capo-machine-learning 0.3.0__tar.gz → 0.4.0__tar.gz

{capo_machine_learning-0.3.0/src/capo_machine_learning.egg-info → capo_machine_learning-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: capo-machine-learning
-Version: 0.3.0
+Version: 0.4.0
 Summary: Python SDK for AWS Machine Learning.
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "capo-machine-learning"
-version = "0.3.0"
+version = "0.4.0"
 description = "Python SDK for AWS Machine Learning."
 readme = "README.md"
 requires-python = ">=3.10"

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/_services/async_machine_learning.py

@@ -276,14 +276,14 @@ class AsyncMachineLearningClient:
             "capo_machine_learning.types.entity_name.EntityName"
         ] = None,
     ) -> "capo_machine_learning.types.create_batch_prediction_output.CreateBatchPredictionOutput":
-        r"""<p>Generates predictions for a group of observations. The observations to process exist in one or more data files referenced by a <code>DataSource</code>. This operation creates a new <code>BatchPrediction</code>, and uses an <code>MLModel</code> and the data files referenced by the <code>DataSource</code> as information sources. </p> <p> <code>CreateBatchPrediction</code> is an asynchronous operation. In response to <code>CreateBatchPrediction</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>BatchPrediction</code> status to <code>PENDING</code>. After the <code>BatchPrediction</code> completes, Amazon ML sets the status to <code>COMPLETED</code>. </p> <p>You can poll for status updates by using the <a>GetBatchPrediction</a> operation and checking the <code>Status</code> parameter of the result. After the <code>COMPLETED</code> status appears, the results are available in the location specified by the <code>OutputUri</code> parameter.</p>
+        """<p>Generates predictions for a group of observations. The observations to process exist in one or more data files referenced by a <code>DataSource</code>. This operation creates a new <code>BatchPrediction</code>, and uses an <code>MLModel</code> and the data files referenced by the <code>DataSource</code> as information sources. </p> <p> <code>CreateBatchPrediction</code> is an asynchronous operation. In response to <code>CreateBatchPrediction</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>BatchPrediction</code> status to <code>PENDING</code>. After the <code>BatchPrediction</code> completes, Amazon ML sets the status to <code>COMPLETED</code>. </p> <p>You can poll for status updates by using the <a>GetBatchPrediction</a> operation and checking the <code>Status</code> parameter of the result. After the <code>COMPLETED</code> status appears, the results are available in the location specified by the <code>OutputUri</code> parameter.</p>
 
         Args:
             batch_prediction_id: <p>A user-supplied ID that uniquely identifies the <code>BatchPrediction</code>.</p>
             batch_prediction_name: <p>A user-supplied name or description of the <code>BatchPrediction</code>. <code>BatchPredictionName</code> can only use the UTF-8 character set.</p>
             ml_model_id: <p>The ID of the <code>MLModel</code> that will generate predictions for the group of observations. </p>
             batch_prediction_data_source_id: <p>The ID of the <code>DataSource</code> that points to the group of observations to predict.</p>
-            output_uri: <p>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 <code>s3 key</code> portion of the <code>outputURI</code> field: ':', '//', '/./', '/../'.</p> <p>Amazon ML needs permissions to store and retrieve the logs on your behalf. For information about how to set permissions, see the <a href=\"https://docs.aws.amazon.com/machine-learning/latest/dg\">Amazon Machine Learning Developer Guide</a>.</p>
+            output_uri: <p>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 <code>s3 key</code> portion of the <code>outputURI</code> field: ':', '//', '/./', '/../'.</p> <p>Amazon ML needs permissions to store and retrieve the logs on your behalf. For information about how to set permissions, see the <a href="https://docs.aws.amazon.com/machine-learning/latest/dg">Amazon Machine Learning Developer Guide</a>.</p>
 
         Raises:
             capo_machine_learning.errors.idempotent_parameter_mismatch_exception.IdempotentParameterMismatchException: <p>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.</p>
@@ -339,12 +339,12 @@ class AsyncMachineLearningClient:
             "capo_machine_learning.types.compute_statistics.ComputeStatistics"
         ] = None,
     ) -> "capo_machine_learning.types.create_data_source_from_rds_output.CreateDataSourceFromRDSOutput":
-        r"""<p>Creates a <code>DataSource</code> object from an <a href=\"http://aws.amazon.com/rds/\"> Amazon Relational Database Service</a> (Amazon RDS). A <code>DataSource</code> references data that can be used to perform <code>CreateMLModel</code>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations.</p> <p> <code>CreateDataSourceFromRDS</code> is an asynchronous operation. In response to <code>CreateDataSourceFromRDS</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>DataSource</code> status to <code>PENDING</code>. After the <code>DataSource</code> is created and ready for use, Amazon ML sets the <code>Status</code> parameter to <code>COMPLETED</code>. <code>DataSource</code> in the <code>COMPLETED</code> or <code>PENDING</code> state can be used only to perform <code>>CreateMLModel</code>>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations. </p> <p> If Amazon ML cannot accept the input source, it sets the <code>Status</code> parameter to <code>FAILED</code> and includes an error message in the <code>Message</code> attribute of the <code>GetDataSource</code> operation response. </p>
+        r"""<p>Creates a <code>DataSource</code> object from an <a href="http://aws.amazon.com/rds/"> Amazon Relational Database Service</a> (Amazon RDS). A <code>DataSource</code> references data that can be used to perform <code>CreateMLModel</code>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations.</p> <p> <code>CreateDataSourceFromRDS</code> is an asynchronous operation. In response to <code>CreateDataSourceFromRDS</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>DataSource</code> status to <code>PENDING</code>. After the <code>DataSource</code> is created and ready for use, Amazon ML sets the <code>Status</code> parameter to <code>COMPLETED</code>. <code>DataSource</code> in the <code>COMPLETED</code> or <code>PENDING</code> state can be used only to perform <code>>CreateMLModel</code>>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations. </p> <p> If Amazon ML cannot accept the input source, it sets the <code>Status</code> parameter to <code>FAILED</code> and includes an error message in the <code>Message</code> attribute of the <code>GetDataSource</code> operation response. </p>
 
         Args:
             data_source_id: <p>A user-supplied ID that uniquely identifies the <code>DataSource</code>. Typically, an Amazon Resource Number (ARN) becomes the ID for a <code>DataSource</code>.</p>
             data_source_name: <p>A user-supplied name or description of the <code>DataSource</code>.</p>
-            rds_data: <p>The data specification of an Amazon RDS <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon RDS database.</p> </li> <li> <p> <code>InstanceIdentifier </code> - A unique identifier for the Amazon RDS database instance.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon RDS database.</p> </li> <li> <p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p> </li> <li> <p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p> </li> <li> <p>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 [<code>SubnetId</code>, <code>SecurityGroupIds</code>] pair for a VPC-based RDS DB instance.</p> </li> <li> <p>SelectSqlQuery - A query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon S3 location for staging Amazon RDS data. The data retrieved from Amazon RDS using <code>SelectSqlQuery</code> is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> \"{\\"splitting\\":{\\"percentBegin\\":10,\\"percentEnd\\":60}}\"</code> </p> </li> </ul>
+            rds_data: <p>The data specification of an Amazon RDS <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon RDS database.</p> </li> <li> <p> <code>InstanceIdentifier </code> - A unique identifier for the Amazon RDS database instance.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon RDS database.</p> </li> <li> <p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p> </li> <li> <p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p> </li> <li> <p>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 [<code>SubnetId</code>, <code>SecurityGroupIds</code>] pair for a VPC-based RDS DB instance.</p> </li> <li> <p>SelectSqlQuery - A query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon S3 location for staging Amazon RDS data. The data retrieved from Amazon RDS using <code>SelectSqlQuery</code> is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>
             role_arn: <p>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 <code>SelectSqlQuery</code> query from Amazon RDS to Amazon S3.</p> <p></p>
             compute_statistics: <p>The compute statistics for a <code>DataSource</code>. The statistics are generated from the observation data referenced by a <code>DataSource</code>. Amazon ML uses the statistics internally during <code>MLModel</code> training. This parameter must be set to <code>true</code> if the <code></code>DataSource<code></code> needs to be used for <code>MLModel</code> training. </p>
 
@@ -408,7 +408,7 @@ class AsyncMachineLearningClient:
         Args:
             data_source_id: <p>A user-supplied ID that uniquely identifies the <code>DataSource</code>.</p>
             data_source_name: <p>A user-supplied name or description of the <code>DataSource</code>. </p>
-            data_spec: <p>The data specification of an Amazon Redshift <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon Redshift database.</p> </li> <li> <p> <code> ClusterIdentifier</code> - The unique ID for the Amazon Redshift cluster.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - The AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon Redshift database.</p> </li> <li> <p>SelectSqlQuery - The query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon Simple Storage Service (Amazon S3) location for staging Amazon Redshift data. The data retrieved from Amazon Redshift using the <code>SelectSqlQuery</code> query is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>DataSource</code>.</p> <p> Sample - <code> \"{\\"splitting\\":{\\"percentBegin\\":10,\\"percentEnd\\":60}}\"</code> </p> </li> </ul>
+            data_spec: <p>The data specification of an Amazon Redshift <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon Redshift database.</p> </li> <li> <p> <code> ClusterIdentifier</code> - The unique ID for the Amazon Redshift cluster.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - The AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon Redshift database.</p> </li> <li> <p>SelectSqlQuery - The query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon Simple Storage Service (Amazon S3) location for staging Amazon Redshift data. The data retrieved from Amazon Redshift using the <code>SelectSqlQuery</code> query is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>DataSource</code>.</p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>
             role_arn: <p>A fully specified role Amazon Resource Name (ARN). Amazon ML assumes the role on behalf of the user to create the following:</p> <ul> <li> <p>A security group to allow Amazon ML to execute the <code>SelectSqlQuery</code> query on an Amazon Redshift cluster</p> </li> <li> <p>An Amazon S3 bucket policy to grant Amazon ML read/write permissions on the <code>S3StagingLocation</code> </p> </li> </ul>
             compute_statistics: <p>The compute statistics for a <code>DataSource</code>. The statistics are generated from the observation data referenced by a <code>DataSource</code>. Amazon ML uses the statistics internally during <code>MLModel</code> training. This parameter must be set to <code>true</code> if the <code>DataSource</code> needs to be used for <code>MLModel</code> training.</p>
 
@@ -471,7 +471,7 @@ class AsyncMachineLearningClient:
         Args:
             data_source_id: <p>A user-supplied identifier that uniquely identifies the <code>DataSource</code>. </p>
             data_source_name: <p>A user-supplied name or description of the <code>DataSource</code>. </p>
-            data_spec: <p>The data specification of a <code>DataSource</code>:</p> <ul> <li> <p>DataLocationS3 - The Amazon S3 location of the observation data.</p> </li> <li> <p>DataSchemaLocationS3 - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> \"{\\"splitting\\":{\\"percentBegin\\":10,\\"percentEnd\\":60}}\"</code> </p> </li> </ul>
+            data_spec: <p>The data specification of a <code>DataSource</code>:</p> <ul> <li> <p>DataLocationS3 - The Amazon S3 location of the observation data.</p> </li> <li> <p>DataSchemaLocationS3 - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>
             compute_statistics: <p>The compute statistics for a <code>DataSource</code>. The statistics are generated from the observation data referenced by a <code>DataSource</code>. Amazon ML uses the statistics internally during <code>MLModel</code> training. This parameter must be set to <code>true</code> if the <code></code>DataSource<code></code> needs to be used for <code>MLModel</code> training.</p>
 
         Raises:
@@ -588,12 +588,12 @@ class AsyncMachineLearningClient:
         recipe: Optional["capo_machine_learning.types.recipe.Recipe"] = None,
         recipe_uri: Optional["capo_machine_learning.types.s3_url.S3Url"] = None,
     ) -> "capo_machine_learning.types.create_ml_model_output.CreateMLModelOutput":
-        r"""<p>Creates a new <code>MLModel</code> using the <code>DataSource</code> and the recipe as information sources. </p> <p>An <code>MLModel</code> is nearly immutable. Users can update only the <code>MLModelName</code> and the <code>ScoreThreshold</code> in an <code>MLModel</code> without creating a new <code>MLModel</code>. </p> <p> <code>CreateMLModel</code> is an asynchronous operation. In response to <code>CreateMLModel</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>MLModel</code> status to <code>PENDING</code>. After the <code>MLModel</code> has been created and ready is for use, Amazon ML sets the status to <code>COMPLETED</code>. </p> <p>You can use the <code>GetMLModel</code> operation to check the progress of the <code>MLModel</code> during the creation operation.</p> <p> <code>CreateMLModel</code> requires a <code>DataSource</code> with computed statistics, which can be created by setting <code>ComputeStatistics</code> to <code>true</code> in <code>CreateDataSourceFromRDS</code>, <code>CreateDataSourceFromS3</code>, or <code>CreateDataSourceFromRedshift</code> operations. </p>
+        """<p>Creates a new <code>MLModel</code> using the <code>DataSource</code> and the recipe as information sources. </p> <p>An <code>MLModel</code> is nearly immutable. Users can update only the <code>MLModelName</code> and the <code>ScoreThreshold</code> in an <code>MLModel</code> without creating a new <code>MLModel</code>. </p> <p> <code>CreateMLModel</code> is an asynchronous operation. In response to <code>CreateMLModel</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>MLModel</code> status to <code>PENDING</code>. After the <code>MLModel</code> has been created and ready is for use, Amazon ML sets the status to <code>COMPLETED</code>. </p> <p>You can use the <code>GetMLModel</code> operation to check the progress of the <code>MLModel</code> during the creation operation.</p> <p> <code>CreateMLModel</code> requires a <code>DataSource</code> with computed statistics, which can be created by setting <code>ComputeStatistics</code> to <code>true</code> in <code>CreateDataSourceFromRDS</code>, <code>CreateDataSourceFromS3</code>, or <code>CreateDataSourceFromRedshift</code> operations. </p>
 
         Args:
             ml_model_id: <p>A user-supplied ID that uniquely identifies the <code>MLModel</code>.</p>
             ml_model_name: <p>A user-supplied name or description of the <code>MLModel</code>.</p>
-            ml_model_type: <p>The category of supervised learning that this <code>MLModel</code> will address. Choose from the following types:</p> <ul> <li> <p>Choose <code>REGRESSION</code> if the <code>MLModel</code> will be used to predict a numeric value.</p> </li> <li> <p>Choose <code>BINARY</code> if the <code>MLModel</code> result has two possible values.</p> </li> <li> <p>Choose <code>MULTICLASS</code> if the <code>MLModel</code> result has a limited number of values.</p> </li> </ul> <p> For more information, see the <a href=\"https://docs.aws.amazon.com/machine-learning/latest/dg\">Amazon Machine Learning Developer Guide</a>.</p>
+            ml_model_type: <p>The category of supervised learning that this <code>MLModel</code> will address. Choose from the following types:</p> <ul> <li> <p>Choose <code>REGRESSION</code> if the <code>MLModel</code> will be used to predict a numeric value.</p> </li> <li> <p>Choose <code>BINARY</code> if the <code>MLModel</code> result has two possible values.</p> </li> <li> <p>Choose <code>MULTICLASS</code> if the <code>MLModel</code> result has a limited number of values.</p> </li> </ul> <p> For more information, see the <a href="https://docs.aws.amazon.com/machine-learning/latest/dg">Amazon Machine Learning Developer Guide</a>.</p>
             parameters: <p>A list of the training parameters in the <code>MLModel</code>. The list is implemented as a map of key-value pairs.</p> <p>The following is the current set of training parameters:</p> <ul> <li> <p> <code>sgd.maxMLModelSizeInBytes</code> - The maximum allowed size of the model. Depending on the input data, the size of the model might affect its performance.</p> <p> The value is an integer that ranges from <code>100000</code> to <code>2147483648</code>. The default value is <code>33554432</code>.</p> </li> <li> <p> <code>sgd.maxPasses</code> - The number of times that the training process traverses the observations to build the <code>MLModel</code>. The value is an integer that ranges from <code>1</code> to <code>10000</code>. The default value is <code>10</code>.</p> </li> <li> <p> <code>sgd.shuffleType</code> - 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 <code>auto</code> and <code>none</code>. The default value is <code>none</code>. We strongly recommend that you shuffle your data.</p> </li> <li> <p> <code>sgd.l1RegularizationAmount</code> - 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 <code>1.0E-08</code>.</p> <p>The value is a double that ranges from <code>0</code> to <code>MAX_DOUBLE</code>. The default is to not use L1 normalization. This parameter can't be used when <code>L2</code> is specified. Use this parameter sparingly.</p> </li> <li> <p> <code>sgd.l2RegularizationAmount</code> - 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 <code>1.0E-08</code>.</p> <p>The value is a double that ranges from <code>0</code> to <code>MAX_DOUBLE</code>. The default is to not use L2 normalization. This parameter can't be used when <code>L1</code> is specified. Use this parameter sparingly.</p> </li> </ul>
             training_data_source_id: <p>The <code>DataSource</code> that points to the training data.</p>
             recipe: <p>The data recipe for creating the <code>MLModel</code>. You must specify either the recipe or its URI. If you don't specify a recipe or its URI, Amazon ML creates a default.</p>

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/_services/machine_learning.py

@@ -275,14 +275,14 @@ class MachineLearningClient:
             "capo_machine_learning.types.entity_name.EntityName"
         ] = None,
     ) -> "capo_machine_learning.types.create_batch_prediction_output.CreateBatchPredictionOutput":
-        r"""<p>Generates predictions for a group of observations. The observations to process exist in one or more data files referenced by a <code>DataSource</code>. This operation creates a new <code>BatchPrediction</code>, and uses an <code>MLModel</code> and the data files referenced by the <code>DataSource</code> as information sources. </p> <p> <code>CreateBatchPrediction</code> is an asynchronous operation. In response to <code>CreateBatchPrediction</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>BatchPrediction</code> status to <code>PENDING</code>. After the <code>BatchPrediction</code> completes, Amazon ML sets the status to <code>COMPLETED</code>. </p> <p>You can poll for status updates by using the <a>GetBatchPrediction</a> operation and checking the <code>Status</code> parameter of the result. After the <code>COMPLETED</code> status appears, the results are available in the location specified by the <code>OutputUri</code> parameter.</p>
+        """<p>Generates predictions for a group of observations. The observations to process exist in one or more data files referenced by a <code>DataSource</code>. This operation creates a new <code>BatchPrediction</code>, and uses an <code>MLModel</code> and the data files referenced by the <code>DataSource</code> as information sources. </p> <p> <code>CreateBatchPrediction</code> is an asynchronous operation. In response to <code>CreateBatchPrediction</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>BatchPrediction</code> status to <code>PENDING</code>. After the <code>BatchPrediction</code> completes, Amazon ML sets the status to <code>COMPLETED</code>. </p> <p>You can poll for status updates by using the <a>GetBatchPrediction</a> operation and checking the <code>Status</code> parameter of the result. After the <code>COMPLETED</code> status appears, the results are available in the location specified by the <code>OutputUri</code> parameter.</p>
 
         Args:
             batch_prediction_id: <p>A user-supplied ID that uniquely identifies the <code>BatchPrediction</code>.</p>
             batch_prediction_name: <p>A user-supplied name or description of the <code>BatchPrediction</code>. <code>BatchPredictionName</code> can only use the UTF-8 character set.</p>
             ml_model_id: <p>The ID of the <code>MLModel</code> that will generate predictions for the group of observations. </p>
             batch_prediction_data_source_id: <p>The ID of the <code>DataSource</code> that points to the group of observations to predict.</p>
-            output_uri: <p>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 <code>s3 key</code> portion of the <code>outputURI</code> field: ':', '//', '/./', '/../'.</p> <p>Amazon ML needs permissions to store and retrieve the logs on your behalf. For information about how to set permissions, see the <a href=\"https://docs.aws.amazon.com/machine-learning/latest/dg\">Amazon Machine Learning Developer Guide</a>.</p>
+            output_uri: <p>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 <code>s3 key</code> portion of the <code>outputURI</code> field: ':', '//', '/./', '/../'.</p> <p>Amazon ML needs permissions to store and retrieve the logs on your behalf. For information about how to set permissions, see the <a href="https://docs.aws.amazon.com/machine-learning/latest/dg">Amazon Machine Learning Developer Guide</a>.</p>
 
         Raises:
             capo_machine_learning.errors.idempotent_parameter_mismatch_exception.IdempotentParameterMismatchException: <p>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.</p>
@@ -337,12 +337,12 @@ class MachineLearningClient:
             "capo_machine_learning.types.compute_statistics.ComputeStatistics"
         ] = None,
     ) -> "capo_machine_learning.types.create_data_source_from_rds_output.CreateDataSourceFromRDSOutput":
-        r"""<p>Creates a <code>DataSource</code> object from an <a href=\"http://aws.amazon.com/rds/\"> Amazon Relational Database Service</a> (Amazon RDS). A <code>DataSource</code> references data that can be used to perform <code>CreateMLModel</code>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations.</p> <p> <code>CreateDataSourceFromRDS</code> is an asynchronous operation. In response to <code>CreateDataSourceFromRDS</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>DataSource</code> status to <code>PENDING</code>. After the <code>DataSource</code> is created and ready for use, Amazon ML sets the <code>Status</code> parameter to <code>COMPLETED</code>. <code>DataSource</code> in the <code>COMPLETED</code> or <code>PENDING</code> state can be used only to perform <code>>CreateMLModel</code>>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations. </p> <p> If Amazon ML cannot accept the input source, it sets the <code>Status</code> parameter to <code>FAILED</code> and includes an error message in the <code>Message</code> attribute of the <code>GetDataSource</code> operation response. </p>
+        r"""<p>Creates a <code>DataSource</code> object from an <a href="http://aws.amazon.com/rds/"> Amazon Relational Database Service</a> (Amazon RDS). A <code>DataSource</code> references data that can be used to perform <code>CreateMLModel</code>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations.</p> <p> <code>CreateDataSourceFromRDS</code> is an asynchronous operation. In response to <code>CreateDataSourceFromRDS</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>DataSource</code> status to <code>PENDING</code>. After the <code>DataSource</code> is created and ready for use, Amazon ML sets the <code>Status</code> parameter to <code>COMPLETED</code>. <code>DataSource</code> in the <code>COMPLETED</code> or <code>PENDING</code> state can be used only to perform <code>>CreateMLModel</code>>, <code>CreateEvaluation</code>, or <code>CreateBatchPrediction</code> operations. </p> <p> If Amazon ML cannot accept the input source, it sets the <code>Status</code> parameter to <code>FAILED</code> and includes an error message in the <code>Message</code> attribute of the <code>GetDataSource</code> operation response. </p>
 
         Args:
             data_source_id: <p>A user-supplied ID that uniquely identifies the <code>DataSource</code>. Typically, an Amazon Resource Number (ARN) becomes the ID for a <code>DataSource</code>.</p>
             data_source_name: <p>A user-supplied name or description of the <code>DataSource</code>.</p>
-            rds_data: <p>The data specification of an Amazon RDS <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon RDS database.</p> </li> <li> <p> <code>InstanceIdentifier </code> - A unique identifier for the Amazon RDS database instance.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon RDS database.</p> </li> <li> <p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p> </li> <li> <p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p> </li> <li> <p>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 [<code>SubnetId</code>, <code>SecurityGroupIds</code>] pair for a VPC-based RDS DB instance.</p> </li> <li> <p>SelectSqlQuery - A query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon S3 location for staging Amazon RDS data. The data retrieved from Amazon RDS using <code>SelectSqlQuery</code> is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> \"{\\"splitting\\":{\\"percentBegin\\":10,\\"percentEnd\\":60}}\"</code> </p> </li> </ul>
+            rds_data: <p>The data specification of an Amazon RDS <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon RDS database.</p> </li> <li> <p> <code>InstanceIdentifier </code> - A unique identifier for the Amazon RDS database instance.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon RDS database.</p> </li> <li> <p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p> </li> <li> <p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p> </li> <li> <p>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 [<code>SubnetId</code>, <code>SecurityGroupIds</code>] pair for a VPC-based RDS DB instance.</p> </li> <li> <p>SelectSqlQuery - A query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon S3 location for staging Amazon RDS data. The data retrieved from Amazon RDS using <code>SelectSqlQuery</code> is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>
             role_arn: <p>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 <code>SelectSqlQuery</code> query from Amazon RDS to Amazon S3.</p> <p></p>
             compute_statistics: <p>The compute statistics for a <code>DataSource</code>. The statistics are generated from the observation data referenced by a <code>DataSource</code>. Amazon ML uses the statistics internally during <code>MLModel</code> training. This parameter must be set to <code>true</code> if the <code></code>DataSource<code></code> needs to be used for <code>MLModel</code> training. </p>
 
@@ -405,7 +405,7 @@ class MachineLearningClient:
         Args:
             data_source_id: <p>A user-supplied ID that uniquely identifies the <code>DataSource</code>.</p>
             data_source_name: <p>A user-supplied name or description of the <code>DataSource</code>. </p>
-            data_spec: <p>The data specification of an Amazon Redshift <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon Redshift database.</p> </li> <li> <p> <code> ClusterIdentifier</code> - The unique ID for the Amazon Redshift cluster.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - The AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon Redshift database.</p> </li> <li> <p>SelectSqlQuery - The query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon Simple Storage Service (Amazon S3) location for staging Amazon Redshift data. The data retrieved from Amazon Redshift using the <code>SelectSqlQuery</code> query is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>DataSource</code>.</p> <p> Sample - <code> \"{\\"splitting\\":{\\"percentBegin\\":10,\\"percentEnd\\":60}}\"</code> </p> </li> </ul>
+            data_spec: <p>The data specification of an Amazon Redshift <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon Redshift database.</p> </li> <li> <p> <code> ClusterIdentifier</code> - The unique ID for the Amazon Redshift cluster.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - The AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon Redshift database.</p> </li> <li> <p>SelectSqlQuery - The query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon Simple Storage Service (Amazon S3) location for staging Amazon Redshift data. The data retrieved from Amazon Redshift using the <code>SelectSqlQuery</code> query is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>DataSource</code>.</p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>
             role_arn: <p>A fully specified role Amazon Resource Name (ARN). Amazon ML assumes the role on behalf of the user to create the following:</p> <ul> <li> <p>A security group to allow Amazon ML to execute the <code>SelectSqlQuery</code> query on an Amazon Redshift cluster</p> </li> <li> <p>An Amazon S3 bucket policy to grant Amazon ML read/write permissions on the <code>S3StagingLocation</code> </p> </li> </ul>
             compute_statistics: <p>The compute statistics for a <code>DataSource</code>. The statistics are generated from the observation data referenced by a <code>DataSource</code>. Amazon ML uses the statistics internally during <code>MLModel</code> training. This parameter must be set to <code>true</code> if the <code>DataSource</code> needs to be used for <code>MLModel</code> training.</p>
 
@@ -467,7 +467,7 @@ class MachineLearningClient:
         Args:
             data_source_id: <p>A user-supplied identifier that uniquely identifies the <code>DataSource</code>. </p>
             data_source_name: <p>A user-supplied name or description of the <code>DataSource</code>. </p>
-            data_spec: <p>The data specification of a <code>DataSource</code>:</p> <ul> <li> <p>DataLocationS3 - The Amazon S3 location of the observation data.</p> </li> <li> <p>DataSchemaLocationS3 - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> \"{\\"splitting\\":{\\"percentBegin\\":10,\\"percentEnd\\":60}}\"</code> </p> </li> </ul>
+            data_spec: <p>The data specification of a <code>DataSource</code>:</p> <ul> <li> <p>DataLocationS3 - The Amazon S3 location of the observation data.</p> </li> <li> <p>DataSchemaLocationS3 - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>
             compute_statistics: <p>The compute statistics for a <code>DataSource</code>. The statistics are generated from the observation data referenced by a <code>DataSource</code>. Amazon ML uses the statistics internally during <code>MLModel</code> training. This parameter must be set to <code>true</code> if the <code></code>DataSource<code></code> needs to be used for <code>MLModel</code> training.</p>
 
         Raises:
@@ -582,12 +582,12 @@ class MachineLearningClient:
         recipe: Optional["capo_machine_learning.types.recipe.Recipe"] = None,
         recipe_uri: Optional["capo_machine_learning.types.s3_url.S3Url"] = None,
     ) -> "capo_machine_learning.types.create_ml_model_output.CreateMLModelOutput":
-        r"""<p>Creates a new <code>MLModel</code> using the <code>DataSource</code> and the recipe as information sources. </p> <p>An <code>MLModel</code> is nearly immutable. Users can update only the <code>MLModelName</code> and the <code>ScoreThreshold</code> in an <code>MLModel</code> without creating a new <code>MLModel</code>. </p> <p> <code>CreateMLModel</code> is an asynchronous operation. In response to <code>CreateMLModel</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>MLModel</code> status to <code>PENDING</code>. After the <code>MLModel</code> has been created and ready is for use, Amazon ML sets the status to <code>COMPLETED</code>. </p> <p>You can use the <code>GetMLModel</code> operation to check the progress of the <code>MLModel</code> during the creation operation.</p> <p> <code>CreateMLModel</code> requires a <code>DataSource</code> with computed statistics, which can be created by setting <code>ComputeStatistics</code> to <code>true</code> in <code>CreateDataSourceFromRDS</code>, <code>CreateDataSourceFromS3</code>, or <code>CreateDataSourceFromRedshift</code> operations. </p>
+        """<p>Creates a new <code>MLModel</code> using the <code>DataSource</code> and the recipe as information sources. </p> <p>An <code>MLModel</code> is nearly immutable. Users can update only the <code>MLModelName</code> and the <code>ScoreThreshold</code> in an <code>MLModel</code> without creating a new <code>MLModel</code>. </p> <p> <code>CreateMLModel</code> is an asynchronous operation. In response to <code>CreateMLModel</code>, Amazon Machine Learning (Amazon ML) immediately returns and sets the <code>MLModel</code> status to <code>PENDING</code>. After the <code>MLModel</code> has been created and ready is for use, Amazon ML sets the status to <code>COMPLETED</code>. </p> <p>You can use the <code>GetMLModel</code> operation to check the progress of the <code>MLModel</code> during the creation operation.</p> <p> <code>CreateMLModel</code> requires a <code>DataSource</code> with computed statistics, which can be created by setting <code>ComputeStatistics</code> to <code>true</code> in <code>CreateDataSourceFromRDS</code>, <code>CreateDataSourceFromS3</code>, or <code>CreateDataSourceFromRedshift</code> operations. </p>
 
         Args:
             ml_model_id: <p>A user-supplied ID that uniquely identifies the <code>MLModel</code>.</p>
             ml_model_name: <p>A user-supplied name or description of the <code>MLModel</code>.</p>
-            ml_model_type: <p>The category of supervised learning that this <code>MLModel</code> will address. Choose from the following types:</p> <ul> <li> <p>Choose <code>REGRESSION</code> if the <code>MLModel</code> will be used to predict a numeric value.</p> </li> <li> <p>Choose <code>BINARY</code> if the <code>MLModel</code> result has two possible values.</p> </li> <li> <p>Choose <code>MULTICLASS</code> if the <code>MLModel</code> result has a limited number of values.</p> </li> </ul> <p> For more information, see the <a href=\"https://docs.aws.amazon.com/machine-learning/latest/dg\">Amazon Machine Learning Developer Guide</a>.</p>
+            ml_model_type: <p>The category of supervised learning that this <code>MLModel</code> will address. Choose from the following types:</p> <ul> <li> <p>Choose <code>REGRESSION</code> if the <code>MLModel</code> will be used to predict a numeric value.</p> </li> <li> <p>Choose <code>BINARY</code> if the <code>MLModel</code> result has two possible values.</p> </li> <li> <p>Choose <code>MULTICLASS</code> if the <code>MLModel</code> result has a limited number of values.</p> </li> </ul> <p> For more information, see the <a href="https://docs.aws.amazon.com/machine-learning/latest/dg">Amazon Machine Learning Developer Guide</a>.</p>
             parameters: <p>A list of the training parameters in the <code>MLModel</code>. The list is implemented as a map of key-value pairs.</p> <p>The following is the current set of training parameters:</p> <ul> <li> <p> <code>sgd.maxMLModelSizeInBytes</code> - The maximum allowed size of the model. Depending on the input data, the size of the model might affect its performance.</p> <p> The value is an integer that ranges from <code>100000</code> to <code>2147483648</code>. The default value is <code>33554432</code>.</p> </li> <li> <p> <code>sgd.maxPasses</code> - The number of times that the training process traverses the observations to build the <code>MLModel</code>. The value is an integer that ranges from <code>1</code> to <code>10000</code>. The default value is <code>10</code>.</p> </li> <li> <p> <code>sgd.shuffleType</code> - 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 <code>auto</code> and <code>none</code>. The default value is <code>none</code>. We strongly recommend that you shuffle your data.</p> </li> <li> <p> <code>sgd.l1RegularizationAmount</code> - 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 <code>1.0E-08</code>.</p> <p>The value is a double that ranges from <code>0</code> to <code>MAX_DOUBLE</code>. The default is to not use L1 normalization. This parameter can't be used when <code>L2</code> is specified. Use this parameter sparingly.</p> </li> <li> <p> <code>sgd.l2RegularizationAmount</code> - 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 <code>1.0E-08</code>.</p> <p>The value is a double that ranges from <code>0</code> to <code>MAX_DOUBLE</code>. The default is to not use L2 normalization. This parameter can't be used when <code>L1</code> is specified. Use this parameter sparingly.</p> </li> </ul>
             training_data_source_id: <p>The <code>DataSource</code> that points to the training data.</p>
             recipe: <p>The data recipe for creating the <code>MLModel</code>. You must specify either the recipe or its URI. If you don't specify a recipe or its URI, Amazon ML creates a default.</p>

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/create_batch_prediction_input.py

@@ -24,7 +24,7 @@ class CreateBatchPredictionInput(TypedDict, closed=True):
     batch_prediction_data_source_id: "capo_machine_learning.types.entity_id.EntityId"
     """<p>The ID of the <code>DataSource</code> that points to the group of observations to predict.</p>"""
     output_uri: "capo_machine_learning.types.s3_url.S3Url"
-    r"""<p>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 <code>s3 key</code> portion of the <code>outputURI</code> field: ':', '//', '/./', '/../'.</p> <p>Amazon ML needs permissions to store and retrieve the logs on your behalf. For information about how to set permissions, see the <a href=\"https://docs.aws.amazon.com/machine-learning/latest/dg\">Amazon Machine Learning Developer Guide</a>.</p>"""
+    """<p>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 <code>s3 key</code> portion of the <code>outputURI</code> field: ':', '//', '/./', '/../'.</p> <p>Amazon ML needs permissions to store and retrieve the logs on your behalf. For information about how to set permissions, see the <a href="https://docs.aws.amazon.com/machine-learning/latest/dg">Amazon Machine Learning Developer Guide</a>.</p>"""
 
 
 # --- awsJson1_1 ser/de ---

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/create_data_source_from_rds_input.py

@@ -20,7 +20,7 @@ class CreateDataSourceFromRDSInput(TypedDict, closed=True):
     data_source_name: NotRequired["capo_machine_learning.types.entity_name.EntityName"]
     """<p>A user-supplied name or description of the <code>DataSource</code>.</p>"""
     rds_data: "capo_machine_learning.types.rds_data_spec.RDSDataSpec"
-    r"""<p>The data specification of an Amazon RDS <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon RDS database.</p> </li> <li> <p> <code>InstanceIdentifier </code> - A unique identifier for the Amazon RDS database instance.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon RDS database.</p> </li> <li> <p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p> </li> <li> <p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p> </li> <li> <p>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 [<code>SubnetId</code>, <code>SecurityGroupIds</code>] pair for a VPC-based RDS DB instance.</p> </li> <li> <p>SelectSqlQuery - A query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon S3 location for staging Amazon RDS data. The data retrieved from Amazon RDS using <code>SelectSqlQuery</code> is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> \"{\\"splitting\\":{\\"percentBegin\\":10,\\"percentEnd\\":60}}\"</code> </p> </li> </ul>"""
+    r"""<p>The data specification of an Amazon RDS <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon RDS database.</p> </li> <li> <p> <code>InstanceIdentifier </code> - A unique identifier for the Amazon RDS database instance.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon RDS database.</p> </li> <li> <p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p> </li> <li> <p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p> </li> <li> <p>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 [<code>SubnetId</code>, <code>SecurityGroupIds</code>] pair for a VPC-based RDS DB instance.</p> </li> <li> <p>SelectSqlQuery - A query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon S3 location for staging Amazon RDS data. The data retrieved from Amazon RDS using <code>SelectSqlQuery</code> is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>"""
     role_arn: "capo_machine_learning.types.role_arn.RoleARN"
     """<p>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 <code>SelectSqlQuery</code> query from Amazon RDS to Amazon S3.</p> <p></p>"""
     compute_statistics: (

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/create_data_source_from_redshift_input.py

@@ -20,7 +20,7 @@ class CreateDataSourceFromRedshiftInput(TypedDict, closed=True):
     data_source_name: NotRequired["capo_machine_learning.types.entity_name.EntityName"]
     """<p>A user-supplied name or description of the <code>DataSource</code>. </p>"""
     data_spec: "capo_machine_learning.types.redshift_data_spec.RedshiftDataSpec"
-    r"""<p>The data specification of an Amazon Redshift <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon Redshift database.</p> </li> <li> <p> <code> ClusterIdentifier</code> - The unique ID for the Amazon Redshift cluster.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - The AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon Redshift database.</p> </li> <li> <p>SelectSqlQuery - The query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon Simple Storage Service (Amazon S3) location for staging Amazon Redshift data. The data retrieved from Amazon Redshift using the <code>SelectSqlQuery</code> query is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>DataSource</code>.</p> <p> Sample - <code> \"{\\"splitting\\":{\\"percentBegin\\":10,\\"percentEnd\\":60}}\"</code> </p> </li> </ul>"""
+    r"""<p>The data specification of an Amazon Redshift <code>DataSource</code>:</p> <ul> <li> <p>DatabaseInformation -</p> <ul> <li> <p> <code>DatabaseName</code> - The name of the Amazon Redshift database.</p> </li> <li> <p> <code> ClusterIdentifier</code> - The unique ID for the Amazon Redshift cluster.</p> </li> </ul> </li> <li> <p>DatabaseCredentials - The AWS Identity and Access Management (IAM) credentials that are used to connect to the Amazon Redshift database.</p> </li> <li> <p>SelectSqlQuery - The query that is used to retrieve the observation data for the <code>Datasource</code>.</p> </li> <li> <p>S3StagingLocation - The Amazon Simple Storage Service (Amazon S3) location for staging Amazon Redshift data. The data retrieved from Amazon Redshift using the <code>SelectSqlQuery</code> query is stored in this location.</p> </li> <li> <p>DataSchemaUri - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>DataSource</code>.</p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>"""
     role_arn: "capo_machine_learning.types.role_arn.RoleARN"
     """<p>A fully specified role Amazon Resource Name (ARN). Amazon ML assumes the role on behalf of the user to create the following:</p> <ul> <li> <p>A security group to allow Amazon ML to execute the <code>SelectSqlQuery</code> query on an Amazon Redshift cluster</p> </li> <li> <p>An Amazon S3 bucket policy to grant Amazon ML read/write permissions on the <code>S3StagingLocation</code> </p> </li> </ul>"""
     compute_statistics: (

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/create_data_source_from_s3_input.py

@@ -19,7 +19,7 @@ class CreateDataSourceFromS3Input(TypedDict, closed=True):
     data_source_name: NotRequired["capo_machine_learning.types.entity_name.EntityName"]
     """<p>A user-supplied name or description of the <code>DataSource</code>. </p>"""
     data_spec: "capo_machine_learning.types.s3_data_spec.S3DataSpec"
-    r"""<p>The data specification of a <code>DataSource</code>:</p> <ul> <li> <p>DataLocationS3 - The Amazon S3 location of the observation data.</p> </li> <li> <p>DataSchemaLocationS3 - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> \"{\\"splitting\\":{\\"percentBegin\\":10,\\"percentEnd\\":60}}\"</code> </p> </li> </ul>"""
+    r"""<p>The data specification of a <code>DataSource</code>:</p> <ul> <li> <p>DataLocationS3 - The Amazon S3 location of the observation data.</p> </li> <li> <p>DataSchemaLocationS3 - The Amazon S3 location of the <code>DataSchema</code>.</p> </li> <li> <p>DataSchema - A JSON string representing the schema. This is not required if <code>DataSchemaUri</code> is specified. </p> </li> <li> <p>DataRearrangement - A JSON string that represents the splitting and rearrangement requirements for the <code>Datasource</code>. </p> <p> Sample - <code> "{\"splitting\":{\"percentBegin\":10,\"percentEnd\":60}}"</code> </p> </li> </ul>"""
     compute_statistics: (
         "capo_machine_learning.types.compute_statistics.ComputeStatistics"
     )

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/create_ml_model_input.py

@@ -21,7 +21,7 @@ class CreateMLModelInput(TypedDict, closed=True):
     ml_model_name: NotRequired["capo_machine_learning.types.entity_name.EntityName"]
     """<p>A user-supplied name or description of the <code>MLModel</code>.</p>"""
     ml_model_type: "capo_machine_learning.types.ml_model_type.MLModelType"
-    r"""<p>The category of supervised learning that this <code>MLModel</code> will address. Choose from the following types:</p> <ul> <li> <p>Choose <code>REGRESSION</code> if the <code>MLModel</code> will be used to predict a numeric value.</p> </li> <li> <p>Choose <code>BINARY</code> if the <code>MLModel</code> result has two possible values.</p> </li> <li> <p>Choose <code>MULTICLASS</code> if the <code>MLModel</code> result has a limited number of values.</p> </li> </ul> <p> For more information, see the <a href=\"https://docs.aws.amazon.com/machine-learning/latest/dg\">Amazon Machine Learning Developer Guide</a>.</p>"""
+    """<p>The category of supervised learning that this <code>MLModel</code> will address. Choose from the following types:</p> <ul> <li> <p>Choose <code>REGRESSION</code> if the <code>MLModel</code> will be used to predict a numeric value.</p> </li> <li> <p>Choose <code>BINARY</code> if the <code>MLModel</code> result has two possible values.</p> </li> <li> <p>Choose <code>MULTICLASS</code> if the <code>MLModel</code> result has a limited number of values.</p> </li> </ul> <p> For more information, see the <a href="https://docs.aws.amazon.com/machine-learning/latest/dg">Amazon Machine Learning Developer Guide</a>.</p>"""
     parameters: NotRequired[
         "capo_machine_learning.types.training_parameters.TrainingParameters"
     ]

capo_machine_learning-0.4.0/src/capo_machine_learning/types/data_schema.py

@@ -0,0 +1,6 @@
+"""Generated from Smithy shape ``com.amazonaws.machinelearning#DataSchema``."""
+
+from typing import TypeAlias
+
+"""<p>The schema of a <code>DataSource</code>. The <code>DataSchema</code> defines the structure of the observation data in the data file(s) referenced in the <code>DataSource</code>. The DataSource schema is expressed in JSON format.</p> <p> <code>DataSchema</code> is not required if you specify a <code>DataSchemaUri</code> </p> <p>{ "version": "1.0", "recordAnnotationFieldName": "F1", "recordWeightFieldName": "F2", "targetFieldName": "F3", "dataFormat": "CSV", "dataFileContainsHeader": true, "variables": [ { "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" ] }</p>"""
+DataSchema: TypeAlias = str

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/evaluation.py

@@ -42,7 +42,7 @@ class Evaluation(TypedDict, closed=True):
     performance_metrics: NotRequired[
         "capo_machine_learning.types.performance_metrics.PerformanceMetrics"
     ]
-    r"""<p>Measurements of how well the <code>MLModel</code> performed, using observations referenced by the <code>DataSource</code>. One of the following metrics is returned, based on the type of the <code>MLModel</code>: </p> <ul> <li> <p>BinaryAUC: A binary <code>MLModel</code> uses the Area Under the Curve (AUC) technique to measure performance. </p> </li> <li> <p>RegressionRMSE: A regression <code>MLModel</code> uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable.</p> </li> <li> <p>MulticlassAvgFScore: A multiclass <code>MLModel</code> uses the F1 score technique to measure performance. </p> </li> </ul> <p> For more information about performance metrics, please see the <a href=\"https://docs.aws.amazon.com/machine-learning/latest/dg\">Amazon Machine Learning Developer Guide</a>. </p>"""
+    """<p>Measurements of how well the <code>MLModel</code> performed, using observations referenced by the <code>DataSource</code>. One of the following metrics is returned, based on the type of the <code>MLModel</code>: </p> <ul> <li> <p>BinaryAUC: A binary <code>MLModel</code> uses the Area Under the Curve (AUC) technique to measure performance. </p> </li> <li> <p>RegressionRMSE: A regression <code>MLModel</code> uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable.</p> </li> <li> <p>MulticlassAvgFScore: A multiclass <code>MLModel</code> uses the F1 score technique to measure performance. </p> </li> </ul> <p> For more information about performance metrics, please see the <a href="https://docs.aws.amazon.com/machine-learning/latest/dg">Amazon Machine Learning Developer Guide</a>. </p>"""
     message: NotRequired["capo_machine_learning.types.message.Message"]
     """<p>A description of the most recent details about evaluating the <code>MLModel</code>.</p>"""
     compute_time: NotRequired["capo_machine_learning.types.long_type.LongType"]

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/get_evaluation_output.py

@@ -43,7 +43,7 @@ class GetEvaluationOutput(TypedDict, closed=True):
     performance_metrics: NotRequired[
         "capo_machine_learning.types.performance_metrics.PerformanceMetrics"
     ]
-    r"""<p>Measurements of how well the <code>MLModel</code> performed using observations referenced by the <code>DataSource</code>. One of the following metric is returned based on the type of the <code>MLModel</code>: </p> <ul> <li> <p>BinaryAUC: A binary <code>MLModel</code> uses the Area Under the Curve (AUC) technique to measure performance. </p> </li> <li> <p>RegressionRMSE: A regression <code>MLModel</code> uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable.</p> </li> <li> <p>MulticlassAvgFScore: A multiclass <code>MLModel</code> uses the F1 score technique to measure performance. </p> </li> </ul> <p> For more information about performance metrics, please see the <a href=\"https://docs.aws.amazon.com/machine-learning/latest/dg\">Amazon Machine Learning Developer Guide</a>. </p>"""
+    """<p>Measurements of how well the <code>MLModel</code> performed using observations referenced by the <code>DataSource</code>. One of the following metric is returned based on the type of the <code>MLModel</code>: </p> <ul> <li> <p>BinaryAUC: A binary <code>MLModel</code> uses the Area Under the Curve (AUC) technique to measure performance. </p> </li> <li> <p>RegressionRMSE: A regression <code>MLModel</code> uses the Root Mean Square Error (RMSE) technique to measure performance. RMSE measures the difference between predicted and actual values for a single variable.</p> </li> <li> <p>MulticlassAvgFScore: A multiclass <code>MLModel</code> uses the F1 score technique to measure performance. </p> </li> </ul> <p> For more information about performance metrics, please see the <a href="https://docs.aws.amazon.com/machine-learning/latest/dg">Amazon Machine Learning Developer Guide</a>. </p>"""
     log_uri: NotRequired["capo_machine_learning.types.presigned_s3_url.PresignedS3Url"]
     """<p>A link to the file that contains logs of the <code>CreateEvaluation</code> operation.</p>"""
     message: NotRequired["capo_machine_learning.types.message.Message"]

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/get_ml_model_output.py

@@ -53,7 +53,7 @@ class GetMLModelOutput(TypedDict, closed=True):
     input_data_location_s3: NotRequired["capo_machine_learning.types.s3_url.S3Url"]
     """<p>The location of the data file or directory in Amazon Simple Storage Service (Amazon S3).</p>"""
     ml_model_type: NotRequired["capo_machine_learning.types.ml_model_type.MLModelType"]
-    r"""<p>Identifies the <code>MLModel</code> category. The following are the available types: </p> <ul> <li> <p>REGRESSION -- Produces a numeric result. For example, \"What price should a house be listed at?\"</p> </li> <li> <p>BINARY -- Produces one of two possible results. For example, \"Is this an e-commerce website?\"</p> </li> <li> <p>MULTICLASS -- Produces one of several possible results. For example, \"Is this a HIGH, LOW or MEDIUM risk trade?\"</p> </li> </ul>"""
+    """<p>Identifies the <code>MLModel</code> category. The following are the available types: </p> <ul> <li> <p>REGRESSION -- Produces a numeric result. For example, "What price should a house be listed at?"</p> </li> <li> <p>BINARY -- Produces one of two possible results. For example, "Is this an e-commerce website?"</p> </li> <li> <p>MULTICLASS -- Produces one of several possible results. For example, "Is this a HIGH, LOW or MEDIUM risk trade?"</p> </li> </ul>"""
     score_threshold: NotRequired[
         "capo_machine_learning.types.score_threshold.ScoreThreshold"
     ]

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/ml_model.py

@@ -53,7 +53,7 @@ class MLModel(TypedDict, closed=True):
     algorithm: NotRequired["capo_machine_learning.types.algorithm.Algorithm"]
     """<p>The algorithm used to train the <code>MLModel</code>. The following algorithm is supported:</p> <ul> <li> <p> <code>SGD</code> -- Stochastic gradient descent. The goal of <code>SGD</code> is to minimize the gradient of the loss function. </p> </li> </ul>"""
     ml_model_type: NotRequired["capo_machine_learning.types.ml_model_type.MLModelType"]
-    r"""<p>Identifies the <code>MLModel</code> category. The following are the available types:</p> <ul> <li> <p> <code>REGRESSION</code> - Produces a numeric result. For example, \"What price should a house be listed at?\"</p> </li> <li> <p> <code>BINARY</code> - Produces one of two possible results. For example, \"Is this a child-friendly web site?\".</p> </li> <li> <p> <code>MULTICLASS</code> - Produces one of several possible results. For example, \"Is this a HIGH-, LOW-, or MEDIUM-risk trade?\".</p> </li> </ul>"""
+    """<p>Identifies the <code>MLModel</code> category. The following are the available types:</p> <ul> <li> <p> <code>REGRESSION</code> - Produces a numeric result. For example, "What price should a house be listed at?"</p> </li> <li> <p> <code>BINARY</code> - Produces one of two possible results. For example, "Is this a child-friendly web site?".</p> </li> <li> <p> <code>MULTICLASS</code> - Produces one of several possible results. For example, "Is this a HIGH-, LOW-, or MEDIUM-risk trade?".</p> </li> </ul>"""
     score_threshold: NotRequired[
         "capo_machine_learning.types.score_threshold.ScoreThreshold"
     ]

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/rds_data_spec.py

@@ -35,15 +35,15 @@ class RDSDataSpec(TypedDict, closed=True):
     data_rearrangement: NotRequired[
         "capo_machine_learning.types.data_rearrangement.DataRearrangement"
     ]
-    r"""<p>A JSON string that represents the splitting and rearrangement processing to be applied to a <code>DataSource</code>. If the <code>DataRearrangement</code> parameter is not provided, all of the input data is used to create the <code>Datasource</code>.</p> <p>There are multiple parameters that control what data is used to create a datasource:</p> <ul> <li> <p> <b> <code>percentBegin</code> </b> </p> <p>Use <code>percentBegin</code> to indicate the beginning of the range of the data used to create the Datasource. If you do not include <code>percentBegin</code> and <code>percentEnd</code>, Amazon ML includes all of the data when creating the datasource.</p> </li> <li> <p> <b> <code>percentEnd</code> </b> </p> <p>Use <code>percentEnd</code> to indicate the end of the range of the data used to create the Datasource. If you do not include <code>percentBegin</code> and <code>percentEnd</code>, Amazon ML includes all of the data when creating the datasource.</p> </li> <li> <p> <b> <code>complement</code> </b> </p> <p>The <code>complement</code> parameter instructs Amazon ML to use the data that is not included in the range of <code>percentBegin</code> to <code>percentEnd</code> to create a datasource. The <code>complement</code> parameter is useful if you need to create complementary datasources for training and evaluation. To create a complementary datasource, use the same values for <code>percentBegin</code> and <code>percentEnd</code>, along with the <code>complement</code> parameter.</p> <p>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.</p> <p>Datasource for evaluation: <code>{\"splitting\":{\"percentBegin\":0, \"percentEnd\":25}}</code> </p> <p>Datasource for training: <code>{\"splitting\":{\"percentBegin\":0, \"percentEnd\":25, \"complement\":\"true\"}}</code> </p> </li> <li> <p> <b> <code>strategy</code> </b> </p> <p>To change how Amazon ML splits the data for a datasource, use the <code>strategy</code> parameter.</p> <p>The default value for the <code>strategy</code> parameter is <code>sequential</code>, meaning that Amazon ML takes all of the data records between the <code>percentBegin</code> and <code>percentEnd</code> parameters for the datasource, in the order that the records appear in the input data.</p> <p>The following two <code>DataRearrangement</code> lines are examples of sequentially ordered training and evaluation datasources:</p> <p>Datasource for evaluation: <code>{\"splitting\":{\"percentBegin\":70, \"percentEnd\":100, \"strategy\":\"sequential\"}}</code> </p> <p>Datasource for training: <code>{\"splitting\":{\"percentBegin\":70, \"percentEnd\":100, \"strategy\":\"sequential\", \"complement\":\"true\"}}</code> </p> <p>To randomly split the input data into the proportions indicated by the percentBegin and percentEnd parameters, set the <code>strategy</code> parameter to <code>random</code> 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 <code>percentBegin</code> and <code>percentEnd</code>. 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.</p> <p>The following two <code>DataRearrangement</code> lines are examples of non-sequentially ordered training and evaluation datasources:</p> <p>Datasource for evaluation: <code>{\"splitting\":{\"percentBegin\":70, \"percentEnd\":100, \"strategy\":\"random\", \"randomSeed\"=\"s3://my_s3_path/bucket/file.csv\"}}</code> </p> <p>Datasource for training: <code>{\"splitting\":{\"percentBegin\":70, \"percentEnd\":100, \"strategy\":\"random\", \"randomSeed\"=\"s3://my_s3_path/bucket/file.csv\", \"complement\":\"true\"}}</code> </p> </li> </ul>"""
+    """<p>A JSON string that represents the splitting and rearrangement processing to be applied to a <code>DataSource</code>. If the <code>DataRearrangement</code> parameter is not provided, all of the input data is used to create the <code>Datasource</code>.</p> <p>There are multiple parameters that control what data is used to create a datasource:</p> <ul> <li> <p> <b> <code>percentBegin</code> </b> </p> <p>Use <code>percentBegin</code> to indicate the beginning of the range of the data used to create the Datasource. If you do not include <code>percentBegin</code> and <code>percentEnd</code>, Amazon ML includes all of the data when creating the datasource.</p> </li> <li> <p> <b> <code>percentEnd</code> </b> </p> <p>Use <code>percentEnd</code> to indicate the end of the range of the data used to create the Datasource. If you do not include <code>percentBegin</code> and <code>percentEnd</code>, Amazon ML includes all of the data when creating the datasource.</p> </li> <li> <p> <b> <code>complement</code> </b> </p> <p>The <code>complement</code> parameter instructs Amazon ML to use the data that is not included in the range of <code>percentBegin</code> to <code>percentEnd</code> to create a datasource. The <code>complement</code> parameter is useful if you need to create complementary datasources for training and evaluation. To create a complementary datasource, use the same values for <code>percentBegin</code> and <code>percentEnd</code>, along with the <code>complement</code> parameter.</p> <p>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.</p> <p>Datasource for evaluation: <code>{"splitting":{"percentBegin":0, "percentEnd":25}}</code> </p> <p>Datasource for training: <code>{"splitting":{"percentBegin":0, "percentEnd":25, "complement":"true"}}</code> </p> </li> <li> <p> <b> <code>strategy</code> </b> </p> <p>To change how Amazon ML splits the data for a datasource, use the <code>strategy</code> parameter.</p> <p>The default value for the <code>strategy</code> parameter is <code>sequential</code>, meaning that Amazon ML takes all of the data records between the <code>percentBegin</code> and <code>percentEnd</code> parameters for the datasource, in the order that the records appear in the input data.</p> <p>The following two <code>DataRearrangement</code> lines are examples of sequentially ordered training and evaluation datasources:</p> <p>Datasource for evaluation: <code>{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential"}}</code> </p> <p>Datasource for training: <code>{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential", "complement":"true"}}</code> </p> <p>To randomly split the input data into the proportions indicated by the percentBegin and percentEnd parameters, set the <code>strategy</code> parameter to <code>random</code> 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 <code>percentBegin</code> and <code>percentEnd</code>. 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.</p> <p>The following two <code>DataRearrangement</code> lines are examples of non-sequentially ordered training and evaluation datasources:</p> <p>Datasource for evaluation: <code>{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv"}}</code> </p> <p>Datasource for training: <code>{"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv", "complement":"true"}}</code> </p> </li> </ul>"""
     data_schema: NotRequired["capo_machine_learning.types.data_schema.DataSchema"]
-    r"""<p>A JSON string that represents the schema for an Amazon RDS <code>DataSource</code>. The <code>DataSchema</code> defines the structure of the observation data in the data file(s) referenced in the <code>DataSource</code>.</p> <p>A <code>DataSchema</code> is not required if you specify a <code>DataSchemaUri</code> </p> <p>Define your <code>DataSchema</code> as a series of key-value pairs. <code>attributes</code> and <code>excludedVariableNames</code> have an array of key-value pairs for their value. Use the following format to define your <code>DataSchema</code>.</p> <p>{ \"version\": \"1.0\",</p> <p>\"recordAnnotationFieldName\": \"F1\",</p> <p>\"recordWeightFieldName\": \"F2\",</p> <p>\"targetFieldName\": \"F3\",</p> <p>\"dataFormat\": \"CSV\",</p> <p>\"dataFileContainsHeader\": true,</p> <p>\"attributes\": [</p> <p>{ \"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\" } ],</p> <p>\"excludedVariableNames\": [ \"F6\" ] }</p>"""
+    """<p>A JSON string that represents the schema for an Amazon RDS <code>DataSource</code>. The <code>DataSchema</code> defines the structure of the observation data in the data file(s) referenced in the <code>DataSource</code>.</p> <p>A <code>DataSchema</code> is not required if you specify a <code>DataSchemaUri</code> </p> <p>Define your <code>DataSchema</code> as a series of key-value pairs. <code>attributes</code> and <code>excludedVariableNames</code> have an array of key-value pairs for their value. Use the following format to define your <code>DataSchema</code>.</p> <p>{ "version": "1.0",</p> <p>"recordAnnotationFieldName": "F1",</p> <p>"recordWeightFieldName": "F2",</p> <p>"targetFieldName": "F3",</p> <p>"dataFormat": "CSV",</p> <p>"dataFileContainsHeader": true,</p> <p>"attributes": [</p> <p>{ "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" } ],</p> <p>"excludedVariableNames": [ "F6" ] }</p>"""
     data_schema_uri: NotRequired["capo_machine_learning.types.s3_url.S3Url"]
     """<p>The Amazon S3 location of the <code>DataSchema</code>. </p>"""
     resource_role: "capo_machine_learning.types.edp_resource_role.EDPResourceRole"
-    r"""<p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p>"""
+    """<p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p>"""
     service_role: "capo_machine_learning.types.edp_service_role.EDPServiceRole"
-    r"""<p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p>"""
+    """<p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p>"""
     subnet_id: "capo_machine_learning.types.edp_subnet_id.EDPSubnetId"
     """<p>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.</p>"""
     security_group_ids: (

{capo_machine_learning-0.3.0 → capo_machine_learning-0.4.0}/src/capo_machine_learning/types/rds_metadata.py

@@ -26,11 +26,11 @@ class RDSMetadata(TypedDict, closed=True):
     resource_role: NotRequired[
         "capo_machine_learning.types.edp_resource_role.EDPResourceRole"
     ]
-    r"""<p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p>"""
+    """<p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p>"""
     service_role: NotRequired[
         "capo_machine_learning.types.edp_service_role.EDPServiceRole"
     ]
-    r"""<p>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 <a href=\"https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html\">Role templates</a> for data pipelines.</p>"""
+    """<p>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 <a href="https://docs.aws.amazon.com/datapipeline/latest/DeveloperGuide/dp-iam-roles.html">Role templates</a> for data pipelines.</p>"""
     data_pipeline_id: NotRequired[
         "capo_machine_learning.types.edp_pipeline_id.EDPPipelineId"
     ]