Smaws_Client_Forecast.Typestype nonrec weighted_quantile_loss = {loss_value : double option;The difference between the predicted value and the actual value over the quantile, weighted (normalized) by dividing by the sum over all quantiles.
*)quantile : double option;The quantile. Quantiles divide a probability distribution into regions of equal probability. For example, if the distribution was divided into 5 regions of equal probability, the quantiles would be 0.2, 0.4, 0.6, and 0.8.
*)}The weighted loss value for a quantile. This object is part of the Metrics object.
type nonrec weighted_quantile_losses = weighted_quantile_loss listtype nonrec error_metric = {map_e : double option;The Mean Absolute Percentage Error (MAPE)
*)mas_e : double option;The Mean Absolute Scaled Error (MASE)
*)rms_e : double option;The root-mean-square error (RMSE).
*)wap_e : double option;The weighted absolute percentage error (WAPE).
*)forecast_type : forecast_type option;The Forecast type used to compute WAPE, MAPE, MASE, and RMSE.
*)}Provides detailed error metrics to evaluate the performance of a predictor. This object is part of the Metrics object.
type nonrec error_metrics = error_metric listtype nonrec metrics = {average_weighted_quantile_loss : double option;The average value of all weighted quantile losses.
*)error_metrics : error_metrics option;Provides detailed error metrics for each forecast type. Metrics include root-mean square-error (RMSE), mean absolute percentage error (MAPE), mean absolute scaled error (MASE), and weighted average percentage error (WAPE).
*)weighted_quantile_losses : weighted_quantile_losses option;An array of weighted quantile losses. Quantiles divide a probability distribution into regions of equal probability. The distribution in this case is the loss function.
*)rms_e : double option;The root-mean-square error (RMSE).
*)}Provides metrics that are used to evaluate the performance of a predictor. This object is part of the WindowSummary object.
type nonrec window_summary = {metrics : metrics option;Provides metrics used to evaluate the performance of a predictor.
*)evaluation_type : evaluation_type option;The type of evaluation.
SUMMARY - The average metrics across all windows.COMPUTED - The metrics for the specified window.item_count : integer option;The number of data points within the window.
*)test_window_end : timestamp option;The timestamp that defines the end of the window.
*)test_window_start : timestamp option;The timestamp that defines the start of the window.
*)}The metrics for a time range within the evaluation portion of a dataset. This object is part of the EvaluationResult object.
The TestWindowStart and TestWindowEnd parameters are determined by the BackTestWindowOffset parameter of the EvaluationParameters object.
type nonrec what_if_forecast_summary = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the what-if forecast was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : status option;The status of the what-if forecast. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the what-if analysis must be ACTIVE before you can access the analysis.
what_if_analysis_arn : arn option;The Amazon Resource Name (ARN) of the what-if analysis that contains this what-if forecast.
*)what_if_forecast_name : name option;The name of the what-if forecast.
*)what_if_forecast_arn : long_arn option;The Amazon Resource Name (ARN) of the what-if forecast.
*)}Provides a summary of the what-if forecast properties used in the ListWhatIfForecasts operation. To get the complete set of properties, call the DescribeWhatIfForecast operation, and provide the WhatIfForecastArn that is listed in the summary.
type nonrec what_if_forecasts = what_if_forecast_summary listtype nonrec what_if_forecast_arn_list_for_export = long_arn listtype nonrec s3_config = {kms_key_arn : kms_key_arn option;The Amazon Resource Name (ARN) of an Key Management Service (KMS) key.
*)role_arn : arn;The ARN of the Identity and Access Management (IAM) role that Amazon Forecast can assume to access the Amazon S3 bucket or files. If you provide a value for the KMSKeyArn key, the role must allow access to the key.
Passing a role across Amazon Web Services accounts is not allowed. If you pass a role that isn't in your account, you get an InvalidInputException error.
path : s3_path;The path to an Amazon Simple Storage Service (Amazon S3) bucket or file(s) in an Amazon S3 bucket.
*)}The path to the file(s) in an Amazon Simple Storage Service (Amazon S3) bucket, and an Identity and Access Management (IAM) role that Amazon Forecast can assume to access the file(s). Optionally, includes an Key Management Service (KMS) key. This object is part of the DataSource object that is submitted in the CreateDatasetImportJob request, and part of the DataDestination object.
type nonrec data_destination = {s3_config : s3_config;The path to an Amazon Simple Storage Service (Amazon S3) bucket along with the credentials to access the bucket.
*)}The destination for an export job. Provide an S3 path, an Identity and Access Management (IAM) role that allows Amazon Forecast to access the location, and an Key Management Service (KMS) key (optional).
type nonrec what_if_forecast_export_summary = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the what-if forecast export was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : status option;The status of the what-if forecast export. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the what-if analysis must be ACTIVE before you can access the analysis.
destination : data_destination option;The path to the Amazon Simple Storage Service (Amazon S3) bucket where the forecast is exported.
*)what_if_forecast_export_name : name option;The what-if forecast export name.
*)what_if_forecast_arns : what_if_forecast_arn_list_for_export option;An array of Amazon Resource Names (ARNs) that define the what-if forecasts included in the export.
*)what_if_forecast_export_arn : long_arn option;The Amazon Resource Name (ARN) of the what-if forecast export.
*)}Provides a summary of the what-if forecast export properties used in the ListWhatIfForecastExports operation. To get the complete set of properties, call the DescribeWhatIfForecastExport operation, and provide the WhatIfForecastExportArn that is listed in the summary.
type nonrec what_if_forecast_exports = what_if_forecast_export_summary listtype nonrec what_if_analysis_summary = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the what-if analysis was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : status option;The status of the what-if analysis. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the what-if analysis must be ACTIVE before you can access the analysis.
forecast_arn : arn option;The Amazon Resource Name (ARN) of the baseline forecast that is being used in this what-if analysis.
*)what_if_analysis_name : name option;The name of the what-if analysis.
*)what_if_analysis_arn : arn option;The Amazon Resource Name (ARN) of the what-if analysis.
*)}Provides a summary of the what-if analysis properties used in the ListWhatIfAnalyses operation. To get the complete set of properties, call the DescribeWhatIfAnalysis operation, and provide the WhatIfAnalysisArn that is listed in the summary.
type nonrec what_if_analyses = what_if_analysis_summary listtype nonrec values = value listtype nonrec arn_list = arn listWe can't find a resource with that Amazon Resource Name (ARN). Check the ARN and try again.
The specified resource is in use.
We can't process the request because it includes an invalid value or a value that exceeds the valid range.
type nonrec tag_keys = tag_key listtype nonrec training_parameters = (parameter_key * parameter_value) listtype nonrec action = {value : double;The value that is applied for the chosen Operation.
operation : operation;The operation that is applied to the provided attribute. Operations include:
ADD - adds Value to all rows of AttributeName.SUBTRACT - subtracts Value from all rows of AttributeName.MULTIPLY - multiplies all rows of AttributeName by Value.DIVIDE - divides all rows of AttributeName by Value.attribute_name : name;The related time series that you are modifying. This value is case insensitive.
*)}Defines the modifications that you are making to an attribute for a what-if forecast. For example, you can use this operation to create a what-if forecast that investigates a 10% off sale on all shoes. To do this, you specify "AttributeName": "shoes", "Operation": "MULTIPLY", and "Value": "0.90". Pair this operation with the TimeSeriesCondition operation within the CreateWhatIfForecastRequest$TimeSeriesTransformations operation to define a subset of attribute items that are modified.
type nonrec time_series_condition = {condition : condition;The condition to apply. Valid values are EQUALS, NOT_EQUALS, LESS_THAN and GREATER_THAN.
attribute_value : attribute_value;The value that is applied for the chosen Condition.
attribute_name : name;The item_id, dimension name, IM name, or timestamp that you are modifying.
*)}Creates a subset of items within an attribute that are modified. For example, you can use this operation to create a subset of items that cost $5 or less. To do this, you specify "AttributeName": "price", "AttributeValue": "5", and "Condition": "LESS_THAN". Pair this operation with the Action operation within the CreateWhatIfForecastRequest$TimeSeriesTransformations operation to define how the attribute is modified.
type nonrec time_series_conditions = time_series_condition listtype nonrec time_series_transformation = {time_series_conditions : time_series_conditions option;An array of conditions that define which members of the related time series are transformed.
*)action : action option;An array of actions that define a time series and how it is transformed. These transformations create a new time series that is used for the what-if analysis.
*)}A transformation function is a pair of operations that select and modify the rows in a related time series. You select the rows that you want with a condition operation and you modify the rows with a transformation operation. All conditions are joined with an AND operation, meaning that all conditions must be true for the transformation to be applied. Transformations are applied in the order that they are listed.
type nonrec time_series_transformations = time_series_transformation listtype nonrec data_source = {s3_config : s3_config;The path to the data stored in an Amazon Simple Storage Service (Amazon S3) bucket along with the credentials to access the data.
*)}The source of your data, an Identity and Access Management (IAM) role that allows Amazon Forecast to access the data and, optionally, an Key Management Service (KMS) key.
type nonrec schema_attribute = {attribute_type : attribute_type option;The data type of the field.
For a related time series dataset, other than date, item_id, and forecast dimensions attributes, all attributes should be of numerical type (integer/float).
*)attribute_name : name option;The name of the dataset field.
*)}An attribute of a schema, which defines a dataset field. A schema attribute is required for every field in a dataset. The Schema object contains an array of SchemaAttribute objects.
type nonrec schema_attributes = schema_attribute listtype nonrec schema = {attributes : schema_attributes option;An array of attributes specifying the name and type of each field in a dataset.
*)}Defines the fields of a dataset.
type nonrec time_series_identifiers = {format : format option;The format of the data, either CSV or PARQUET.
*)schema : schema option;data_source : data_source option;}Details about the import file that contains the time series for which you want to create forecasts.
type nonrec time_series_selector = {time_series_identifiers : time_series_identifiers option;Details about the import file that contains the time series for which you want to create forecasts.
*)}Defines the set of time series that are used to create the forecasts in a TimeSeriesIdentifiers object.
The TimeSeriesIdentifiers object needs the following information:
DataSourceFormatSchematype nonrec time_series_replacements_data_source = {timestamp_format : timestamp_format option;The timestamp format of the replacement data.
*)format : format option;The format of the replacement data, CSV or PARQUET.
*)schema : schema;s3_config : s3_config;}A replacement dataset is a modified version of the baseline related time series that contains only the values that you want to include in a what-if forecast. The replacement dataset must contain the forecast dimensions and item identifiers in the baseline related time series as well as at least 1 changed time series. This dataset is merged with the baseline related time series to create a transformed dataset that is used for the what-if forecast.
type nonrec time_alignment_boundary = {hour : hour option;The hour of day to use for time alignment during aggregation.
*)day_of_week : day_of_week option;The day of week to use for time alignment during aggregation. The day must be in uppercase.
*)day_of_month : day_of_month option;The day of the month to use for time alignment during aggregation.
*)month : month option;The month to use for time alignment during aggregation. The month must be in uppercase.
*)}The time boundary Forecast uses to align and aggregate your data to match your forecast frequency. Provide the unit of time and the time boundary as a key value pair. If you don't provide a time boundary, Forecast uses a set of Default Time Boundaries.
For more information about aggregation, see Data Aggregation for Different Forecast Frequencies. For more information setting a custom time boundary, see Specifying a Time Boundary.
type nonrec test_windows = window_summary listtype nonrec test_window_summary = {message : error_message option;If the test failed, the reason why it failed.
*)status : status option;The status of the test. Possible status values are:
ACTIVECREATE_IN_PROGRESSCREATE_FAILEDtest_window_end : timestamp option;The time at which the test ended.
*)test_window_start : timestamp option;The time at which the test began.
*)}The status, start time, and end time of a backtest, as well as a failure reason if applicable.
type nonrec test_window_details = test_window_summary listtype nonrec tag = {value : tag_value;The optional part of a key-value pair that makes up a tag. A value acts as a descriptor within a tag category (key).
key : tag_key;One part of a key-value pair that makes up a tag. A key is a general label that acts like a category for more specific tag values.
}The optional metadata that you apply to a resource to help you categorize and organize them. Each tag consists of a key and an optional value, both of which you define.
The following basic restrictions apply to tags:
aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for Amazon Web Services use. You cannot edit or delete tag keys with this prefix. Values can have this prefix. If a tag value has aws as its prefix but the key does not, then Forecast considers it to be a user tag and will count against the limit of 50 tags. Tags with only the key prefix of aws do not count against your tags per resource limit.type nonrec tags = tag listtype nonrec tag_resource_request = {resource_arn : arn;The Amazon Resource Name (ARN) that identifies the resource for which to list the tags.
*)}The limit on the number of resources per account has been exceeded.
type nonrec supplementary_feature = {value : value;Weather Index
To enable the Weather Index, set the value to "true"
Holidays
To enable Holidays, specify a country with one of the following two-letter country codes:
name : name;The name of the feature. Valid values: "holiday" and "weather".
}This object belongs to the CreatePredictor operation. If you created your predictor with CreateAutoPredictor, see AdditionalDataset.
Describes a supplementary feature of a dataset group. This object is part of the InputDataConfig object. Forecast supports the Weather Index and Holidays built-in featurizations.
Weather Index
The Amazon Forecast Weather Index is a built-in featurization that incorporates historical and projected weather information into your model. The Weather Index supplements your datasets with over two years of historical weather data and up to 14 days of projected weather data. For more information, see Amazon Forecast Weather Index.
Holidays
Holidays is a built-in featurization that incorporates a feature-engineered dataset of national holiday information into your model. It provides native support for the holiday calendars of 66 countries. To view the holiday calendars, refer to the Jollyday library. For more information, see Holidays Featurization.
type nonrec supplementary_features = supplementary_feature listtype nonrec stop_resource_request = {resource_arn : arn;The Amazon Resource Name (ARN) that identifies the resource to stop. The supported ARNs are DatasetImportJobArn, PredictorArn, PredictorBacktestExportJobArn, ForecastArn, ForecastExportJobArn, ExplainabilityArn, and ExplainabilityExportArn.
}type nonrec long = Smaws_Lib.CoreTypes.Int64.ttype nonrec statistics = {count_nan_long : long option;The number of NAN (not a number) values in the field. CountNanLong is used instead of CountNan if the value is greater than 2,147,483,647.
count_null_long : long option;The number of null values in the field. CountNullLong is used instead of CountNull if the value is greater than 2,147,483,647.
count_distinct_long : long option;The number of distinct values in the field. CountDistinctLong is used instead of CountDistinct if the value is greater than 2,147,483,647.
count_long : long option;The number of values in the field. CountLong is used instead of Count if the value is greater than 2,147,483,647.
stddev : double option;For a numeric field, the standard deviation.
*)avg : double option;For a numeric field, the average value in the field.
*)max : string_ option;For a numeric field, the maximum value in the field.
*)min : string_ option;For a numeric field, the minimum value in the field.
*)count_nan : integer option;The number of NAN (not a number) values in the field. If the response value is -1, refer to CountNanLong.
count_null : integer option;The number of null values in the field. If the response value is -1, refer to CountNullLong.
count_distinct : integer option;The number of distinct values in the field. If the response value is -1, refer to CountDistinctLong.
count : integer option;The number of values in the field. If the response value is -1, refer to CountLong.
}Provides statistics for each data field imported into to an Amazon Forecast dataset with the CreateDatasetImportJob operation.
type nonrec resume_resource_request = {resource_arn : arn;The Amazon Resource Name (ARN) of the monitor resource to resume.
*)}There is already a resource with this name. Try again with a different name.
type nonrec reference_predictor_summary = {state : state option;Whether the reference predictor is Active or Deleted.
arn : arn option;The ARN of the reference predictor.
*)}Provides a summary of the reference predictor used when retraining or upgrading a predictor.
type nonrec predictor_summary = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the model training task was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : status option;The status of the predictor. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDCREATE_STOPPING, CREATE_STOPPEDThe Status of the predictor must be ACTIVE before you can use the predictor to create a forecast.
reference_predictor_summary : reference_predictor_summary option;A summary of the reference predictor used if the predictor was retrained or upgraded.
*)is_auto_predictor : boolean_ option;Whether AutoPredictor was used to create the predictor.
*)dataset_group_arn : arn option;The Amazon Resource Name (ARN) of the dataset group that contains the data used to train the predictor.
*)predictor_name : name option;The name of the predictor.
*)predictor_arn : arn option;The ARN of the predictor.
*)}Provides a summary of the predictor properties that are used in the ListPredictors operation. To get the complete set of properties, call the DescribePredictor operation, and provide the listed PredictorArn.
type nonrec predictors = predictor_summary listtype nonrec predictor_event = {datetime : timestamp option;The timestamp for when the event occurred.
*)detail : detail option;The type of event. For example, Retrain. A retraining event denotes the timepoint when a predictor was retrained. Any monitor results from before the Datetime are from the previous predictor. Any new metrics are for the newly retrained predictor.
}Provides details about a predictor event, such as a retraining.
type nonrec monitor_data_source = {predictor_arn : arn option;The Amazon Resource Name (ARN) of the predictor resource you are monitoring.
*)forecast_arn : arn option;The Amazon Resource Name (ARN) of the forecast the monitor used during the evaluation.
*)dataset_import_job_arn : arn option;The Amazon Resource Name (ARN) of the dataset import job used to import the data that initiated the monitor evaluation.
*)}The source of the data the monitor used during the evaluation.
type nonrec metric_result = {metric_value : double option;The value for the metric.
*)metric_name : metric_name option;The name of the metric.
*)}An individual metric Forecast calculated when monitoring predictor usage. You can compare the value for this metric to the metric's value in the Baseline to see how your predictor's performance is changing.
For more information about metrics generated by Forecast see Evaluating Predictor Accuracy
type nonrec metric_results = metric_result listtype nonrec predictor_monitor_evaluation = {message : message option;Information about any errors that may have occurred during the monitor evaluation.
*)num_items_evaluated : long option;The number of items considered during the evaluation.
*)metric_results : metric_results option;A list of metrics Forecast calculated when monitoring a predictor. You can compare the value for each metric in the list to the metric's value in the Baseline to see how your predictor's performance is changing.
monitor_data_source : monitor_data_source option;The source of the data the monitor resource used during the evaluation.
*)predictor_event : predictor_event option;Provides details about a predictor event, such as a retraining.
*)window_end_datetime : timestamp option;The timestamp that indicates the end of the window that is used for monitor evaluation.
*)window_start_datetime : timestamp option;The timestamp that indicates the start of the window that is used for monitor evaluation.
*)evaluation_state : evaluation_state option;The status of the monitor evaluation. The state can be SUCCESS or FAILURE.
evaluation_time : timestamp option;The timestamp that indicates when the monitor evaluation was started.
*)monitor_arn : arn option;The Amazon Resource Name (ARN) of the monitor resource.
*)resource_arn : arn option;The Amazon Resource Name (ARN) of the resource to monitor.
*)}Describes the results of a monitor evaluation.
type nonrec predictor_monitor_evaluations = predictor_monitor_evaluation listtype nonrec predictor_execution = {test_windows : test_window_details option;An array of test windows used to evaluate the algorithm. The NumberOfBacktestWindows from the object determines the number of windows in the array.
algorithm_arn : arn option;The ARN of the algorithm used to test the predictor.
*)}The algorithm used to perform a backtest and the status of those tests.
type nonrec predictor_executions = predictor_execution listtype nonrec predictor_execution_details = {predictor_executions : predictor_executions option;An array of the backtests performed to evaluate the accuracy of the predictor against a particular algorithm. The NumberOfBacktestWindows from the object determines the number of windows in the array.
}Contains details on the backtests performed to evaluate the accuracy of the predictor. The tests are returned in descending order of accuracy, with the most accurate backtest appearing first. You specify the number of backtests to perform when you call the operation.
type nonrec evaluation_result = {test_windows : test_windows option;The array of test windows used for evaluating the algorithm. The NumberOfBacktestWindows from the EvaluationParameters object determines the number of windows in the array.
algorithm_arn : arn option;The Amazon Resource Name (ARN) of the algorithm that was evaluated.
*)}The results of evaluating an algorithm. Returned as part of the GetAccuracyMetrics response.
type nonrec predictor_evaluation_results = evaluation_result listAn individual metric that you can use for comparison as you evaluate your monitoring results.
type nonrec baseline_metrics = baseline_metric listtype nonrec predictor_baseline = {baseline_metrics : baseline_metrics option;The initial accuracy metrics for the predictor. Use these metrics as a baseline for comparison purposes as you use your predictor and the metrics change.
*)}Metrics you can use as a baseline for comparison purposes. Use these metrics when you interpret monitoring results for an auto predictor.
type nonrec predictor_backtest_export_job_summary = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the predictor backtest export job was created.
*)message : error_message option;Information about any errors that may have occurred during the backtest export.
*)status : status option;The status of the predictor backtest export job. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDdestination : data_destination option;predictor_backtest_export_job_name : name option;The name of the predictor backtest export job.
*)predictor_backtest_export_job_arn : arn option;The Amazon Resource Name (ARN) of the predictor backtest export job.
*)}Provides a summary of the predictor backtest export job properties used in the ListPredictorBacktestExportJobs operation. To get a complete set of properties, call the DescribePredictorBacktestExportJob operation, and provide the listed PredictorBacktestExportJobArn.
type nonrec predictor_backtest_export_jobs =
predictor_backtest_export_job_summary listtype nonrec categorical_parameter_range = {values : values;A list of the tunable categories for the hyperparameter.
*)name : name;The name of the categorical hyperparameter to tune.
*)}Specifies a categorical hyperparameter and it's range of tunable values. This object is part of the ParameterRanges object.
type nonrec categorical_parameter_ranges = categorical_parameter_range listtype nonrec continuous_parameter_range = {scaling_type : scaling_type option;The scale that hyperparameter tuning uses to search the hyperparameter range. Valid values:
Auto Amazon Forecast hyperparameter tuning chooses the best scale for the hyperparameter.
Linear Hyperparameter tuning searches the values in the hyperparameter range by using a linear scale.
Logarithmic Hyperparameter tuning searches the values in the hyperparameter range by using a logarithmic scale.
Logarithmic scaling works only for ranges that have values greater than 0.
ReverseLogarithmic hyperparameter tuning searches the values in the hyperparameter range by using a reverse logarithmic scale.
Reverse logarithmic scaling works only for ranges that are entirely within the range 0 <= x < 1.0.
For information about choosing a hyperparameter scale, see Hyperparameter Scaling. One of the following values:
*)min_value : double;The minimum tunable value of the hyperparameter.
*)max_value : double;The maximum tunable value of the hyperparameter.
*)name : name;The name of the hyperparameter to tune.
*)}Specifies a continuous hyperparameter and it's range of tunable values. This object is part of the ParameterRanges object.
type nonrec continuous_parameter_ranges = continuous_parameter_range listtype nonrec integer_parameter_range = {scaling_type : scaling_type option;The scale that hyperparameter tuning uses to search the hyperparameter range. Valid values:
Auto Amazon Forecast hyperparameter tuning chooses the best scale for the hyperparameter.
Linear Hyperparameter tuning searches the values in the hyperparameter range by using a linear scale.
Logarithmic Hyperparameter tuning searches the values in the hyperparameter range by using a logarithmic scale.
Logarithmic scaling works only for ranges that have values greater than 0.
ReverseLogarithmic Not supported for IntegerParameterRange.
Reverse logarithmic scaling works only for ranges that are entirely within the range 0 <= x < 1.0.
For information about choosing a hyperparameter scale, see Hyperparameter Scaling. One of the following values:
*)min_value : integer;The minimum tunable value of the hyperparameter.
*)max_value : integer;The maximum tunable value of the hyperparameter.
*)name : name;The name of the hyperparameter to tune.
*)}Specifies an integer hyperparameter and it's range of tunable values. This object is part of the ParameterRanges object.
type nonrec integer_parameter_ranges = integer_parameter_range listtype nonrec parameter_ranges = {integer_parameter_ranges : integer_parameter_ranges option;Specifies the tunable range for each integer hyperparameter.
*)continuous_parameter_ranges : continuous_parameter_ranges option;Specifies the tunable range for each continuous hyperparameter.
*)categorical_parameter_ranges : categorical_parameter_ranges option;Specifies the tunable range for each categorical hyperparameter.
*)}Specifies the categorical, continuous, and integer hyperparameters, and their ranges of tunable values. The range of tunable values determines which values that a hyperparameter tuning job can choose for the specified hyperparameter. This object is part of the HyperParameterTuningJobConfig object.
type nonrec monitor_summary = {last_modification_time : timestamp option;The last time the monitor resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.STOPPED - When the resource stopped.ACTIVE or CREATE_FAILED - When the monitor creation finished or failed.creation_time : timestamp option;When the monitor resource was created.
*)status : status option;The status of the monitor. States include:
ACTIVEACTIVE_STOPPING, ACTIVE_STOPPEDUPDATE_IN_PROGRESSCREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDresource_arn : arn option;The Amazon Resource Name (ARN) of the predictor being monitored.
*)monitor_name : name option;The name of the monitor resource.
*)monitor_arn : arn option;The Amazon Resource Name (ARN) of the monitor resource.
*)}Provides a summary of the monitor properties used in the ListMonitors operation. To get a complete set of properties, call the DescribeMonitor operation, and provide the listed MonitorArn.
type nonrec monitors = monitor_summary listtype nonrec monitor_info = {status : status option;The status of the monitor. States include:
ACTIVEACTIVE_STOPPING, ACTIVE_STOPPEDUPDATE_IN_PROGRESSCREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDmonitor_arn : arn option;The Amazon Resource Name (ARN) of the monitor resource.
*)}Provides information about the monitor resource.
The configuration details for the predictor monitor.
type nonrec long_arn_list = long_arn listtype nonrec list_what_if_forecasts_response = {next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next
request. Tokens expire after 24 hours.
what_if_forecasts : what_if_forecasts option;An array of WhatIfForecasts objects that describe the matched forecasts.
}type nonrec filter = {condition : filter_condition_string;The condition to apply. To include the objects that match the statement, specify IS. To exclude matching objects, specify IS_NOT.
value : arn;The value to match.
*)key : string_;The name of the parameter to filter on.
*)}Describes a filter for choosing a subset of objects. Each filter consists of a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the objects that match the statement, respectively. The match statement consists of a key and a value.
type nonrec filters = filter listtype nonrec list_what_if_forecasts_request = {filters : filters option;An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the what-if forecast export jobs that match the statement from the list, respectively. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT. To include the forecast export jobs that match the statement, specify IS. To exclude matching forecast export jobs, specify IS_NOT.Key - The name of the parameter to filter on. Valid values are WhatIfForecastArn and Status.Value - The value to match.For example, to list all jobs that export a forecast named electricityWhatIfForecast, specify the following filter:
"Filters": \[ \{ "Condition": "IS", "Key": "WhatIfForecastArn", "Value": "arn:aws:forecast:us-west-2::forecast/electricityWhatIfForecast" \} \]max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next
request. Tokens expire after 24 hours.
}The token is not valid. Tokens expire after 24 hours.
type nonrec list_what_if_forecast_exports_response = {next_token : next_token option;If the response is truncated, Forecast returns this token. To retrieve the next set of results, use the token in the next request.
*)what_if_forecast_exports : what_if_forecast_exports option;An array of WhatIfForecastExports objects that describe the matched forecast exports.
}type nonrec list_what_if_forecast_exports_request = {filters : filters option;An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the what-if forecast export jobs that match the statement from the list, respectively. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT. To include the forecast export jobs that match the statement, specify IS. To exclude matching forecast export jobs, specify IS_NOT.Key - The name of the parameter to filter on. Valid values are WhatIfForecastExportArn and Status.Value - The value to match.For example, to list all jobs that export a forecast named electricityWIFExport, specify the following filter:
"Filters": \[ \{ "Condition": "IS", "Key": "WhatIfForecastExportArn", "Value": "arn:aws:forecast:us-west-2::forecast/electricityWIFExport" \} \]max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next
request. Tokens expire after 24 hours.
}type nonrec list_what_if_analyses_response = {next_token : next_token option;If the response is truncated, Forecast returns this token. To retrieve the next set of results, use the token in the next request.
*)what_if_analyses : what_if_analyses option;An array of WhatIfAnalysisSummary objects that describe the matched analyses.
}type nonrec list_what_if_analyses_request = {filters : filters option;An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the what-if analysis jobs that match the statement from the list, respectively. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT. To include the what-if analysis jobs that match the statement, specify IS. To exclude matching what-if analysis jobs, specify IS_NOT.Key - The name of the parameter to filter on. Valid values are WhatIfAnalysisArn and Status.Value - The value to match.For example, to list all jobs that export a forecast named electricityWhatIf, specify the following filter:
"Filters": \[ \{ "Condition": "IS", "Key": "WhatIfAnalysisArn", "Value": "arn:aws:forecast:us-west-2::forecast/electricityWhatIf" \} \]max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
}type nonrec list_predictors_response = {next_token : next_token option;If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.
*)predictors : predictors option;An array of objects that summarize each predictor's properties.
*)}type nonrec list_predictors_request = {filters : filters option;An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the predictors that match the statement from the list, respectively. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT. To include the predictors that match the statement, specify IS. To exclude matching predictors, specify IS_NOT.Key - The name of the parameter to filter on. Valid values are DatasetGroupArn and Status.Value - The value to match.For example, to list all predictors whose status is ACTIVE, you would specify:
"Filters": [ { "Condition": "IS", "Key": "Status", "Value": "ACTIVE" } ]
max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
}type nonrec list_predictor_backtest_export_jobs_response = {next_token : next_token option;Returns this token if the response is truncated. To retrieve the next set of results, use the token in the next request.
*)predictor_backtest_export_jobs : predictor_backtest_export_jobs option;An array of objects that summarize the properties of each predictor backtest export job.
*)}type nonrec list_predictor_backtest_export_jobs_request = {filters : filters option;An array of filters. For each filter, provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the predictor backtest export jobs that match the statement from the list. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT. To include the predictor backtest export jobs that match the statement, specify IS. To exclude matching predictor backtest export jobs, specify IS_NOT.Key - The name of the parameter to filter on. Valid values are PredictorArn and Status.Value - The value to match.max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
*)}type nonrec list_monitors_response = {next_token : next_token option;If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.
*)monitors : monitors option;An array of objects that summarize each monitor's properties.
*)}type nonrec list_monitors_request = {filters : filters option;An array of filters. For each filter, provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the resources that match the statement from the list. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT.Key - The name of the parameter to filter on. The only valid value is Status.Value - The value to match.For example, to list all monitors who's status is ACTIVE, you would specify:
"Filters": [ { "Condition": "IS", "Key": "Status", "Value": "ACTIVE" } ]
max_results : max_results option;The maximum number of monitors to include in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
}type nonrec list_monitor_evaluations_response = {predictor_monitor_evaluations : predictor_monitor_evaluations option;The monitoring results and predictor events collected by the monitor resource during different windows of time.
For information about monitoring see Viewing Monitoring Results. For more information about retrieving monitoring results see Viewing Monitoring Results.
*)next_token : next_token option;If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
*)}type nonrec list_monitor_evaluations_request = {filters : filters option;An array of filters. For each filter, provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the resources that match the statement from the list. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT.Key - The name of the parameter to filter on. The only valid value is EvaluationState.Value - The value to match. Valid values are only SUCCESS or FAILURE.For example, to list only successful monitor evaluations, you would specify:
"Filters": [ { "Condition": "IS", "Key": "EvaluationState", "Value": "SUCCESS" } ]
monitor_arn : arn;The Amazon Resource Name (ARN) of the monitor resource to get results from.
*)max_results : max_results option;The maximum number of monitoring results to return.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
}type nonrec forecast_summary = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the forecast creation task was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : status option;The status of the forecast. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the forecast must be ACTIVE before you can query or export the forecast.
dataset_group_arn : string_ option;The Amazon Resource Name (ARN) of the dataset group that provided the data used to train the predictor.
*)created_using_auto_predictor : boolean_ option;Whether the Forecast was created from an AutoPredictor.
*)predictor_arn : string_ option;The ARN of the predictor used to generate the forecast.
*)forecast_name : name option;The name of the forecast.
*)forecast_arn : arn option;The ARN of the forecast.
*)}Provides a summary of the forecast properties used in the ListForecasts operation. To get the complete set of properties, call the DescribeForecast operation, and provide the ForecastArn that is listed in the summary.
type nonrec forecasts = forecast_summary listtype nonrec list_forecasts_response = {next_token : next_token option;If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.
*)forecasts : forecasts option;An array of objects that summarize each forecast's properties.
*)}type nonrec list_forecasts_request = {filters : filters option;An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the forecasts that match the statement from the list, respectively. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT. To include the forecasts that match the statement, specify IS. To exclude matching forecasts, specify IS_NOT.Key - The name of the parameter to filter on. Valid values are DatasetGroupArn, PredictorArn, and Status.Value - The value to match.For example, to list all forecasts whose status is not ACTIVE, you would specify:
"Filters": [ { "Condition": "IS_NOT", "Key": "Status", "Value": "ACTIVE" } ]
max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
}type nonrec forecast_export_job_summary = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the forecast export job was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : status option;The status of the forecast export job. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the forecast export job must be ACTIVE before you can access the forecast in your S3 bucket.
destination : data_destination option;The path to the Amazon Simple Storage Service (Amazon S3) bucket where the forecast is exported.
*)forecast_export_job_name : name option;The name of the forecast export job.
*)forecast_export_job_arn : arn option;The Amazon Resource Name (ARN) of the forecast export job.
*)}Provides a summary of the forecast export job properties used in the ListForecastExportJobs operation. To get the complete set of properties, call the DescribeForecastExportJob operation, and provide the listed ForecastExportJobArn.
type nonrec forecast_export_jobs = forecast_export_job_summary listtype nonrec list_forecast_export_jobs_response = {next_token : next_token option;If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.
*)forecast_export_jobs : forecast_export_jobs option;An array of objects that summarize each export job's properties.
*)}type nonrec list_forecast_export_jobs_request = {filters : filters option;An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the forecast export jobs that match the statement from the list, respectively. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT. To include the forecast export jobs that match the statement, specify IS. To exclude matching forecast export jobs, specify IS_NOT.Key - The name of the parameter to filter on. Valid values are ForecastArn and Status.Value - The value to match.For example, to list all jobs that export a forecast named electricityforecast, specify the following filter:
"Filters": \[ \{ "Condition": "IS", "Key": "ForecastArn", "Value": "arn:aws:forecast:us-west-2::forecast/electricityforecast" \} \]max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
}type nonrec explainability_export_summary = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the Explainability was created.
*)message : error_message option;Information about any errors that may have occurred during the Explainability export.
*)status : status option;The status of the Explainability export. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDdestination : data_destination option;explainability_export_name : name option;The name of the Explainability export
*)explainability_export_arn : arn option;The Amazon Resource Name (ARN) of the Explainability export.
*)}Provides a summary of the Explainability export properties used in the ListExplainabilityExports operation. To get a complete set of properties, call the DescribeExplainabilityExport operation, and provide the ExplainabilityExportArn.
type nonrec explainability_exports = explainability_export_summary listtype nonrec list_explainability_exports_response = {next_token : next_token option;Returns this token if the response is truncated. To retrieve the next set of results, use the token in the next request.
*)explainability_exports : explainability_exports option;An array of objects that summarize the properties of each Explainability export.
*)}type nonrec list_explainability_exports_request = {filters : filters option;An array of filters. For each filter, provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude resources that match the statement from the list. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT.Key - The name of the parameter to filter on. Valid values are ResourceArn and Status.Value - The value to match.max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
*)}type nonrec explainability_config = {time_point_granularity : time_point_granularity;To create an Explainability for all time points in your forecast horizon, use ALL. To create an Explainability for specific time points in your forecast horizon, use SPECIFIC.
Specify time points with the StartDateTime and EndDateTime parameters within the CreateExplainability operation.
time_series_granularity : time_series_granularity;To create an Explainability for all time series in your datasets, use ALL. To create an Explainability for specific time series in your datasets, use SPECIFIC.
Specify time series by uploading a CSV or Parquet file to an Amazon S3 bucket and set the location within the DataDestination data type.
}The ExplainabilityConfig data type defines the number of time series and time points included in CreateExplainability.
If you provide a predictor ARN for ResourceArn, you must set both TimePointGranularity and TimeSeriesGranularity to “ALL”. When creating Predictor Explainability, Amazon Forecast considers all time series and time points.
If you provide a forecast ARN for ResourceArn, you can set TimePointGranularity and TimeSeriesGranularity to either “ALL” or “Specific”.
type nonrec explainability_summary = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the Explainability was created.
*)message : message option;Information about any errors that may have occurred during the Explainability creation process.
*)status : status option;The status of the Explainability. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDexplainability_config : explainability_config option;The configuration settings that define the granularity of time series and time points for the Explainability.
*)resource_arn : arn option;The Amazon Resource Name (ARN) of the Predictor or Forecast used to create the Explainability.
*)explainability_name : name option;The name of the Explainability.
*)explainability_arn : arn option;The Amazon Resource Name (ARN) of the Explainability.
*)}Provides a summary of the Explainability properties used in the ListExplainabilities operation. To get a complete set of properties, call the DescribeExplainability operation, and provide the listed ExplainabilityArn.
type nonrec explainabilities = explainability_summary listtype nonrec list_explainabilities_response = {next_token : next_token option;Returns this token if the response is truncated. To retrieve the next set of results, use the token in the next request.
*)explainabilities : explainabilities option;An array of objects that summarize the properties of each Explainability resource.
*)}type nonrec list_explainabilities_request = {filters : filters option;An array of filters. For each filter, provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the resources that match the statement from the list. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT.Key - The name of the parameter to filter on. Valid values are ResourceArn and Status.Value - The value to match.max_results : max_results option;The number of items returned in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
*)}type nonrec dataset_summary = {last_modification_time : timestamp option;When you create a dataset, LastModificationTime is the same as CreationTime. While data is being imported to the dataset, LastModificationTime is the current time of the ListDatasets call. After a CreateDatasetImportJob operation has finished, LastModificationTime is when the import job completed or failed.
creation_time : timestamp option;When the dataset was created.
*)domain : domain option;The domain associated with the dataset.
*)dataset_type : dataset_type option;The dataset type.
*)dataset_name : name option;The name of the dataset.
*)dataset_arn : arn option;The Amazon Resource Name (ARN) of the dataset.
*)}Provides a summary of the dataset properties used in the ListDatasets operation. To get the complete set of properties, call the DescribeDataset operation, and provide the DatasetArn.
type nonrec datasets = dataset_summary listtype nonrec list_datasets_response = {next_token : next_token option;If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.
*)datasets : datasets option;An array of objects that summarize each dataset's properties.
*)}type nonrec list_datasets_request = {max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
}type nonrec dataset_import_job_summary = {import_mode : import_mode option;The import mode of the dataset import job, FULL or INCREMENTAL.
*)last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the dataset import job was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : status option;The status of the dataset import job. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDCREATE_STOPPING, CREATE_STOPPEDdata_source : data_source option;The location of the training data to import and an Identity and Access Management (IAM) role that Amazon Forecast can assume to access the data. The training data must be stored in an Amazon S3 bucket.
If encryption is used, DataSource includes an Key Management Service (KMS) key.
dataset_import_job_name : name option;The name of the dataset import job.
*)dataset_import_job_arn : arn option;The Amazon Resource Name (ARN) of the dataset import job.
*)}Provides a summary of the dataset import job properties used in the ListDatasetImportJobs operation. To get the complete set of properties, call the DescribeDatasetImportJob operation, and provide the DatasetImportJobArn.
type nonrec dataset_import_jobs = dataset_import_job_summary listtype nonrec list_dataset_import_jobs_response = {next_token : next_token option;If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.
*)dataset_import_jobs : dataset_import_jobs option;An array of objects that summarize each dataset import job's properties.
*)}type nonrec list_dataset_import_jobs_request = {filters : filters option;An array of filters. For each filter, you provide a condition and a match statement. The condition is either IS or IS_NOT, which specifies whether to include or exclude the datasets that match the statement from the list, respectively. The match statement consists of a key and a value.
Filter properties
Condition - The condition to apply. Valid values are IS and IS_NOT. To include the datasets that match the statement, specify IS. To exclude matching datasets, specify IS_NOT.Key - The name of the parameter to filter on. Valid values are DatasetArn and Status.Value - The value to match.For example, to list all dataset import jobs whose status is ACTIVE, you specify the following filter:
"Filters": [ { "Condition": "IS", "Key": "Status", "Value": "ACTIVE" } ]
max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
}type nonrec dataset_group_summary = {last_modification_time : timestamp option;When the dataset group was created or last updated from a call to the UpdateDatasetGroup operation. While the dataset group is being updated, LastModificationTime is the current time of the ListDatasetGroups call.
creation_time : timestamp option;When the dataset group was created.
*)dataset_group_name : name option;The name of the dataset group.
*)dataset_group_arn : arn option;The Amazon Resource Name (ARN) of the dataset group.
*)}Provides a summary of the dataset group properties used in the ListDatasetGroups operation. To get the complete set of properties, call the DescribeDatasetGroup operation, and provide the DatasetGroupArn.
type nonrec dataset_groups = dataset_group_summary listtype nonrec list_dataset_groups_response = {next_token : next_token option;If the response is truncated, Amazon Forecast returns this token. To retrieve the next set of results, use the token in the next request.
*)dataset_groups : dataset_groups option;An array of objects that summarize each dataset group's properties.
*)}type nonrec list_dataset_groups_request = {max_results : max_results option;The number of items to return in the response.
*)next_token : next_token option;If the result of the previous request was truncated, the response includes a NextToken. To retrieve the next set of results, use the token in the next request. Tokens expire after 24 hours.
}type nonrec input_data_config = {supplementary_features : supplementary_features option;An array of supplementary features. The only supported feature is a holiday calendar.
*)dataset_group_arn : arn;The Amazon Resource Name (ARN) of the dataset group.
*)}This object belongs to the CreatePredictor operation. If you created your predictor with CreateAutoPredictor, see DataConfig.
The data used to train a predictor. The data includes a dataset group and any supplementary features. You specify this object in the CreatePredictor request.
type nonrec hyper_parameter_tuning_job_config = {parameter_ranges : parameter_ranges option;Specifies the ranges of valid values for the hyperparameters.
*)}Configuration information for a hyperparameter tuning job. You specify this object in the CreatePredictor request.
A hyperparameter is a parameter that governs the model training process. You set hyperparameters before training starts, unlike model parameters, which are determined during training. The values of the hyperparameters effect which values are chosen for the model parameters.
In a hyperparameter tuning job, Amazon Forecast chooses the set of hyperparameter values that optimize a specified metric. Forecast accomplishes this by running many training jobs over a range of hyperparameter values. The optimum set of values depends on the algorithm, the training data, and the specified metric objective.
type nonrec get_accuracy_metrics_response = {optimization_metric : optimization_metric option;The accuracy metric used to optimize the predictor.
*)auto_ml_override_strategy : auto_ml_override_strategy option;The LatencyOptimized AutoML override strategy is only available in private beta. Contact Amazon Web Services Support or your account manager to learn more about access privileges.
The AutoML strategy used to train the predictor. Unless LatencyOptimized is specified, the AutoML strategy optimizes predictor accuracy.
This parameter is only valid for predictors trained using AutoML.
*)is_auto_predictor : boolean_ option;Whether the predictor was created with CreateAutoPredictor.
predictor_evaluation_results : predictor_evaluation_results option;An array of results from evaluating the predictor.
*)}type nonrec get_accuracy_metrics_request = {predictor_arn : arn;The Amazon Resource Name (ARN) of the predictor to get metrics for.
*)}type nonrec forecast_types = forecast_type listtype nonrec forecast_dimensions = name listtype nonrec field_statistics = (string_ * statistics) listtype nonrec featurization_method_parameters =
(parameter_key * parameter_value) listtype nonrec featurization_method = {featurization_method_parameters : featurization_method_parameters option;The method parameters (key-value pairs), which are a map of override parameters. Specify these parameters to override the default values. Related Time Series attributes do not accept aggregation parameters.
The following list shows the parameters and their valid values for the "filling" featurization method for a Target Time Series dataset. Bold signifies the default value.
aggregation: sum, avg, first, min, maxfrontfill: nonemiddlefill: zero, nan (not a number), value, median, mean, min, maxbackfill: zero, nan, value, median, mean, min, maxThe following list shows the parameters and their valid values for a Related Time Series featurization method (there are no defaults):
middlefill: zero, value, median, mean, min, maxbackfill: zero, value, median, mean, min, maxfuturefill: zero, value, median, mean, min, maxTo set a filling method to a specific value, set the fill parameter to value and define the value in a corresponding _value parameter. For example, to set backfilling to a value of 2, include the following: "backfill": "value" and "backfill_value":"2".
featurization_method_name : featurization_method_name;The name of the method. The "filling" method is the only supported method.
*)}Provides information about the method that featurizes (transforms) a dataset field. The method is part of the FeaturizationPipeline of the Featurization object.
The following is an example of how you specify a FeaturizationMethod object.
{
"FeaturizationMethodName": "filling",
"FeaturizationMethodParameters": {"aggregation": "sum", "middlefill": "zero", "backfill": "zero"}
}
type nonrec featurization_pipeline = featurization_method listtype nonrec featurization = {featurization_pipeline : featurization_pipeline option;An array of one FeaturizationMethod object that specifies the feature transformation method.
attribute_name : name;The name of the schema attribute that specifies the data field to be featurized. Amazon Forecast supports the target field of the TARGET_TIME_SERIES and the RELATED_TIME_SERIES datasets. For example, for the RETAIL domain, the target is demand, and for the CUSTOM domain, the target is target_value. For more information, see howitworks-missing-values.
}This object belongs to the CreatePredictor operation. If you created your predictor with CreateAutoPredictor, see AttributeConfig.
Provides featurization (transformation) information for a dataset field. This object is part of the FeaturizationConfig object.
For example:
{
"AttributeName": "demand",
FeaturizationPipeline [ {
"FeaturizationMethodName": "filling",
"FeaturizationMethodParameters": {"aggregation": "avg", "backfill": "nan"}
} ]
}
type nonrec featurizations = featurization listtype nonrec featurization_config = {featurizations : featurizations option;An array of featurization (transformation) information for the fields of a dataset.
*)forecast_dimensions : forecast_dimensions option;An array of dimension (field) names that specify how to group the generated forecast.
For example, suppose that you are generating a forecast for item sales across all of your stores, and your dataset contains a store_id field. If you want the sales forecast for each item by store, you would specify store_id as the dimension.
All forecast dimensions specified in the TARGET_TIME_SERIES dataset don't need to be specified in the CreatePredictor request. All forecast dimensions specified in the RELATED_TIME_SERIES dataset must be specified in the CreatePredictor request.
forecast_frequency : frequency;The frequency of predictions in a forecast.
Valid intervals are an integer followed by Y (Year), M (Month), W (Week), D (Day), H (Hour), and min (Minute). For example, "1D" indicates every day and "15min" indicates every 15 minutes. You cannot specify a value that would overlap with the next larger frequency. That means, for example, you cannot specify a frequency of 60 minutes, because that is equivalent to 1 hour. The valid values for each frequency are the following:
Thus, if you want every other week forecasts, specify "2W". Or, if you want quarterly forecasts, you specify "3M".
The frequency must be greater than or equal to the TARGET_TIME_SERIES dataset frequency.
When a RELATED_TIME_SERIES dataset is provided, the frequency must be equal to the TARGET_TIME_SERIES dataset frequency.
*)}This object belongs to the CreatePredictor operation. If you created your predictor with CreateAutoPredictor, see AttributeConfig.
In a CreatePredictor operation, the specified algorithm trains a model using the specified dataset group. You can optionally tell the operation to modify data fields prior to training a model. These modifications are referred to as featurization.
You define featurization using the FeaturizationConfig object. You specify an array of transformations, one for each field that you want to featurize. You then include the FeaturizationConfig object in your CreatePredictor request. Amazon Forecast applies the featurization to the TARGET_TIME_SERIES and RELATED_TIME_SERIES datasets before model training.
You can create multiple featurization configurations. For example, you might call the CreatePredictor operation twice by specifying different featurization configurations.
type nonrec explainability_info = {status : status option;The status of the Explainability. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDexplainability_arn : arn option;The Amazon Resource Name (ARN) of the Explainability.
*)}Provides information about the Explainability resource.
type nonrec evaluation_parameters = {back_test_window_offset : integer option;The point from the end of the dataset where you want to split the data for model training and testing (evaluation). Specify the value as the number of data points. The default is the value of the forecast horizon. BackTestWindowOffset can be used to mimic a past virtual forecast start date. This value must be greater than or equal to the forecast horizon and less than half of the TARGET_TIME_SERIES dataset length.
ForecastHorizon <= BackTestWindowOffset < 1/2 * TARGET_TIME_SERIES dataset length
number_of_backtest_windows : integer option;The number of times to split the input data. The default is 1. Valid values are 1 through 5.
*)}Parameters that define how to split a dataset into training data and testing data, and the number of iterations to perform. These parameters are specified in the predefined algorithms but you can override them in the CreatePredictor request.
type nonrec encryption_config = {kms_key_arn : kms_key_arn;The Amazon Resource Name (ARN) of the KMS key.
*)role_arn : arn;The ARN of the IAM role that Amazon Forecast can assume to access the KMS key.
Passing a role across Amazon Web Services accounts is not allowed. If you pass a role that isn't in your account, you get an InvalidInputException error.
}An Key Management Service (KMS) key and an Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key. You can specify this optional object in the CreateDataset and CreatePredictor requests.
type nonrec describe_what_if_forecast_response = {forecast_types : forecast_types option;The quantiles at which probabilistic forecasts are generated. You can specify up to five quantiles per what-if forecast in the CreateWhatIfForecast operation. If you didn't specify quantiles, the default values are ["0.1", "0.5", "0.9"].
time_series_replacements_data_source : time_series_replacements_data_source
option;An array of S3Config, Schema, and Format elements that describe the replacement time series.
time_series_transformations : time_series_transformations option;An array of Action and TimeSeriesConditions elements that describe what transformations were applied to which time series.
last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the what-if forecast was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : string_ option;The status of the what-if forecast. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the what-if forecast must be ACTIVE before you can access the forecast.
estimated_time_remaining_in_minutes : long option;The approximate time remaining to complete the what-if forecast, in minutes.
*)what_if_analysis_arn : arn option;The Amazon Resource Name (ARN) of the what-if analysis that contains this forecast.
*)what_if_forecast_arn : long_arn option;The Amazon Resource Name (ARN) of the what-if forecast.
*)what_if_forecast_name : name option;The name of the what-if forecast.
*)}type nonrec describe_what_if_forecast_request = {what_if_forecast_arn : long_arn;The Amazon Resource Name (ARN) of the what-if forecast that you are interested in.
*)}type nonrec describe_what_if_forecast_export_response = {format : format option;The format of the exported data, CSV or PARQUET.
*)last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.estimated_time_remaining_in_minutes : long option;The approximate time remaining to complete the what-if forecast export, in minutes.
*)creation_time : timestamp option;When the what-if forecast export was created.
*)status : status option;The status of the what-if forecast. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the what-if forecast export must be ACTIVE before you can access the forecast export.
message : message option;If an error occurred, an informational message about the error.
*)destination : data_destination option;what_if_forecast_arns : long_arn_list option;An array of Amazon Resource Names (ARNs) that represent all of the what-if forecasts exported in this resource.
*)what_if_forecast_export_name : name option;The name of the what-if forecast export.
*)what_if_forecast_export_arn : long_arn option;The Amazon Resource Name (ARN) of the what-if forecast export.
*)}type nonrec describe_what_if_forecast_export_request = {what_if_forecast_export_arn : long_arn;The Amazon Resource Name (ARN) of the what-if forecast export that you are interested in.
*)}type nonrec describe_what_if_analysis_response = {time_series_selector : time_series_selector option;last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the what-if analysis was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : string_ option;The status of the what-if analysis. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the what-if analysis must be ACTIVE before you can access the analysis.
estimated_time_remaining_in_minutes : long option;The approximate time remaining to complete the what-if analysis, in minutes.
*)forecast_arn : arn option;The Amazon Resource Name (ARN) of the what-if forecast.
*)what_if_analysis_arn : arn option;The Amazon Resource Name (ARN) of the what-if analysis.
*)what_if_analysis_name : name option;The name of the what-if analysis.
*)}type nonrec describe_what_if_analysis_request = {what_if_analysis_arn : arn;The Amazon Resource Name (ARN) of the what-if analysis that you are interested in.
*)}type nonrec describe_predictor_response = {optimization_metric : optimization_metric option;The accuracy metric used to optimize the predictor.
*)last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the model training task was created.
*)message : message option;If an error occurred, an informational message about the error.
*)status : status option;The status of the predictor. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDCREATE_STOPPING, CREATE_STOPPEDThe Status of the predictor must be ACTIVE before you can use the predictor to create a forecast.
dataset_import_job_arns : arn_list option;An array of the ARNs of the dataset import jobs used to import training data for the predictor.
*)is_auto_predictor : boolean_ option;Whether the predictor was created with CreateAutoPredictor.
estimated_time_remaining_in_minutes : long option;The estimated time remaining in minutes for the predictor training job to complete.
*)predictor_execution_details : predictor_execution_details option;Details on the the status and results of the backtests performed to evaluate the accuracy of the predictor. You specify the number of backtests to perform when you call the operation.
*)encryption_config : encryption_config option;An Key Management Service (KMS) key and the Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.
*)featurization_config : featurization_config option;The featurization configuration.
*)input_data_config : input_data_config option;Describes the dataset group that contains the data to use to train the predictor.
*)hpo_config : hyper_parameter_tuning_job_config option;The hyperparameter override values for the algorithm.
*)evaluation_parameters : evaluation_parameters option;Used to override the default evaluation parameters of the specified algorithm. Amazon Forecast evaluates a predictor by splitting a dataset into training data and testing data. The evaluation parameters define how to perform the split and the number of iterations.
*)training_parameters : training_parameters option;The default training parameters or overrides selected during model training. When running AutoML or choosing HPO with CNN-QR or DeepAR+, the optimized values for the chosen hyperparameters are returned. For more information, see aws-forecast-choosing-recipes.
perform_hp_o : boolean_ option;Whether the predictor is set to perform hyperparameter optimization (HPO).
*)auto_ml_override_strategy : auto_ml_override_strategy option;The LatencyOptimized AutoML override strategy is only available in private beta. Contact Amazon Web Services Support or your account manager to learn more about access privileges.
The AutoML strategy used to train the predictor. Unless LatencyOptimized is specified, the AutoML strategy optimizes predictor accuracy.
This parameter is only valid for predictors trained using AutoML.
*)perform_auto_m_l : boolean_ option;Whether the predictor is set to perform AutoML.
*)forecast_types : forecast_types option;The forecast types used during predictor training. Default value is ["0.1","0.5","0.9"]
forecast_horizon : integer option;The number of time-steps of the forecast. The forecast horizon is also called the prediction length.
*)auto_ml_algorithm_arns : arn_list option;When PerformAutoML is specified, the ARN of the chosen algorithm.
algorithm_arn : arn option;The Amazon Resource Name (ARN) of the algorithm used for model training.
*)predictor_name : name option;The name of the predictor.
*)predictor_arn : name option;The ARN of the predictor.
*)}type nonrec describe_predictor_request = {predictor_arn : arn;The Amazon Resource Name (ARN) of the predictor that you want information about.
*)}type nonrec describe_predictor_backtest_export_job_response = {format : format option;The format of the exported data, CSV or PARQUET.
*)last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the predictor backtest export job was created.
*)status : status option;The status of the predictor backtest export job. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDmessage : message option;Information about any errors that may have occurred during the backtest export.
*)destination : data_destination option;predictor_arn : arn option;The Amazon Resource Name (ARN) of the predictor.
*)predictor_backtest_export_job_name : name option;The name of the predictor backtest export job.
*)predictor_backtest_export_job_arn : arn option;The Amazon Resource Name (ARN) of the predictor backtest export job.
*)}type nonrec describe_predictor_backtest_export_job_request = {predictor_backtest_export_job_arn : arn;The Amazon Resource Name (ARN) of the predictor backtest export job.
*)}type nonrec baseline = {predictor_baseline : predictor_baseline option;The initial accuracy metrics for the predictor you are monitoring. Use these metrics as a baseline for comparison purposes as you use your predictor and the metrics change.
*)}Metrics you can use as a baseline for comparison purposes. Use these metrics when you interpret monitoring results for an auto predictor.
type nonrec describe_monitor_response = {estimated_evaluation_time_remaining_in_minutes : long option;The estimated number of minutes remaining before the monitor resource finishes its current evaluation.
*)last_modification_time : timestamp option;The timestamp of the latest modification to the monitor.
*)creation_time : timestamp option;The timestamp for when the monitor resource was created.
*)message : message option;An error message, if any, for the monitor.
*)baseline : baseline option;Metrics you can use as a baseline for comparison purposes. Use these values you interpret monitoring results for an auto predictor.
*)last_evaluation_state : evaluation_state option;The state of the monitor's latest evaluation.
*)last_evaluation_time : timestamp option;The timestamp of the latest evaluation completed by the monitor.
*)status : status option;The status of the monitor resource.
*)resource_arn : arn option;The Amazon Resource Name (ARN) of the auto predictor being monitored.
*)monitor_arn : arn option;The Amazon Resource Name (ARN) of the monitor resource described.
*)monitor_name : name option;The name of the monitor.
*)}type nonrec describe_monitor_request = {monitor_arn : arn;The Amazon Resource Name (ARN) of the monitor resource to describe.
*)}type nonrec describe_forecast_response = {time_series_selector : time_series_selector option;The time series to include in the forecast.
*)last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the forecast creation task was created.
*)message : error_message option;If an error occurred, an informational message about the error.
*)status : string_ option;The status of the forecast. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the forecast must be ACTIVE before you can query or export the forecast.
estimated_time_remaining_in_minutes : long option;The estimated time remaining in minutes for the forecast job to complete.
*)dataset_group_arn : arn option;The ARN of the dataset group that provided the data used to train the predictor.
*)predictor_arn : arn option;The ARN of the predictor used to generate the forecast.
*)forecast_types : forecast_types option;The quantiles at which probabilistic forecasts were generated.
*)forecast_name : name option;The name of the forecast.
*)forecast_arn : arn option;The forecast ARN as specified in the request.
*)}type nonrec describe_forecast_request = {forecast_arn : arn;The Amazon Resource Name (ARN) of the forecast.
*)}type nonrec describe_forecast_export_job_response = {format : format option;The format of the exported data, CSV or PARQUET.
*)last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the forecast export job was created.
*)status : status option;The status of the forecast export job. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDThe Status of the forecast export job must be ACTIVE before you can access the forecast in your S3 bucket.
message : message option;If an error occurred, an informational message about the error.
*)destination : data_destination option;The path to the Amazon Simple Storage Service (Amazon S3) bucket where the forecast is exported.
*)forecast_arn : arn option;The Amazon Resource Name (ARN) of the exported forecast.
*)forecast_export_job_name : name option;The name of the forecast export job.
*)forecast_export_job_arn : arn option;The ARN of the forecast export job.
*)}type nonrec describe_forecast_export_job_request = {forecast_export_job_arn : arn;The Amazon Resource Name (ARN) of the forecast export job.
*)}type nonrec describe_explainability_response = {last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the Explainability resource was created.
*)status : status option;The status of the Explainability resource. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDmessage : message option;If an error occurred, a message about the error.
*)estimated_time_remaining_in_minutes : long option;The estimated time remaining in minutes for the CreateExplainability job to complete.
end_date_time : local_date_time option;If TimePointGranularity is set to SPECIFIC, the last time point in the Explainability.
start_date_time : local_date_time option;If TimePointGranularity is set to SPECIFIC, the first time point in the Explainability.
schema : schema option;data_source : data_source option;enable_visualization : boolean_ option;Whether the visualization was enabled for the Explainability resource.
*)explainability_config : explainability_config option;The configuration settings that define the granularity of time series and time points for the Explainability.
*)resource_arn : arn option;The Amazon Resource Name (ARN) of the Predictor or Forecast used to create the Explainability resource.
*)explainability_name : name option;The name of the Explainability.
*)explainability_arn : arn option;The Amazon Resource Name (ARN) of the Explainability.
*)}type nonrec describe_explainability_request = {explainability_arn : arn;The Amazon Resource Name (ARN) of the Explaianability to describe.
*)}type nonrec describe_explainability_export_response = {format : format option;The format of the exported data, CSV or PARQUET.
*)last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the Explainability export was created.
*)status : status option;The status of the Explainability export. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDmessage : message option;Information about any errors that occurred during the export.
*)destination : data_destination option;explainability_arn : arn option;The Amazon Resource Name (ARN) of the Explainability export.
*)explainability_export_name : name option;The name of the Explainability export.
*)explainability_export_arn : arn option;The Amazon Resource Name (ARN) of the Explainability export.
*)}type nonrec describe_explainability_export_request = {explainability_export_arn : arn;The Amazon Resource Name (ARN) of the Explainability export.
*)}type nonrec describe_dataset_response = {last_modification_time : timestamp option;When you create a dataset, LastModificationTime is the same as CreationTime. While data is being imported to the dataset, LastModificationTime is the current time of the DescribeDataset call. After a CreateDatasetImportJob operation has finished, LastModificationTime is when the import job completed or failed.
creation_time : timestamp option;When the dataset was created.
*)status : status option;The status of the dataset. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDUPDATE_PENDING, UPDATE_IN_PROGRESS, UPDATE_FAILEDThe UPDATE states apply while data is imported to the dataset from a call to the CreateDatasetImportJob operation and reflect the status of the dataset import job. For example, when the import job status is CREATE_IN_PROGRESS, the status of the dataset is UPDATE_IN_PROGRESS.
The Status of the dataset must be ACTIVE before you can import training data.
encryption_config : encryption_config option;The Key Management Service (KMS) key and the Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.
*)schema : schema option;An array of SchemaAttribute objects that specify the dataset fields. Each SchemaAttribute specifies the name and data type of a field.
data_frequency : frequency option;The frequency of data collection.
Valid intervals are Y (Year), M (Month), W (Week), D (Day), H (Hour), 30min (30 minutes), 15min (15 minutes), 10min (10 minutes), 5min (5 minutes), and 1min (1 minute). For example, "M" indicates every month and "30min" indicates every 30 minutes.
*)dataset_type : dataset_type option;The dataset type.
*)domain : domain option;The domain associated with the dataset.
*)dataset_name : name option;The name of the dataset.
*)dataset_arn : arn option;The Amazon Resource Name (ARN) of the dataset.
*)}type nonrec describe_dataset_request = {dataset_arn : arn;The Amazon Resource Name (ARN) of the dataset.
*)}type nonrec describe_dataset_import_job_response = {import_mode : import_mode option;The import mode of the dataset import job, FULL or INCREMENTAL.
*)format : format option;The format of the imported data, CSV or PARQUET.
*)last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;When the dataset import job was created.
*)message : message option;If an error occurred, an informational message about the error.
*)status : status option;The status of the dataset import job. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDCREATE_STOPPING, CREATE_STOPPEDdata_size : double option;The size of the dataset in gigabytes (GB) after the import job has finished.
*)field_statistics : field_statistics option;Statistical information about each field in the input data.
*)estimated_time_remaining_in_minutes : long option;The estimated time remaining in minutes for the dataset import job to complete.
*)data_source : data_source option;The location of the training data to import and an Identity and Access Management (IAM) role that Amazon Forecast can assume to access the data.
If encryption is used, DataSource includes an Key Management Service (KMS) key.
geolocation_format : geolocation_format option;The format of the geolocation attribute. Valid Values:"LAT_LONG" and "CC_POSTALCODE".
use_geolocation_for_time_zone : use_geolocation_for_time_zone option;Whether TimeZone is automatically derived from the geolocation attribute.
time_zone : time_zone option;The single time zone applied to every item in the dataset
*)timestamp_format : timestamp_format option;The format of timestamps in the dataset. The format that you specify depends on the DataFrequency specified when the dataset was created. The following formats are supported
"yyyy-MM-dd"
For the following data frequencies: Y, M, W, and D
"yyyy-MM-dd HH:mm:ss"
For the following data frequencies: H, 30min, 15min, and 1min; and optionally, for: Y, M, W, and D
dataset_arn : arn option;The Amazon Resource Name (ARN) of the dataset that the training data was imported to.
*)dataset_import_job_arn : arn option;The ARN of the dataset import job.
*)dataset_import_job_name : name option;The name of the dataset import job.
*)}type nonrec describe_dataset_import_job_request = {dataset_import_job_arn : arn;The Amazon Resource Name (ARN) of the dataset import job.
*)}type nonrec describe_dataset_group_response = {last_modification_time : timestamp option;When the dataset group was created or last updated from a call to the UpdateDatasetGroup operation. While the dataset group is being updated, LastModificationTime is the current time of the DescribeDatasetGroup call.
creation_time : timestamp option;When the dataset group was created.
*)status : status option;The status of the dataset group. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDUPDATE_PENDING, UPDATE_IN_PROGRESS, UPDATE_FAILEDThe UPDATE states apply when you call the UpdateDatasetGroup operation.
The Status of the dataset group must be ACTIVE before you can use the dataset group to create a predictor.
domain : domain option;The domain associated with the dataset group.
*)dataset_arns : arn_list option;An array of Amazon Resource Names (ARNs) of the datasets contained in the dataset group.
*)dataset_group_arn : arn option;The ARN of the dataset group.
*)dataset_group_name : name option;The name of the dataset group.
*)}type nonrec describe_dataset_group_request = {dataset_group_arn : arn;The Amazon Resource Name (ARN) of the dataset group.
*)}type nonrec attribute_config = {transformations : transformations;The method parameters (key-value pairs), which are a map of override parameters. Specify these parameters to override the default values. Related Time Series attributes do not accept aggregation parameters.
The following list shows the parameters and their valid values for the "filling" featurization method for a Target Time Series dataset. Default values are bolded.
aggregation: sum, avg, first, min, maxfrontfill: nonemiddlefill: zero, nan (not a number), value, median, mean, min, maxbackfill: zero, nan, value, median, mean, min, maxThe following list shows the parameters and their valid values for a Related Time Series featurization method (there are no defaults):
middlefill: zero, value, median, mean, min, maxbackfill: zero, value, median, mean, min, maxfuturefill: zero, value, median, mean, min, maxTo set a filling method to a specific value, set the fill parameter to value and define the value in a corresponding _value parameter. For example, to set backfilling to a value of 2, include the following: "backfill": "value" and "backfill_value":"2".
attribute_name : name;The name of the attribute as specified in the schema. Amazon Forecast supports the target field of the target time series and the related time series datasets. For example, for the RETAIL domain, the target is demand.
}Provides information about the method used to transform attributes.
The following is an example using the RETAIL domain:
{
"AttributeName": "demand",
"Transformations": {"aggregation": "sum", "middlefill": "zero", "backfill": "zero"}
}
type nonrec attribute_configs = attribute_config listtype nonrec additional_dataset = {configuration : configuration option;Weather Index
To enable the Weather Index, do not specify a value for Configuration.
Holidays
Holidays
To enable Holidays, set CountryCode to one of the following two-letter country codes:
name : name;The name of the additional dataset. Valid names: "holiday" and "weather".
}Describes an additional dataset. This object is part of the DataConfig object. Forecast supports the Weather Index and Holidays additional datasets.
Weather Index
The Amazon Forecast Weather Index is a built-in dataset that incorporates historical and projected weather information into your model. The Weather Index supplements your datasets with over two years of historical weather data and up to 14 days of projected weather data. For more information, see Amazon Forecast Weather Index.
Holidays
Holidays is a built-in dataset that incorporates national holiday information into your model. It provides native support for the holiday calendars of 66 countries. To view the holiday calendars, refer to the Jollyday library. For more information, see Holidays Featurization.
type nonrec additional_datasets = additional_dataset listtype nonrec data_config = {additional_datasets : additional_datasets option;Additional built-in datasets like Holidays and the Weather Index.
*)attribute_configs : attribute_configs option;Aggregation and filling options for attributes in your dataset group.
*)dataset_group_arn : arn;The ARN of the dataset group used to train the predictor.
*)}The data configuration for your dataset group and any additional datasets.
type nonrec describe_auto_predictor_response = {time_alignment_boundary : time_alignment_boundary option;The time boundary Forecast uses when aggregating data.
*)monitor_info : monitor_info option;A object with the Amazon Resource Name (ARN) and status of the monitor resource.
*)explainability_info : explainability_info option;Provides the status and ARN of the Predictor Explainability.
*)optimization_metric : optimization_metric option;The accuracy metric used to optimize the predictor.
*)last_modification_time : timestamp option;The last time the resource was modified. The timestamp depends on the status of the job:
CREATE_PENDING - The CreationTime.CREATE_IN_PROGRESS - The current timestamp.CREATE_STOPPING - The current timestamp.CREATE_STOPPED - When the job stopped.ACTIVE or CREATE_FAILED - When the job finished or failed.creation_time : timestamp option;The timestamp of the CreateAutoPredictor request.
*)message : message option;In the event of an error, a message detailing the cause of the error.
*)status : status option;The status of the predictor. States include:
ACTIVECREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILEDCREATE_STOPPING, CREATE_STOPPEDDELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILEDestimated_time_remaining_in_minutes : long option;The estimated time remaining in minutes for the predictor training job to complete.
*)reference_predictor_summary : reference_predictor_summary option;The ARN and state of the reference predictor. This parameter is only valid for retrained or upgraded predictors.
*)encryption_config : encryption_config option;data_config : data_config option;The data configuration for your dataset group and any additional datasets.
*)dataset_import_job_arns : arn_list option;An array of the ARNs of the dataset import jobs used to import training data for the predictor.
*)forecast_dimensions : forecast_dimensions option;An array of dimension (field) names that specify the attributes used to group your time series.
*)forecast_frequency : frequency option;The frequency of predictions in a forecast.
Valid intervals are Y (Year), M (Month), W (Week), D (Day), H (Hour), 30min (30 minutes), 15min (15 minutes), 10min (10 minutes), 5min (5 minutes), and 1min (1 minute). For example, "Y" indicates every year and "5min" indicates every five minutes.
*)forecast_types : forecast_types option;The forecast types used during predictor training. Default value is ["0.1","0.5","0.9"].
*)forecast_horizon : integer option;The number of time-steps that the model predicts. The forecast horizon is also called the prediction length.
*)predictor_name : name option;The name of the predictor.
*)predictor_arn : arn option;The Amazon Resource Name (ARN) of the predictor
*)}type nonrec describe_auto_predictor_request = {predictor_arn : arn;The Amazon Resource Name (ARN) of the predictor.
*)}type nonrec delete_what_if_forecast_request = {what_if_forecast_arn : long_arn;The Amazon Resource Name (ARN) of the what-if forecast that you want to delete.
*)}type nonrec delete_what_if_forecast_export_request = {what_if_forecast_export_arn : long_arn;The Amazon Resource Name (ARN) of the what-if forecast export that you want to delete.
*)}type nonrec delete_what_if_analysis_request = {what_if_analysis_arn : arn;The Amazon Resource Name (ARN) of the what-if analysis that you want to delete.
*)}type nonrec delete_resource_tree_request = {resource_arn : arn;The Amazon Resource Name (ARN) of the parent resource to delete. All child resources of the parent resource will also be deleted.
*)}type nonrec delete_predictor_request = {predictor_arn : arn;The Amazon Resource Name (ARN) of the predictor to delete.
*)}type nonrec delete_predictor_backtest_export_job_request = {predictor_backtest_export_job_arn : arn;The Amazon Resource Name (ARN) of the predictor backtest export job to delete.
*)}type nonrec delete_monitor_request = {monitor_arn : arn;The Amazon Resource Name (ARN) of the monitor resource to delete.
*)}type nonrec delete_forecast_request = {forecast_arn : arn;The Amazon Resource Name (ARN) of the forecast to delete.
*)}type nonrec delete_forecast_export_job_request = {forecast_export_job_arn : arn;The Amazon Resource Name (ARN) of the forecast export job to delete.
*)}type nonrec delete_explainability_request = {explainability_arn : arn;The Amazon Resource Name (ARN) of the Explainability resource to delete.
*)}type nonrec delete_explainability_export_request = {explainability_export_arn : arn;The Amazon Resource Name (ARN) of the Explainability export to delete.
*)}type nonrec delete_dataset_request = {dataset_arn : arn;The Amazon Resource Name (ARN) of the dataset to delete.
*)}type nonrec delete_dataset_import_job_request = {dataset_import_job_arn : arn;The Amazon Resource Name (ARN) of the dataset import job to delete.
*)}type nonrec delete_dataset_group_request = {dataset_group_arn : arn;The Amazon Resource Name (ARN) of the dataset group to delete.
*)}type nonrec create_what_if_forecast_response = {what_if_forecast_arn : long_arn option;The Amazon Resource Name (ARN) of the what-if forecast.
*)}type nonrec create_what_if_forecast_request = {time_series_replacements_data_source : time_series_replacements_data_source
option;The replacement time series dataset, which contains the rows that you want to change in the related time series dataset. A replacement time series does not need to contain all rows that are in the baseline related time series. Include only the rows (measure-dimension combinations) that you want to include in the what-if forecast.
This dataset is merged with the original time series to create a transformed dataset that is used for the what-if analysis.
This dataset should contain the items to modify (such as item_id or workforce_type), any relevant dimensions, the timestamp column, and at least one of the related time series columns. This file should not contain duplicate timestamps for the same time series.
Timestamps and item_ids not included in this dataset are not included in the what-if analysis.
*)time_series_transformations : time_series_transformations option;The transformations that are applied to the baseline time series. Each transformation contains an action and a set of conditions. An action is applied only when all conditions are met. If no conditions are provided, the action is applied to all items.
*)what_if_analysis_arn : arn;The Amazon Resource Name (ARN) of the what-if analysis.
*)what_if_forecast_name : name;The name of the what-if forecast. Names must be unique within each what-if analysis.
*)}type nonrec create_what_if_forecast_export_response = {what_if_forecast_export_arn : long_arn option;The Amazon Resource Name (ARN) of the what-if forecast.
*)}type nonrec create_what_if_forecast_export_request = {format : format option;The format of the exported data, CSV or PARQUET.
*)destination : data_destination;The location where you want to save the forecast and an Identity and Access Management (IAM) role that Amazon Forecast can assume to access the location. The forecast must be exported to an Amazon S3 bucket.
If encryption is used, Destination must include an Key Management Service (KMS) key. The IAM role must allow Amazon Forecast permission to access the key.
what_if_forecast_arns : what_if_forecast_arn_list_for_export;The list of what-if forecast Amazon Resource Names (ARNs) to export.
*)what_if_forecast_export_name : name;The name of the what-if forecast to export.
*)}type nonrec create_what_if_analysis_response = {what_if_analysis_arn : arn option;The Amazon Resource Name (ARN) of the what-if analysis.
*)}type nonrec create_what_if_analysis_request = {time_series_selector : time_series_selector option;Defines the set of time series that are used in the what-if analysis with a TimeSeriesIdentifiers object. What-if analyses are performed only for the time series in this object.
The TimeSeriesIdentifiers object needs the following information:
DataSourceFormatSchemaforecast_arn : arn;The Amazon Resource Name (ARN) of the baseline forecast.
*)what_if_analysis_name : name;The name of the what-if analysis. Each name must be unique.
*)}type nonrec create_predictor_response = {predictor_arn : arn option;The Amazon Resource Name (ARN) of the predictor.
*)}type nonrec create_predictor_request = {optimization_metric : optimization_metric option;The accuracy metric used to optimize the predictor.
*)encryption_config : encryption_config option;An Key Management Service (KMS) key and the Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.
*)featurization_config : featurization_config;The featurization configuration.
*)input_data_config : input_data_config;Describes the dataset group that contains the data to use to train the predictor.
*)hpo_config : hyper_parameter_tuning_job_config option;Provides hyperparameter override values for the algorithm. If you don't provide this parameter, Amazon Forecast uses default values. The individual algorithms specify which hyperparameters support hyperparameter optimization (HPO). For more information, see aws-forecast-choosing-recipes.
If you included the HPOConfig object, you must set PerformHPO to true.
evaluation_parameters : evaluation_parameters option;Used to override the default evaluation parameters of the specified algorithm. Amazon Forecast evaluates a predictor by splitting a dataset into training data and testing data. The evaluation parameters define how to perform the split and the number of iterations.
*)training_parameters : training_parameters option;The hyperparameters to override for model training. The hyperparameters that you can override are listed in the individual algorithms. For the list of supported algorithms, see aws-forecast-choosing-recipes.
perform_hp_o : boolean_ option;Whether to perform hyperparameter optimization (HPO). HPO finds optimal hyperparameter values for your training data. The process of performing HPO is known as running a hyperparameter tuning job.
The default value is false. In this case, Amazon Forecast uses default hyperparameter values from the chosen algorithm.
To override the default values, set PerformHPO to true and, optionally, supply the HyperParameterTuningJobConfig object. The tuning job specifies a metric to optimize, which hyperparameters participate in tuning, and the valid range for each tunable hyperparameter. In this case, you are required to specify an algorithm and PerformAutoML must be false.
The following algorithms support HPO:
auto_ml_override_strategy : auto_ml_override_strategy option;The LatencyOptimized AutoML override strategy is only available in private beta. Contact Amazon Web Services Support or your account manager to learn more about access privileges.
Used to overide the default AutoML strategy, which is to optimize predictor accuracy. To apply an AutoML strategy that minimizes training time, use LatencyOptimized.
This parameter is only valid for predictors trained using AutoML.
*)perform_auto_m_l : boolean_ option;Whether to perform AutoML. When Amazon Forecast performs AutoML, it evaluates the algorithms it provides and chooses the best algorithm and configuration for your training dataset.
The default value is false. In this case, you are required to specify an algorithm.
Set PerformAutoML to true to have Amazon Forecast perform AutoML. This is a good option if you aren't sure which algorithm is suitable for your training data. In this case, PerformHPO must be false.
forecast_types : forecast_types option;Specifies the forecast types used to train a predictor. You can specify up to five forecast types. Forecast types can be quantiles from 0.01 to 0.99, by increments of 0.01 or higher. You can also specify the mean forecast with mean.
The default value is ["0.10", "0.50", "0.9"].
forecast_horizon : integer;Specifies the number of time-steps that the model is trained to predict. The forecast horizon is also called the prediction length.
For example, if you configure a dataset for daily data collection (using the DataFrequency parameter of the CreateDataset operation) and set the forecast horizon to 10, the model returns predictions for 10 days.
The maximum forecast horizon is the lesser of 500 time-steps or 1/3 of the TARGET_TIME_SERIES dataset length.
*)algorithm_arn : arn option;The Amazon Resource Name (ARN) of the algorithm to use for model training. Required if PerformAutoML is not set to true.
Supported algorithms:
arn:aws:forecast:::algorithm/ARIMAarn:aws:forecast:::algorithm/CNN-QRarn:aws:forecast:::algorithm/Deep_AR_Plusarn:aws:forecast:::algorithm/ETSarn:aws:forecast:::algorithm/NPTSarn:aws:forecast:::algorithm/Prophetpredictor_name : name;A name for the predictor.
*)}type nonrec create_predictor_backtest_export_job_response = {predictor_backtest_export_job_arn : arn option;The Amazon Resource Name (ARN) of the predictor backtest export job that you want to export.
*)}type nonrec create_predictor_backtest_export_job_request = {format : format option;The format of the exported data, CSV or PARQUET. The default value is CSV.
*)destination : data_destination;predictor_arn : arn;The Amazon Resource Name (ARN) of the predictor that you want to export.
*)predictor_backtest_export_job_name : name;The name for the backtest export job.
*)}type nonrec create_monitor_response = {monitor_arn : arn option;The Amazon Resource Name (ARN) of the monitor resource.
*)}type nonrec create_forecast_response = {forecast_arn : arn option;The Amazon Resource Name (ARN) of the forecast.
*)}type nonrec create_forecast_request = {time_series_selector : time_series_selector option;Defines the set of time series that are used to create the forecasts in a TimeSeriesIdentifiers object.
The TimeSeriesIdentifiers object needs the following information:
DataSourceFormatSchemaforecast_types : forecast_types option;The quantiles at which probabilistic forecasts are generated. You can currently specify up to 5 quantiles per forecast. Accepted values include 0.01 to 0.99 (increments of .01 only) and mean. The mean forecast is different from the median (0.50) when the distribution is not symmetric (for example, Beta and Negative Binomial).
The default quantiles are the quantiles you specified during predictor creation. If you didn't specify quantiles, the default values are ["0.1", "0.5", "0.9"].
predictor_arn : arn;The Amazon Resource Name (ARN) of the predictor to use to generate the forecast.
*)forecast_name : name;A name for the forecast.
*)}type nonrec create_forecast_export_job_response = {forecast_export_job_arn : arn option;The Amazon Resource Name (ARN) of the export job.
*)}type nonrec create_forecast_export_job_request = {format : format option;The format of the exported data, CSV or PARQUET. The default value is CSV.
*)destination : data_destination;The location where you want to save the forecast and an Identity and Access Management (IAM) role that Amazon Forecast can assume to access the location. The forecast must be exported to an Amazon S3 bucket.
If encryption is used, Destination must include an Key Management Service (KMS) key. The IAM role must allow Amazon Forecast permission to access the key.
forecast_arn : arn;The Amazon Resource Name (ARN) of the forecast that you want to export.
*)forecast_export_job_name : name;The name for the forecast export job.
*)}type nonrec create_explainability_response = {explainability_arn : arn option;The Amazon Resource Name (ARN) of the Explainability.
*)}type nonrec create_explainability_request = {end_date_time : local_date_time option;If TimePointGranularity is set to SPECIFIC, define the last time point for the Explainability.
Use the following timestamp format: yyyy-MM-ddTHH:mm:ss (example: 2015-01-01T20:00:00)
*)start_date_time : local_date_time option;If TimePointGranularity is set to SPECIFIC, define the first point for the Explainability.
Use the following timestamp format: yyyy-MM-ddTHH:mm:ss (example: 2015-01-01T20:00:00)
*)enable_visualization : boolean_ option;Create an Explainability visualization that is viewable within the Amazon Web Services console.
*)schema : schema option;data_source : data_source option;explainability_config : explainability_config;The configuration settings that define the granularity of time series and time points for the Explainability.
*)resource_arn : arn;The Amazon Resource Name (ARN) of the Predictor or Forecast used to create the Explainability.
*)explainability_name : name;A unique name for the Explainability.
*)}type nonrec create_explainability_export_response = {explainability_export_arn : arn option;The Amazon Resource Name (ARN) of the export.
*)}type nonrec create_explainability_export_request = {format : format option;The format of the exported data, CSV or PARQUET.
*)destination : data_destination;explainability_arn : arn;The Amazon Resource Name (ARN) of the Explainability to export.
*)explainability_export_name : name;A unique name for the Explainability export.
*)}type nonrec create_dataset_response = {dataset_arn : arn option;The Amazon Resource Name (ARN) of the dataset.
*)}type nonrec create_dataset_request = {encryption_config : encryption_config option;An Key Management Service (KMS) key and the Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.
*)schema : schema;The schema for the dataset. The schema attributes and their order must match the fields in your data. The dataset Domain and DatasetType that you choose determine the minimum required fields in your training data. For information about the required fields for a specific dataset domain and type, see Dataset Domains and Dataset Types.
data_frequency : frequency option;The frequency of data collection. This parameter is required for RELATED_TIME_SERIES datasets.
Valid intervals are an integer followed by Y (Year), M (Month), W (Week), D (Day), H (Hour), and min (Minute). For example, "1D" indicates every day and "15min" indicates every 15 minutes. You cannot specify a value that would overlap with the next larger frequency. That means, for example, you cannot specify a frequency of 60 minutes, because that is equivalent to 1 hour. The valid values for each frequency are the following:
Thus, if you want every other week forecasts, specify "2W". Or, if you want quarterly forecasts, you specify "3M".
*)dataset_type : dataset_type;The dataset type. Valid values depend on the chosen Domain.
domain : domain;The domain associated with the dataset. When you add a dataset to a dataset group, this value and the value specified for the Domain parameter of the CreateDatasetGroup operation must match.
The Domain and DatasetType that you choose determine the fields that must be present in the training data that you import to the dataset. For example, if you choose the RETAIL domain and TARGET_TIME_SERIES as the DatasetType, Amazon Forecast requires item_id, timestamp, and demand fields to be present in your data. For more information, see Importing datasets.
dataset_name : name;A name for the dataset.
*)}type nonrec create_dataset_import_job_response = {dataset_import_job_arn : arn option;The Amazon Resource Name (ARN) of the dataset import job.
*)}type nonrec create_dataset_import_job_request = {import_mode : import_mode option;Specifies whether the dataset import job is a FULL or INCREMENTAL import. A FULL dataset import replaces all of the existing data with the newly imported data. An INCREMENTAL import appends the imported data to the existing data.
format : format option;The format of the imported data, CSV or PARQUET. The default value is CSV.
*)geolocation_format : geolocation_format option;The format of the geolocation attribute. The geolocation attribute can be formatted in one of two ways:
LAT_LONG - the latitude and longitude in decimal format (Example: 47.61_-122.33).CC_POSTALCODE (US Only) - the country code (US), followed by the 5-digit ZIP code (Example: US_98121).use_geolocation_for_time_zone : use_geolocation_for_time_zone option;Automatically derive time zone information from the geolocation attribute. This option is ideal for datasets that contain timestamps in multiple time zones and those timestamps are expressed in local time.
*)time_zone : time_zone option;A single time zone for every item in your dataset. This option is ideal for datasets with all timestamps within a single time zone, or if all timestamps are normalized to a single time zone.
Refer to the Joda-Time API for a complete list of valid time zone names.
*)timestamp_format : timestamp_format option;The format of timestamps in the dataset. The format that you specify depends on the DataFrequency specified when the dataset was created. The following formats are supported
"yyyy-MM-dd"
For the following data frequencies: Y, M, W, and D
"yyyy-MM-dd HH:mm:ss"
For the following data frequencies: H, 30min, 15min, and 1min; and optionally, for: Y, M, W, and D
If the format isn't specified, Amazon Forecast expects the format to be "yyyy-MM-dd HH:mm:ss".
*)data_source : data_source;The location of the training data to import and an Identity and Access Management (IAM) role that Amazon Forecast can assume to access the data. The training data must be stored in an Amazon S3 bucket.
If encryption is used, DataSource must include an Key Management Service (KMS) key and the IAM role must allow Amazon Forecast permission to access the key. The KMS key and IAM role must match those specified in the EncryptionConfig parameter of the CreateDataset operation.
dataset_arn : arn;The Amazon Resource Name (ARN) of the Amazon Forecast dataset that you want to import data to.
*)dataset_import_job_name : name;The name for the dataset import job. We recommend including the current timestamp in the name, for example, 20190721DatasetImport. This can help you avoid getting a ResourceAlreadyExistsException exception.
}type nonrec create_dataset_group_response = {dataset_group_arn : arn option;The Amazon Resource Name (ARN) of the dataset group.
*)}type nonrec create_dataset_group_request = {dataset_arns : arn_list option;An array of Amazon Resource Names (ARNs) of the datasets that you want to include in the dataset group.
*)domain : domain;The domain associated with the dataset group. When you add a dataset to a dataset group, this value and the value specified for the Domain parameter of the CreateDataset operation must match.
The Domain and DatasetType that you choose determine the fields that must be present in training data that you import to a dataset. For example, if you choose the RETAIL domain and TARGET_TIME_SERIES as the DatasetType, Amazon Forecast requires that item_id, timestamp, and demand fields are present in your data. For more information, see Dataset groups.
dataset_group_name : name;A name for the dataset group.
*)}type nonrec create_auto_predictor_response = {predictor_arn : arn option;The Amazon Resource Name (ARN) of the predictor.
*)}type nonrec create_auto_predictor_request = {time_alignment_boundary : time_alignment_boundary option;The time boundary Forecast uses to align and aggregate any data that doesn't align with your forecast frequency. Provide the unit of time and the time boundary as a key value pair. For more information on specifying a time boundary, see Specifying a Time Boundary. If you don't provide a time boundary, Forecast uses a set of Default Time Boundaries.
*)monitor_config : monitor_config option;The configuration details for predictor monitoring. Provide a name for the monitor resource to enable predictor monitoring.
Predictor monitoring allows you to see how your predictor's performance changes over time. For more information, see Predictor Monitoring.
*)explain_predictor : boolean_ option;Create an Explainability resource for the predictor.
*)optimization_metric : optimization_metric option;The accuracy metric used to optimize the predictor.
*)reference_predictor_arn : arn option;The ARN of the predictor to retrain or upgrade. This parameter is only used when retraining or upgrading a predictor. When creating a new predictor, do not specify a value for this parameter.
When upgrading or retraining a predictor, only specify values for the ReferencePredictorArn and PredictorName. The value for PredictorName must be a unique predictor name.
encryption_config : encryption_config option;data_config : data_config option;The data configuration for your dataset group and any additional datasets.
*)forecast_frequency : frequency option;The frequency of predictions in a forecast.
Valid intervals are an integer followed by Y (Year), M (Month), W (Week), D (Day), H (Hour), and min (Minute). For example, "1D" indicates every day and "15min" indicates every 15 minutes. You cannot specify a value that would overlap with the next larger frequency. That means, for example, you cannot specify a frequency of 60 minutes, because that is equivalent to 1 hour. The valid values for each frequency are the following:
Thus, if you want every other week forecasts, specify "2W". Or, if you want quarterly forecasts, you specify "3M".
The frequency must be greater than or equal to the TARGET_TIME_SERIES dataset frequency.
When a RELATED_TIME_SERIES dataset is provided, the frequency must be equal to the RELATED_TIME_SERIES dataset frequency.
*)forecast_dimensions : forecast_dimensions option;An array of dimension (field) names that specify how to group the generated forecast.
For example, if you are generating forecasts for item sales across all your stores, and your dataset contains a store_id field, you would specify store_id as a dimension to group sales forecasts for each store.
forecast_types : forecast_types option;The forecast types used to train a predictor. You can specify up to five forecast types. Forecast types can be quantiles from 0.01 to 0.99, by increments of 0.01 or higher. You can also specify the mean forecast with mean.
forecast_horizon : integer option;The number of time-steps that the model predicts. The forecast horizon is also called the prediction length.
The maximum forecast horizon is the lesser of 500 time-steps or 1/4 of the TARGET_TIME_SERIES dataset length. If you are retraining an existing AutoPredictor, then the maximum forecast horizon is the lesser of 500 time-steps or 1/3 of the TARGET_TIME_SERIES dataset length.
If you are upgrading to an AutoPredictor or retraining an existing AutoPredictor, you cannot update the forecast horizon parameter. You can meet this requirement by providing longer time-series in the dataset.
*)predictor_name : name;A unique name for the predictor
*)}