_type option;
  4. message : message option;
    (*

    A description of the most recent details about accessing the MLModel.

    *)
  5. score_threshold_last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to the ScoreThreshold. The time is expressed in epoch time.

    *)
  6. score_threshold : score_threshold option;
  7. ml_model_type : ml_model_type option;
    (*

    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?".
    *)
  8. algorithm : algorithm option;
    (*

    The algorithm used to train the MLModel. The following algorithm is supported:

    • SGD -- Stochastic gradient descent. The goal of SGD is to minimize the gradient of the loss function.
    *)
  9. input_data_location_s3 : s3_url option;
    (*

    The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).

    *)
  10. training_parameters : training_parameters option;
    (*

    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 to 2147483648. The default value is 33554432.

    • sgd.maxPasses - The number of times that the training process traverses the observations to build the MLModel. The value is an integer that ranges from 1 to 10000. The default value is 10.
    • 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 are auto and none. The default value is none.

    • 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 as 1.0E-08.

      The value is a double that ranges from 0 to MAX_DOUBLE. The default is to not use L1 normalization. This parameter can't be used when L2 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 as 1.0E-08.

      The value is a double that ranges from 0 to MAX_DOUBLE. The default is to not use L2 normalization. This parameter can't be used when L1 is specified. Use this parameter sparingly.

    *)
  11. endpoint_info : realtime_endpoint_info option;
    (*

    The current endpoint of the MLModel.

    *)
  12. size_in_bytes : long_type option;
  13. status : entity_status option;
    (*

    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 an MLModel.
    • INPROGRESS - The creation process is underway.
    • FAILED - The request to create an MLModel didn't run to completion. The model isn't usable.
    • COMPLETED - The creation process completed successfully.
    • DELETED - The MLModel is marked as deleted. It isn't usable.
    *)
  14. name : ml_model_name option;
    (*

    A user-supplied name or description of the MLModel.

    *)
  15. last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to the MLModel. The time is expressed in epoch time.

    *)
  16. created_at : epoch_time option;
    (*

    The time that the MLModel was created. The time is expressed in epoch time.

    *)
  17. created_by_iam_user : aws_user_arn option;
    (*

    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.

    *)
  18. training_data_source_id : entity_id option;
    (*

    The ID of the training DataSource. The CreateMLModel operation uses the TrainingDataSourceId.

    *)
  19. ml_model_id : entity_id option;
    (*

    The ID assigned to the MLModel at creation.

    *)
}

Represents the output of a GetMLModel operation.

The content consists of the detailed metadata and the current status of the MLModel.

type nonrec ml_models = ml_model list
type nonrec ml_model_filter_variable =
  1. | TRAINING_DATA_URI
  2. | ALGORITHM
  3. | ML_MODEL_TYPE
  4. | REAL_TIME_ENDPOINT_STATUS
  5. | TRAINING_DATASOURCE_ID
  6. | IAM_USER
  7. | NAME
  8. | STATUS
  9. | LAST_UPDATED_AT
  10. | CREATED_AT
type nonrec invalid_tag_exception = {
  1. message : error_message option;
}
type nonrec idempotent_parameter_mismatch_exception = {
  1. code : error_code option;
  2. message : error_message option;
}

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.

type nonrec get_ml_model_output = {
  1. schema : data_schema option;
    (*

    The schema used by all of the data files referenced by the DataSource.

    Note: This parameter is provided as part of the verbose format.

    *)
  2. recipe : recipe option;
    (*

    The recipe to use when training the MLModel. The Recipe 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.

    *)
  3. started_at : epoch_time option;
    (*

    The epoch time when Amazon Machine Learning marked the MLModel as INPROGRESS. StartedAt isn't available if the MLModel is in the PENDING state.

    *)
  4. finished_at : epoch_time option;
    (*

    The epoch time when Amazon Machine Learning marked the MLModel as COMPLETED or FAILED. FinishedAt is only available when the MLModel is in the COMPLETED or FAILED state.

    *)
  5. compute_time : long_type option;
    (*

    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 the MLModel is in the COMPLETED state.

    *)
  6. message : message option;
    (*

    A description of the most recent details about accessing the MLModel.

    *)
  7. log_uri : presigned_s3_url option;
    (*

    A link to the file that contains logs of the CreateMLModel operation.

    *)
  8. score_threshold_last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to the ScoreThreshold. The time is expressed in epoch time.

    *)
  9. score_threshold : score_threshold option;
    (*

    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 as false.

    *)
  10. ml_model_type : ml_model_type option;
    (*

    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?"
    *)
  11. input_data_location_s3 : s3_url option;
    (*

    The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).

    *)
  12. training_parameters : training_parameters option;
    (*

    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 to 2147483648. The default value is 33554432.

    • sgd.maxPasses - The number of times that the training process traverses the observations to build the MLModel. The value is an integer that ranges from 1 to 10000. The default value is 10.
    • 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 are auto and none. The default value is none. 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 as 1.0E-08.

      The value is a double that ranges from 0 to MAX_DOUBLE. The default is to not use L1 normalization. This parameter can't be used when L2 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 as 1.0E-08.

      The value is a double that ranges from 0 to MAX_DOUBLE. The default is to not use L2 normalization. This parameter can't be used when L1 is specified. Use this parameter sparingly.

    *)
  13. endpoint_info : realtime_endpoint_info option;
    (*

    The current endpoint of the MLModel

    *)
  14. size_in_bytes : long_type option;
  15. status : entity_status option;
    (*

    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 a MLModel.
    • 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 - The MLModel is marked as deleted. It isn't usable.
    *)
  16. name : ml_model_name option;
    (*

    A user-supplied name or description of the MLModel.

    *)
  17. last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to the MLModel. The time is expressed in epoch time.

    *)
  18. created_at : epoch_time option;
    (*

    The time that the MLModel was created. The time is expressed in epoch time.

    *)
  19. created_by_iam_user : aws_user_arn option;
    (*

    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.

    *)
  20. training_data_source_id : entity_id option;
    (*

    The ID of the training DataSource.

    *)
  21. ml_model_id : entity_id option;
    (*

    The MLModel ID, which is same as the MLModelId in the request.

    *)
}

Represents the output of a GetMLModel operation, and provides detailed information about a MLModel.

type nonrec get_ml_model_input = {
  1. verbose : verbose option;
    (*

    Specifies whether the GetMLModel operation should return Recipe.

    If true, Recipe is returned.

    If false, Recipe is not returned.

    *)
  2. ml_model_id : entity_id;
    (*

    The ID assigned to the MLModel at creation.

    *)
}
type nonrec get_evaluation_output = {
  1. started_at : epoch_time option;
    (*

    The epoch time when Amazon Machine Learning marked the Evaluation as INPROGRESS. StartedAt isn't available if the Evaluation is in the PENDING state.

    *)
  2. finished_at : epoch_time option;
    (*

    The epoch time when Amazon Machine Learning marked the Evaluation as COMPLETED or FAILED. FinishedAt is only available when the Evaluation is in the COMPLETED or FAILED state.

    *)
  3. compute_time : long_type option;
    (*

    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 the Evaluation is in the COMPLETED state.

    *)
  4. message : message option;
    (*

    A description of the most recent details about evaluating the MLModel.

    *)
  5. log_uri : presigned_s3_url option;
    (*

    A link to the file that contains logs of the CreateEvaluation operation.

    *)
  6. performance_metrics : performance_metrics option;
    (*

    Measurements of how well the MLModel performed using observations referenced by the DataSource. One of the following metric is returned based on the type of the MLModel:

    • 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.

    *)
  7. status : entity_status option;
    (*

    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 an MLModel.
    • INPROGRESS - The evaluation is underway.
    • FAILED - The request to evaluate an MLModel did not run to completion. It is not usable.
    • COMPLETED - The evaluation process completed successfully.
    • DELETED - The Evaluation is marked as deleted. It is not usable.
    *)
  8. name : entity_name option;
    (*

    A user-supplied name or description of the Evaluation.

    *)
  9. last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to the Evaluation. The time is expressed in epoch time.

    *)
  10. created_at : epoch_time option;
    (*

    The time that the Evaluation was created. The time is expressed in epoch time.

    *)
  11. created_by_iam_user : aws_user_arn option;
    (*

    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.

    *)
  12. input_data_location_s3 : s3_url option;
    (*

    The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).

    *)
  13. evaluation_data_source_id : entity_id option;
    (*

    The DataSource used for this evaluation.

    *)
  14. ml_model_id : entity_id option;
    (*

    The ID of the MLModel that was the focus of the evaluation.

    *)
  15. evaluation_id : entity_id option;
    (*

    The evaluation ID which is same as the EvaluationId in the request.

    *)
}

Represents the output of a GetEvaluation operation and describes an Evaluation.

type nonrec get_evaluation_input = {
  1. evaluation_id : entity_id;
    (*

    The ID of the Evaluation to retrieve. The evaluation of each MLModel is recorded and cataloged. The ID provides the means to access the information.

    *)
}
type nonrec compute_statistics = bool
type nonrec get_data_source_output = {
  1. data_source_schema : data_schema option;
    (*

    The schema used by all of the data files of this DataSource.

    Note: This parameter is provided as part of the verbose format.

    *)
  2. started_at : epoch_time option;
    (*

    The epoch time when Amazon Machine Learning marked the DataSource as INPROGRESS. StartedAt isn't available if the DataSource is in the PENDING state.

    *)
  3. finished_at : epoch_time option;
    (*

    The epoch time when Amazon Machine Learning marked the DataSource as COMPLETED or FAILED. FinishedAt is only available when the DataSource is in the COMPLETED or FAILED state.

    *)
  4. compute_time : long_type option;
    (*

    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 the DataSource is in the COMPLETED state and the ComputeStatistics is set to true.

    *)
  5. compute_statistics : compute_statistics option;
    (*

    The parameter is true if statistics need to be generated from the observation data.

    *)
  6. role_ar_n : role_ar_n option;
  7. rds_metadata : rds_metadata option;
  8. redshift_metadata : redshift_metadata option;
  9. message : message option;
    (*

    The user-supplied description of the most recent details about creating the DataSource.

    *)
  10. log_uri : presigned_s3_url option;
    (*

    A link to the file containing logs of CreateDataSourceFrom* operations.

    *)
  11. status : entity_status option;
    (*

    The current status of the DataSource. This element can have one of the following values:

    • PENDING - 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.
    *)
  12. name : entity_name option;
    (*

    A user-supplied name or description of the DataSource.

    *)
  13. number_of_files : long_type option;
    (*

    The number of data files referenced by the DataSource.

    *)
  14. data_size_in_bytes : long_type option;
    (*

    The total size of observations in the data files.

    *)
  15. last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to the DataSource. The time is expressed in epoch time.

    *)
  16. created_at : epoch_time option;
    (*

    The time that the DataSource was created. The time is expressed in epoch time.

    *)
  17. created_by_iam_user : aws_user_arn option;
    (*

    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.

    *)
  18. data_rearrangement : data_rearrangement option;
    (*

    A JSON string that represents the splitting and rearrangement requirement used when this DataSource was created.

    *)
  19. data_location_s3 : s3_url option;
    (*

    The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).

    *)
  20. data_source_id : entity_id option;
    (*

    The ID assigned to the DataSource at creation. This value should be identical to the value of the DataSourceId in the request.

    *)
}

Represents the output of a GetDataSource operation and describes a DataSource.

type nonrec get_data_source_input = {
  1. verbose : verbose option;
    (*

    Specifies whether the GetDataSource operation should return DataSourceSchema.

    If true, DataSourceSchema is returned.

    If false, DataSourceSchema is not returned.

    *)
  2. data_source_id : entity_id;
    (*

    The ID assigned to the DataSource at creation.

    *)
}
type nonrec get_batch_prediction_output = {
  1. invalid_record_count : long_type option;
    (*

    The number of invalid records that Amazon Machine Learning saw while processing the BatchPrediction.

    *)
  2. total_record_count : long_type option;
    (*

    The number of total records that Amazon Machine Learning saw while processing the BatchPrediction.

    *)
  3. started_at : epoch_time option;
    (*

    The epoch time when Amazon Machine Learning marked the BatchPrediction as INPROGRESS. StartedAt isn't available if the BatchPrediction is in the PENDING state.

    *)
  4. finished_at : epoch_time option;
    (*

    The epoch time when Amazon Machine Learning marked the BatchPrediction as COMPLETED or FAILED. FinishedAt is only available when the BatchPrediction is in the COMPLETED or FAILED state.

    *)
  5. compute_time : long_type option;
    (*

    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 the BatchPrediction is in the COMPLETED state.

    *)
  6. message : message option;
    (*

    A description of the most recent details about processing the batch prediction request.

    *)
  7. log_uri : presigned_s3_url option;
    (*

    A link to the file that contains logs of the CreateBatchPrediction operation.

    *)
  8. output_uri : s3_url option;
    (*

    The location of an Amazon S3 bucket or directory to receive the operation results.

    *)
  9. status : entity_status option;
    (*

    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 - The BatchPrediction is marked as deleted. It is not usable.
    *)
  10. name : entity_name option;
    (*

    A user-supplied name or description of the BatchPrediction.

    *)
  11. last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to BatchPrediction. The time is expressed in epoch time.

    *)
  12. created_at : epoch_time option;
    (*

    The time when the BatchPrediction was created. The time is expressed in epoch time.

    *)
  13. created_by_iam_user : aws_user_arn option;
    (*

    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.

    *)
  14. input_data_location_s3 : s3_url option;
    (*

    The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).

    *)
  15. batch_prediction_data_source_id : entity_id option;
    (*

    The ID of the DataSource that was used to create the BatchPrediction.

    *)
  16. ml_model_id : entity_id option;
    (*

    The ID of the MLModel that generated predictions for the BatchPrediction request.

    *)
  17. batch_prediction_id : entity_id option;
    (*

    An ID assigned to the BatchPrediction at creation. This value should be identical to the value of the BatchPredictionID in the request.

    *)
}

Represents the output of a GetBatchPrediction operation and describes a BatchPrediction.

type nonrec get_batch_prediction_input = {
  1. batch_prediction_id : entity_id;
    (*

    An ID assigned to the BatchPrediction at creation.

    *)
}
type nonrec evaluation = {
  1. started_at : epoch_time option;
  2. finished_at : epoch_time option;
  3. compute_time : long_type option;
  4. message : message option;
    (*

    A description of the most recent details about evaluating the MLModel.

    *)
  5. performance_metrics : performance_metrics option;
    (*

    Measurements of how well the MLModel performed, using observations referenced by the DataSource. One of the following metrics is returned, based on the type of the MLModel:

    • 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.

    *)
  6. status : entity_status option;
    (*

    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 an MLModel.
    • INPROGRESS - The evaluation is underway.
    • FAILED - The request to evaluate an MLModel did not run to completion. It is not usable.
    • COMPLETED - The evaluation process completed successfully.
    • DELETED - The Evaluation is marked as deleted. It is not usable.
    *)
  7. name : entity_name option;
    (*

    A user-supplied name or description of the Evaluation.

    *)
  8. last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to the Evaluation. The time is expressed in epoch time.

    *)
  9. created_at : epoch_time option;
    (*

    The time that the Evaluation was created. The time is expressed in epoch time.

    *)
  10. created_by_iam_user : aws_user_arn option;
    (*

    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.

    *)
  11. input_data_location_s3 : s3_url option;
    (*

    The location and name of the data in Amazon Simple Storage Server (Amazon S3) that is used in the evaluation.

    *)
  12. evaluation_data_source_id : entity_id option;
    (*

    The ID of the DataSource that is used to evaluate the MLModel.

    *)
  13. ml_model_id : entity_id option;
    (*

    The ID of the MLModel that is the focus of the evaluation.

    *)
  14. evaluation_id : entity_id option;
    (*

    The ID that is assigned to the Evaluation at creation.

    *)
}

Represents the output of GetEvaluation operation.

The content consists of the detailed metadata and data file information and the current status of the Evaluation.

type nonrec evaluations = evaluation list
type nonrec evaluation_filter_variable =
  1. | DATA_URI
  2. | DATASOURCE_ID
  3. | ML_MODEL_ID
  4. | IAM_USER
  5. | NAME
  6. | STATUS
  7. | LAST_UPDATED_AT
  8. | CREATED_AT

A list of the variables to use in searching or filtering Evaluation.

  • CreatedAt - Sets the search criteria to Evaluation creation date.
  • Status - Sets the search criteria to Evaluation status.
  • Name - Sets the search criteria to the contents of Evaluation Name.
  • IAMUser - Sets the search criteria to the user account that invoked an evaluation.
  • MLModelId - Sets the search criteria to the Predictor that was evaluated.
  • DataSourceId - Sets the search criteria to the DataSource used in evaluation.
  • DataUri - Sets the search criteria to the data file(s) used in evaluation. The URL can identify either a file or an Amazon Simple Storage Service (Amazon S3) bucket or directory.
type nonrec describe_tags_output = {
  1. tags : tag_list option;
    (*

    A list of tags associated with the ML object.

    *)
  2. resource_type : taggable_resource_type option;
    (*

    The type of the tagged ML object.

    *)
  3. resource_id : entity_id option;
    (*

    The ID of the tagged ML object.

    *)
}

Amazon ML returns the following elements.

type nonrec describe_tags_input = {
  1. resource_type : taggable_resource_type;
    (*

    The type of the ML object.

    *)
  2. resource_id : entity_id;
    (*

    The ID of the ML object. For example, exampleModelId.

    *)
}
type nonrec describe_ml_models_output = {
  1. next_token : string_type option;
    (*

    The ID of the next page in the paginated results that indicates at least one more page follows.

    *)
  2. results : ml_models option;
    (*

    A list of MLModel that meet the search criteria.

    *)
}

Represents the output of a DescribeMLModels operation. The content is essentially a list of MLModel.

type nonrec comparator_value = string
type nonrec describe_ml_models_input = {
  1. limit : page_limit option;
    (*

    The number of pages of information to include in the result. The range of acceptable values is 1 through 100. The default value is 100.

    *)
  2. next_token : string_type option;
    (*

    The ID of the page in the paginated results.

    *)
  3. sort_order : sort_order option;
    (*

    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.

    *)
  4. prefix : comparator_value option;
    (*

    A string that is found at the beginning of a variable, such as Name or Id.

    For example, an MLModel could have the Name 2014-09-09-HolidayGiftMailer. To search for this MLModel, select Name for the FilterVariable and any of the following strings for the Prefix:

    • 2014-09
    • 2014-09-09
    • 2014-09-09-Holiday
    *)
  5. n_e : comparator_value option;
    (*

    The not equal to operator. The MLModel results will have FilterVariable values not equal to the value specified with NE.

    *)
  6. l_e : comparator_value option;
    (*

    The less than or equal to operator. The MLModel results will have FilterVariable values that are less than or equal to the value specified with LE.

    *)
  7. g_e : comparator_value option;
    (*

    The greater than or equal to operator. The MLModel results will have FilterVariable values that are greater than or equal to the value specified with GE.

    *)
  8. l_t : comparator_value option;
    (*

    The less than operator. The MLModel results will have FilterVariable values that are less than the value specified with LT.

    *)
  9. g_t : comparator_value option;
    (*

    The greater than operator. The MLModel results will have FilterVariable values that are greater than the value specified with GT.

    *)
  10. e_q : comparator_value option;
    (*

    The equal to operator. The MLModel results will have FilterVariable values that exactly match the value specified with EQ.

    *)
  11. filter_variable : ml_model_filter_variable option;
    (*

    Use one of the following variables to filter a list of MLModel:

    • CreatedAt - Sets the search criteria to MLModel creation date.
    • Status - Sets the search criteria to MLModel status.
    • Name - Sets the search criteria to the contents of MLModel Name.
    • IAMUser - Sets the search criteria to the user account that invoked the MLModel creation.
    • TrainingDataSourceId - Sets the search criteria to the DataSource used to train one or more MLModel.
    • RealtimeEndpointStatus - Sets the search criteria to the MLModel real-time endpoint status.
    • MLModelType - Sets the search criteria to MLModel type: binary, regression, or multi-class.
    • Algorithm - Sets the search criteria to the algorithm that the MLModel uses.
    • TrainingDataURI - Sets the search criteria to the data file(s) used in training a MLModel. The URL can identify either a file or an Amazon Simple Storage Service (Amazon S3) bucket or directory.
    *)
}
type nonrec describe_evaluations_output = {
  1. next_token : string_type option;
    (*

    The ID of the next page in the paginated results that indicates at least one more page follows.

    *)
  2. results : evaluations option;
    (*

    A list of Evaluation that meet the search criteria.

    *)
}

Represents the query results from a DescribeEvaluations operation. The content is essentially a list of Evaluation.

type nonrec describe_evaluations_input = {
  1. limit : page_limit option;
    (*

    The maximum number of Evaluation to include in the result.

    *)
  2. next_token : string_type option;
    (*

    The ID of the page in the paginated results.

    *)
  3. sort_order : sort_order option;
    (*

    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.

    *)
  4. prefix : comparator_value option;
    (*

    A string that is found at the beginning of a variable, such as Name or Id.

    For example, an Evaluation could have the Name 2014-09-09-HolidayGiftMailer. To search for this Evaluation, select Name for the FilterVariable and any of the following strings for the Prefix:

    • 2014-09
    • 2014-09-09
    • 2014-09-09-Holiday
    *)
  5. n_e : comparator_value option;
    (*

    The not equal to operator. The Evaluation results will have FilterVariable values not equal to the value specified with NE.

    *)
  6. l_e : comparator_value option;
    (*

    The less than or equal to operator. The Evaluation results will have FilterVariable values that are less than or equal to the value specified with LE.

    *)
  7. g_e : comparator_value option;
    (*

    The greater than or equal to operator. The Evaluation results will have FilterVariable values that are greater than or equal to the value specified with GE.

    *)
  8. l_t : comparator_value option;
    (*

    The less than operator. The Evaluation results will have FilterVariable values that are less than the value specified with LT.

    *)
  9. g_t : comparator_value option;
    (*

    The greater than operator. The Evaluation results will have FilterVariable values that are greater than the value specified with GT.

    *)
  10. e_q : comparator_value option;
    (*

    The equal to operator. The Evaluation results will have FilterVariable values that exactly match the value specified with EQ.

    *)
  11. filter_variable : evaluation_filter_variable option;
    (*

    Use one of the following variable to filter a list of Evaluation objects:

    • CreatedAt - Sets the search criteria to the Evaluation creation date.
    • Status - Sets the search criteria to the Evaluation status.
    • Name - Sets the search criteria to the contents of Evaluation Name.
    • IAMUser - Sets the search criteria to the user account that invoked an Evaluation.
    • MLModelId - Sets the search criteria to the MLModel that was evaluated.
    • DataSourceId - Sets the search criteria to the DataSource used in Evaluation.
    • DataUri - Sets the search criteria to the data file(s) used in Evaluation. The URL can identify either a file or an Amazon Simple Storage Solution (Amazon S3) bucket or directory.
    *)
}
type nonrec data_source = {
  1. started_at : epoch_time option;
  2. finished_at : epoch_time option;
  3. compute_time : long_type option;
  4. compute_statistics : compute_statistics option;
    (*

    The parameter is true if statistics need to be generated from the observation data.

    *)
  5. role_ar_n : role_ar_n option;
  6. rds_metadata : rds_metadata option;
  7. redshift_metadata : redshift_metadata option;
  8. message : message option;
    (*

    A description of the most recent details about creating the DataSource.

    *)
  9. status : entity_status option;
    (*

    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.
    *)
  10. name : entity_name option;
    (*

    A user-supplied name or description of the DataSource.

    *)
  11. number_of_files : long_type option;
    (*

    The number of data files referenced by the DataSource.

    *)
  12. data_size_in_bytes : long_type option;
    (*

    The total number of observations contained in the data files that the DataSource references.

    *)
  13. last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to the BatchPrediction. The time is expressed in epoch time.

    *)
  14. created_at : epoch_time option;
    (*

    The time that the DataSource was created. The time is expressed in epoch time.

    *)
  15. created_by_iam_user : aws_user_arn option;
    (*

    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.

    *)
  16. data_rearrangement : data_rearrangement option;
    (*

    A JSON string that represents the splitting and rearrangement requirement used when this DataSource was created.

    *)
  17. data_location_s3 : s3_url option;
    (*

    The location and name of the data in Amazon Simple Storage Service (Amazon S3) that is used by a DataSource.

    *)
  18. data_source_id : entity_id option;
    (*

    The ID that is assigned to the DataSource during creation.

    *)
}

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.

type nonrec data_sources = data_source list
type nonrec describe_data_sources_output = {
  1. next_token : string_type option;
    (*

    An ID of the next page in the paginated results that indicates at least one more page follows.

    *)
  2. results : data_sources option;
    (*

    A list of DataSource that meet the search criteria.

    *)
}

Represents the query results from a DescribeDataSources operation. The content is essentially a list of DataSource.

type nonrec data_source_filter_variable =
  1. | IAM_USER
  2. | DATA_URI
  3. | NAME
  4. | STATUS
  5. | LAST_UPDATED_AT
  6. | CREATED_AT

A list of the variables to use in searching or filtering DataSource.

  • CreatedAt - Sets the search criteria to DataSource creation date.
  • Status - Sets the search criteria to DataSource status.
  • Name - Sets the search criteria to the contents of DataSource Name.
  • DataUri - Sets the search criteria to the URI of data files used to create the DataSource. 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 the DataSource creation.

Note: The variable names should match the variable names in the DataSource.

type nonrec describe_data_sources_input = {
  1. limit : page_limit option;
    (*

    The maximum number of DataSource to include in the result.

    *)
  2. next_token : string_type option;
    (*

    The ID of the page in the paginated results.

    *)
  3. sort_order : sort_order option;
    (*

    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.

    *)
  4. prefix : comparator_value option;
    (*

    A string that is found at the beginning of a variable, such as Name or Id.

    For example, a DataSource could have the Name 2014-09-09-HolidayGiftMailer. To search for this DataSource, select Name for the FilterVariable and any of the following strings for the Prefix:

    • 2014-09
    • 2014-09-09
    • 2014-09-09-Holiday
    *)
  5. n_e : comparator_value option;
    (*

    The not equal to operator. The DataSource results will have FilterVariable values not equal to the value specified with NE.

    *)
  6. l_e : comparator_value option;
    (*

    The less than or equal to operator. The DataSource results will have FilterVariable values that are less than or equal to the value specified with LE.

    *)
  7. g_e : comparator_value option;
    (*

    The greater than or equal to operator. The DataSource results will have FilterVariable values that are greater than or equal to the value specified with GE.

    *)
  8. l_t : comparator_value option;
    (*

    The less than operator. The DataSource results will have FilterVariable values that are less than the value specified with LT.

    *)
  9. g_t : comparator_value option;
    (*

    The greater than operator. The DataSource results will have FilterVariable values that are greater than the value specified with GT.

    *)
  10. e_q : comparator_value option;
    (*

    The equal to operator. The DataSource results will have FilterVariable values that exactly match the value specified with EQ.

    *)
  11. filter_variable : data_source_filter_variable option;
    (*

    Use one of the following variables to filter a list of DataSource:

    • CreatedAt - Sets the search criteria to DataSource creation dates.
    • Status - Sets the search criteria to DataSource statuses.
    • Name - Sets the search criteria to the contents of DataSource Name.
    • DataUri - Sets the search criteria to the URI of data files used to create the DataSource. 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 the DataSource creation.
    *)
}
type nonrec batch_prediction = {
  1. invalid_record_count : long_type option;
  2. total_record_count : long_type option;
  3. started_at : epoch_time option;
  4. finished_at : epoch_time option;
  5. compute_time : long_type option;
  6. message : message option;
    (*

    A description of the most recent details about processing the batch prediction request.

    *)
  7. output_uri : s3_url option;
    (*

    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 the outputURI field: ':', '//', '/./', '/../'.

    *)
  8. status : entity_status option;
    (*

    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 - The BatchPrediction is marked as deleted. It is not usable.
    *)
  9. name : entity_name option;
    (*

    A user-supplied name or description of the BatchPrediction.

    *)
  10. last_updated_at : epoch_time option;
    (*

    The time of the most recent edit to the BatchPrediction. The time is expressed in epoch time.

    *)
  11. created_at : epoch_time option;
    (*

    The time that the BatchPrediction was created. The time is expressed in epoch time.

    *)
  12. created_by_iam_user : aws_user_arn option;
    (*

    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.

    *)
  13. input_data_location_s3 : s3_url option;
    (*

    The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).

    *)
  14. batch_prediction_data_source_id : entity_id option;
    (*

    The ID of the DataSource that points to the group of observations to predict.

    *)
  15. ml_model_id : entity_id option;
    (*

    The ID of the MLModel that generated predictions for the BatchPrediction request.

    *)
  16. batch_prediction_id : entity_id option;
    (*

    The ID assigned to the BatchPrediction at creation. This value should be identical to the value of the BatchPredictionID in the request.

    *)
}

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.

type nonrec batch_predictions = batch_prediction list
type nonrec describe_batch_predictions_output = {
  1. next_token : string_type option;
    (*

    The ID of the next page in the paginated results that indicates at least one more page follows.

    *)
  2. results : batch_predictions option;
    (*

    A list of BatchPrediction objects that meet the search criteria.

    *)
}

Represents the output of a DescribeBatchPredictions operation. The content is essentially a list of BatchPredictions.

type nonrec batch_prediction_filter_variable =
  1. | DATA_URI
  2. | DATASOURCE_ID
  3. | ML_MODEL_ID
  4. | IAM_USER
  5. | NAME
  6. | STATUS
  7. | LAST_UPDATED_AT
  8. | CREATED_AT

A list of the variables to use in searching or filtering BatchPrediction.

  • CreatedAt - Sets the search criteria to BatchPrediction creation date.
  • Status - Sets the search criteria to BatchPrediction status.
  • Name - Sets the search criteria to the contents of BatchPrediction Name.
  • IAMUser - Sets the search criteria to the user account that invoked the BatchPrediction creation.
  • MLModelId - Sets the search criteria to the MLModel used in the BatchPrediction.
  • DataSourceId - Sets the search criteria to the DataSource used in the BatchPrediction.
  • DataURI - Sets the search criteria to the data file(s) used in the BatchPrediction. The URL can identify either a file or an Amazon Simple Storage Service (Amazon S3) bucket or directory.
type nonrec describe_batch_predictions_input = {
  1. limit : page_limit option;
    (*

    The number of pages of information to include in the result. The range of acceptable values is 1 through 100. The default value is 100.

    *)
  2. next_token : string_type option;
    (*

    An ID of the page in the paginated results.

    *)
  3. sort_order : sort_order option;
    (*

    A two-value parameter that determines the sequence of the resulting list of MLModels.

    • 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.

    *)
  4. prefix : comparator_value option;
    (*

    A string that is found at the beginning of a variable, such as Name or Id.

    For example, a Batch Prediction operation could have the Name 2014-09-09-HolidayGiftMailer. To search for this BatchPrediction, select Name for the FilterVariable and any of the following strings for the Prefix:

    • 2014-09
    • 2014-09-09
    • 2014-09-09-Holiday
    *)
  5. n_e : comparator_value option;
    (*

    The not equal to operator. The BatchPrediction results will have FilterVariable values not equal to the value specified with NE.

    *)
  6. l_e : comparator_value option;
    (*

    The less than or equal to operator. The BatchPrediction results will have FilterVariable values that are less than or equal to the value specified with LE.

    *)
  7. g_e : comparator_value option;
    (*

    The greater than or equal to operator. The BatchPrediction results will have FilterVariable values that are greater than or equal to the value specified with GE.

    *)
  8. l_t : comparator_value option;
    (*

    The less than operator. The BatchPrediction results will have FilterVariable values that are less than the value specified with LT.

    *)
  9. g_t : comparator_value option;
    (*

    The greater than operator. The BatchPrediction results will have FilterVariable values that are greater than the value specified with GT.

    *)
  10. e_q : comparator_value option;
    (*

    The equal to operator. The BatchPrediction results will have FilterVariable values that exactly match the value specified with EQ.

    *)
  11. filter_variable : batch_prediction_filter_variable option;
    (*

    Use one of the following variables to filter a list of BatchPrediction:

    • CreatedAt - Sets the search criteria to the BatchPrediction creation date.
    • Status - Sets the search criteria to the BatchPrediction status.
    • Name - Sets the search criteria to the contents of the BatchPrediction Name.
    • IAMUser - Sets the search criteria to the user account that invoked the BatchPrediction creation.
    • MLModelId - Sets the search criteria to the MLModel used in the BatchPrediction.
    • DataSourceId - Sets the search criteria to the DataSource used in the BatchPrediction.
    • DataURI - Sets the search criteria to the data file(s) used in the BatchPrediction. The URL can identify either a file or an Amazon Simple Storage Solution (Amazon S3) bucket or directory.
    *)
}
type nonrec delete_tags_output = {
  1. resource_type : taggable_resource_type option;
    (*

    The type of the ML object from which tags were deleted.

    *)
  2. resource_id : entity_id option;
    (*

    The ID of the ML object from which tags were deleted.

    *)
}

Amazon ML returns the following elements.

type nonrec delete_tags_input = {
  1. resource_type : taggable_resource_type;
    (*

    The type of the tagged ML object.

    *)
  2. resource_id : entity_id;
    (*

    The ID of the tagged ML object. For example, exampleModelId.

    *)
  3. tag_keys : tag_key_list;
    (*

    One or more tags to delete.

    *)
}
type nonrec delete_realtime_endpoint_output = {
  1. realtime_endpoint_info : realtime_endpoint_info option;
    (*

    The endpoint information of the MLModel

    *)
  2. ml_model_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the MLModel. This value should be identical to the value of the MLModelId in the request.

    *)
}

Represents the output of an DeleteRealtimeEndpoint operation.

The result contains the MLModelId and the endpoint information for the MLModel.

type nonrec delete_realtime_endpoint_input = {
  1. ml_model_id : entity_id;
    (*

    The ID assigned to the MLModel during creation.

    *)
}
type nonrec delete_ml_model_output = {
  1. ml_model_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the MLModel. This value should be identical to the value of the MLModelID in the request.

    *)
}

Represents the output of a DeleteMLModel operation.

You can use the GetMLModel operation and check the value of the Status parameter to see whether an MLModel is marked as DELETED.

type nonrec delete_ml_model_input = {
  1. ml_model_id : entity_id;
    (*

    A user-supplied ID that uniquely identifies the MLModel.

    *)
}
type nonrec delete_evaluation_output = {
  1. evaluation_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the Evaluation. This value should be identical to the value of the EvaluationId in the request.

    *)
}

Represents the output of a DeleteEvaluation operation. The output indicates that Amazon Machine Learning (Amazon ML) received the request.

You can use the GetEvaluation operation and check the value of the Status parameter to see whether an Evaluation is marked as DELETED.

type nonrec delete_evaluation_input = {
  1. evaluation_id : entity_id;
    (*

    A user-supplied ID that uniquely identifies the Evaluation to delete.

    *)
}
type nonrec delete_data_source_output = {
  1. data_source_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the DataSource. This value should be identical to the value of the DataSourceID in the request.

    *)
}

Represents the output of a DeleteDataSource operation.

type nonrec delete_data_source_input = {
  1. data_source_id : entity_id;
    (*

    A user-supplied ID that uniquely identifies the DataSource.

    *)
}
type nonrec delete_batch_prediction_output = {
  1. batch_prediction_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the BatchPrediction. This value should be identical to the value of the BatchPredictionID in the request.

    *)
}

Represents the output of a DeleteBatchPrediction operation.

You can use the GetBatchPrediction operation and check the value of the Status parameter to see whether a BatchPrediction is marked as DELETED.

type nonrec delete_batch_prediction_input = {
  1. batch_prediction_id : entity_id;
    (*

    A user-supplied ID that uniquely identifies the BatchPrediction.

    *)
}
type nonrec create_realtime_endpoint_output = {
  1. realtime_endpoint_info : realtime_endpoint_info option;
    (*

    The endpoint information of the MLModel

    *)
  2. ml_model_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the MLModel. This value should be identical to the value of the MLModelId in the request.

    *)
}

Represents the output of an CreateRealtimeEndpoint operation.

The result contains the MLModelId and the endpoint information for the MLModel.

Note: The endpoint information includes the URI of the MLModel; that is, the location to send online prediction requests for the specified MLModel.

type nonrec create_realtime_endpoint_input = {
  1. ml_model_id : entity_id;
    (*

    The ID assigned to the MLModel during creation.

    *)
}
type nonrec create_ml_model_output = {
  1. ml_model_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the MLModel. This value should be identical to the value of the MLModelId in the request.

    *)
}

Represents the output of a CreateMLModel operation, and is an acknowledgement that Amazon ML received the request.

The CreateMLModel operation is asynchronous. You can poll for status updates by using the GetMLModel operation and checking the Status parameter.

type nonrec create_ml_model_input = {
  1. recipe_uri : s3_url option;
    (*

    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.

    *)
  2. recipe : recipe option;
    (*

    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.

    *)
  3. training_data_source_id : entity_id;
    (*

    The DataSource that points to the training data.

    *)
  4. parameters : training_parameters option;
    (*

    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 to 2147483648. The default value is 33554432.

    • sgd.maxPasses - The number of times that the training process traverses the observations to build the MLModel. The value is an integer that ranges from 1 to 10000. The default value is 10.
    • 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 are auto and none. The default value is none. 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 as 1.0E-08.

      The value is a double that ranges from 0 to MAX_DOUBLE. The default is to not use L1 normalization. This parameter can't be used when L2 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 as 1.0E-08.

      The value is a double that ranges from 0 to MAX_DOUBLE. The default is to not use L2 normalization. This parameter can't be used when L1 is specified. Use this parameter sparingly.

    *)
  5. ml_model_type : ml_model_type;
    (*

    The category of supervised learning that this MLModel will address. Choose from the following types:

    • Choose REGRESSION if the MLModel will be used to predict a numeric value.
    • Choose BINARY if the MLModel result has two possible values.
    • Choose MULTICLASS if the MLModel result has a limited number of values.

    For more information, see the Amazon Machine Learning Developer Guide.

    *)
  6. ml_model_name : entity_name option;
    (*

    A user-supplied name or description of the MLModel.

    *)
  7. ml_model_id : entity_id;
    (*

    A user-supplied ID that uniquely identifies the MLModel.

    *)
}
type nonrec create_evaluation_output = {
  1. evaluation_id : entity_id option;
    (*

    The user-supplied ID that uniquely identifies the Evaluation. This value should be identical to the value of the EvaluationId in the request.

    *)
}

Represents the output of a CreateEvaluation operation, and is an acknowledgement that Amazon ML received the request.

CreateEvaluation operation is asynchronous. You can poll for status updates by using the GetEvcaluation operation and checking the Status parameter.

type nonrec create_evaluation_input = {
  1. evaluation_data_source_id : entity_id;
    (*

    The ID of the DataSource for the evaluation. The schema of the DataSource must match the schema used to create the MLModel.

    *)
  2. ml_model_id : entity_id;
    (*

    The ID of the MLModel to evaluate.

    The schema used in creating the MLModel must match the schema of the DataSource used in the Evaluation.

    *)
  3. evaluation_name : entity_name option;
    (*

    A user-supplied name or description of the Evaluation.

    *)
  4. evaluation_id : entity_id;
    (*

    A user-supplied ID that uniquely identifies the Evaluation.

    *)
}
type nonrec create_data_source_from_s3_output = {
  1. data_source_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the DataSource. This value should be identical to the value of the DataSourceID in the request.

    *)
}

Represents the output of a CreateDataSourceFromS3 operation, and is an acknowledgement that Amazon ML received the request.

The CreateDataSourceFromS3 operation is asynchronous. You can poll for updates by using the GetBatchPrediction operation and checking the Status parameter.

type nonrec create_data_source_from_s3_input = {
  1. compute_statistics : compute_statistics option;
    (*

    The compute statistics for a DataSource. The statistics are generated from the observation data referenced by a DataSource. Amazon ML uses the statistics internally during MLModel training. This parameter must be set to true if the DataSource needs to be used for MLModel training.

    *)
  2. data_spec : s3_data_spec;
    (*

    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}}"

    *)
  3. data_source_name : entity_name option;
    (*

    A user-supplied name or description of the DataSource.

    *)
  4. data_source_id : entity_id;
    (*

    A user-supplied identifier that uniquely identifies the DataSource.

    *)
}
type nonrec create_data_source_from_redshift_output = {
  1. data_source_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the datasource. This value should be identical to the value of the DataSourceID in the request.

    *)
}

Represents the output of a CreateDataSourceFromRedshift operation, and is an acknowledgement that Amazon ML received the request.

The CreateDataSourceFromRedshift operation is asynchronous. You can poll for updates by using the GetBatchPrediction operation and checking the Status parameter.

type nonrec create_data_source_from_redshift_input = {
  1. compute_statistics : compute_statistics option;
    (*

    The compute statistics for a DataSource. The statistics are generated from the observation data referenced by a DataSource. Amazon ML uses the statistics internally during MLModel training. This parameter must be set to true if the DataSource needs to be used for MLModel training.

    *)
  2. role_ar_n : role_ar_n;
    (*

    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
    *)
  3. data_spec : redshift_data_spec;
    (*

    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}}"

    *)
  4. data_source_name : entity_name option;
    (*

    A user-supplied name or description of the DataSource.

    *)
  5. data_source_id : entity_id;
    (*

    A user-supplied ID that uniquely identifies the DataSource.

    *)
}
type nonrec create_data_source_from_rds_output = {
  1. data_source_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the datasource. This value should be identical to the value of the DataSourceID in the request.

    *)
}

Represents the output of a CreateDataSourceFromRDS operation, and is an acknowledgement that Amazon ML received the request.

The CreateDataSourceFromRDS> operation is asynchronous. You can poll for updates by using the GetBatchPrediction operation and checking the Status parameter. You can inspect the Message when Status shows up as FAILED. You can also check the progress of the copy operation by going to the DataPipeline console and looking up the pipeline using the pipelineId from the describe call.

type nonrec create_data_source_from_rds_input = {
  1. compute_statistics : compute_statistics option;
    (*

    The compute statistics for a DataSource. The statistics are generated from the observation data referenced by a DataSource. Amazon ML uses the statistics internally during MLModel training. This parameter must be set to true if the DataSource needs to be used for MLModel training.

    *)
  2. role_ar_n : role_ar_n;
    (*

    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.

    *)
  3. rds_data : rds_data_spec;
    (*

    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}}"

    *)
  4. data_source_name : entity_name option;
    (*

    A user-supplied name or description of the DataSource.

    *)
  5. data_source_id : entity_id;
    (*

    A user-supplied ID that uniquely identifies the DataSource. Typically, an Amazon Resource Number (ARN) becomes the ID for a DataSource.

    *)
}
type nonrec create_batch_prediction_output = {
  1. batch_prediction_id : entity_id option;
    (*

    A user-supplied ID that uniquely identifies the BatchPrediction. This value is identical to the value of the BatchPredictionId in the request.

    *)
}

Represents the output of a CreateBatchPrediction operation, and is an acknowledgement that Amazon ML received the request.

The CreateBatchPrediction operation is asynchronous. You can poll for status updates by using the >GetBatchPrediction operation and checking the Status parameter of the result.

type nonrec create_batch_prediction_input = {
  1. output_uri : s3_url;
    (*

    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 the outputURI 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.

    *)
  2. batch_prediction_data_source_id : entity_id;
    (*

    The ID of the DataSource that points to the group of observations to predict.

    *)
  3. ml_model_id : entity_id;
    (*

    The ID of the MLModel that will generate predictions for the group of observations.

    *)
  4. batch_prediction_name : entity_name option;
    (*

    A user-supplied name or description of the BatchPrediction. BatchPredictionName can only use the UTF-8 character set.

    *)
  5. batch_prediction_id : entity_id;
    (*

    A user-supplied ID that uniquely identifies the BatchPrediction.

    *)
}
type nonrec add_tags_output = {
  1. resource_type : taggable_resource_type option;
    (*

    The type of the ML object that was tagged.

    *)
  2. resource_id : entity_id option;
    (*

    The ID of the ML object that was tagged.

    *)
}

Amazon ML returns the following elements.

type nonrec add_tags_input = {
  1. resource_type : taggable_resource_type;
    (*

    The type of the ML object to tag.

    *)
  2. resource_id : entity_id;
    (*

    The ID of the ML object to tag. For example, exampleModelId.

    *)
  3. tags : tag_list;
    (*

    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.

    *)
}