String name
The name of the hyperparameter to tune.
Double maxValue
The maximum tunable value of the hyperparameter.
Double minValue
The minimum tunable value of the hyperparameter.
String scalingType
The scale that hyperparameter tuning uses to search the hyperparameter range. For information about choosing a hyperparameter scale, see Hyperparameter Scaling. One of the following values:
Amazon Forecast hyperparameter tuning chooses the best scale for the hyperparameter.
Hyperparameter tuning searches the values in the hyperparameter range by using a linear scale.
Hyperparameter tuning searches the values in the hyperparameter range by using a logarithmic scale.
Logarithmic scaling works only for ranges that have only values greater than 0.
Hyperparemeter 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.
String datasetGroupName
A name for the dataset group.
String domain
The domain associated with the dataset group. 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
howitworks-datasets-groups.
List<E> datasetArns
An array of Amazon Resource Names (ARNs) of the datasets that you want to include in the dataset group.
String datasetGroupArn
The Amazon Resource Name (ARN) of the dataset group.
String datasetImportJobName
The name for the dataset import job. It is recommended to include the current timestamp in the name to guard
against getting a ResourceAlreadyExistsException exception, for example,
20190721DatasetImport.
String datasetArn
The Amazon Resource Name (ARN) of the Amazon Forecast dataset that you want to import data to.
DataSource dataSource
The location of the training data to import and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the data.
String timestampFormat
The format of timestamps in the dataset. Two formats are supported, dependent on the DataFrequency
specified when the dataset was created.
"yyyy-MM-dd"
For data frequencies: Y, M, W, and D
"yyyy-MM-dd HH:mm:ss"
For data frequencies: H, 30min, 15min, and 1min; and optionally, for: Y, M, W, and D
String datasetImportJobArn
The Amazon Resource Name (ARN) of the dataset import job.
String datasetName
A name for the dataset.
String domain
The domain associated with the dataset. 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 howitworks-datasets-groups.
String datasetType
The dataset type. Valid values depend on the chosen Domain.
String dataFrequency
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, "D" indicates every day and "15min" indicates every 15 minutes.
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
howitworks-domains-ds-types.
EncryptionConfig encryptionConfig
An AWS Key Management Service (KMS) key and the AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.
String datasetArn
The Amazon Resource Name (ARN) of the dataset.
String forecastExportJobName
The name for the forecast export job.
String forecastArn
The Amazon Resource Name (ARN) of the forecast that you want to export.
DataDestination destination
The path to the Amazon S3 bucket where you want to save the forecast and an AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the bucket.
String forecastExportJobArn
The Amazon Resource Name (ARN) of the export job.
String forecastArn
The Amazon Resource Name (ARN) of the forecast.
String predictorName
A name for the predictor.
String algorithmArn
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/ARIMA
arn:aws:forecast:::algorithm/Deep_AR_Plus
- supports hyperparameter optimization (HPO)
arn:aws:forecast:::algorithm/ETS
arn:aws:forecast:::algorithm/NPTS
arn:aws:forecast:::algorithm/Prophet
Integer forecastHorizon
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.
Boolean performAutoML
Whether to perform AutoML. The default value is false. In this case, you are required to specify an
algorithm.
If you want Amazon Forecast to evaluate the algorithms it provides and choose the best algorithm and
configuration for your training dataset, set PerformAutoML to true. This is a good
option if you aren't sure which algorithm is suitable for your application.
Boolean performHPO
Whether to perform hyperparameter optimization (HPO). HPO finds optimal hyperparameter values for your training data. The process of performing HPO is known as 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 supply the
HyperParameterTuningJobConfig object. The tuning job specifies an objective metric, the hyperparameters to
optimize, and the valid range for each hyperparameter.
The following algorithms support HPO:
DeepAR+
Map<K,V> trainingParameters
The training parameters to override for model training. The parameters that you can override are listed in the individual algorithms in aws-forecast-choosing-recipes.
EvaluationParameters evaluationParameters
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.
HyperParameterTuningJobConfig hPOConfig
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.
InputDataConfig inputDataConfig
Describes the dataset group that contains the data to use to train the predictor.
FeaturizationConfig featurizationConfig
The featurization configuration.
EncryptionConfig encryptionConfig
An AWS Key Management Service (KMS) key and the AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.
String predictorArn
The Amazon Resource Name (ARN) of the predictor.
S3Config s3Config
The path to an Amazon Simple Storage Service (Amazon S3) bucket along with the credentials to access the bucket.
String datasetGroupArn
The Amazon Resource Name (ARN) of the dataset group.
String datasetGroupName
The name of the dataset group.
Date creationTime
When the datase group was created.
Date lastModificationTime
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 query time.
String datasetImportJobArn
The Amazon Resource Name (ARN) of the dataset import job.
String datasetImportJobName
The name of the dataset import job.
DataSource dataSource
The location of the Amazon S3 bucket that contains the training data.
String status
The status of the dataset import job. The status is reflected in the status of the dataset. For example, when the
import job status is CREATE_IN_PROGRESS, the status of the dataset is
UPDATE_IN_PROGRESS. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
String message
If an error occurred, an informational message about the error.
Date creationTime
When the dataset import job was created.
Date lastModificationTime
Dependent on the status as follows:
CREATE_PENDING - same as CreationTime
CREATE_IN_PROGRESS - the current timestamp
ACTIVE or CREATE_FAILED - when the job finished or failed
String datasetArn
The Amazon Resource Name (ARN) of the dataset.
String datasetName
The name of the dataset.
String datasetType
The dataset type.
String domain
The domain associated with the dataset.
Date creationTime
When the dataset was created.
Date lastModificationTime
When the dataset is created, LastModificationTime is the same as CreationTime. After a
CreateDatasetImportJob operation is called, LastModificationTime is when the import job
finished or failed. While data is being imported to the dataset, LastModificationTime is the current
query time.
S3Config s3Config
The path to the training data stored in an Amazon Simple Storage Service (Amazon S3) bucket along with the credentials to access the data.
String datasetGroupArn
The Amazon Resource Name (ARN) of the dataset group to delete.
String datasetImportJobArn
The Amazon Resource Name (ARN) of the dataset import job to delete.
String datasetArn
The Amazon Resource Name (ARN) of the dataset to delete.
String forecastExportJobArn
The Amazon Resource Name (ARN) of the forecast export job to delete.
String forecastArn
The Amazon Resource Name (ARN) of the forecast to delete.
String predictorArn
The Amazon Resource Name (ARN) of the predictor to delete.
String datasetGroupArn
The Amazon Resource Name (ARN) of the dataset group.
String datasetGroupName
The name of the dataset group.
String datasetGroupArn
The ARN of the dataset group.
List<E> datasetArns
An array of Amazon Resource Names (ARNs) of the datasets contained in the dataset group.
String domain
The domain associated with the dataset group. 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
howitworks-datasets-groups.
String status
The status of the dataset group. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
UPDATE_PENDING, UPDATE_IN_PROGRESS, UPDATE_FAILED
The UPDATE states apply when the UpdateDatasetGroup operation is called.
The Status of the dataset group must be ACTIVE before creating a predictor using the
dataset group.
Date creationTime
When the dataset group was created.
Date lastModificationTime
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 query time.
String datasetImportJobArn
The Amazon Resource Name (ARN) of the dataset import job.
String datasetImportJobName
The name of the dataset import job.
String datasetImportJobArn
The ARN of the dataset import job.
String datasetArn
The Amazon Resource Name (ARN) of the dataset that the training data was imported to.
String timestampFormat
The format of timestamps in the dataset. Two formats are supported dependent on the DataFrequency
specified when the dataset was created.
"yyyy-MM-dd"
For data frequencies: Y, M, W, and D
"yyyy-MM-dd HH:mm:ss"
For data frequencies: H, 30min, 15min, and 1min; and optionally, for: Y, M, W, and D
DataSource dataSource
The location of the training data to import. The training data must be stored in an Amazon S3 bucket.
Map<K,V> fieldStatistics
Statistical information about each field in the input data.
Double dataSize
The size of the dataset in gigabytes (GB) after completion of the import job.
String status
The status of the dataset import job. The status is reflected in the status of the dataset. For example, when the
import job status is CREATE_IN_PROGRESS, the status of the dataset is
UPDATE_IN_PROGRESS. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
String message
If an error occurred, an informational message about the error.
Date creationTime
When the dataset import job was created.
Date lastModificationTime
Dependent on the status as follows:
CREATE_PENDING - same as CreationTime
CREATE_IN_PROGRESS - the current timestamp
ACTIVE or CREATE_FAILED - when the job finished or failed
String datasetArn
The Amazon Resource Name (ARN) of the dataset.
String datasetArn
The Amazon Resource Name (ARN) of the dataset.
String datasetName
The name of the dataset.
String domain
The dataset domain.
String datasetType
The dataset type.
String dataFrequency
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.
Schema schema
An array of SchemaAttribute objects that specify the dataset fields. Each
SchemaAttribute specifies the name and data type of a field.
EncryptionConfig encryptionConfig
An AWS Key Management Service (KMS) key and the AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.
String status
The status of the dataset. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
UPDATE_PENDING, UPDATE_IN_PROGRESS, UPDATE_FAILED
The UPDATE states apply while data is imported to the dataset from a call to the
CreateDatasetImportJob operation. During this time, the status reflects 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.
Date creationTime
When the dataset was created.
Date lastModificationTime
When the dataset is created, LastModificationTime is the same as CreationTime. After a
CreateDatasetImportJob operation is called, LastModificationTime is when the import job
finished or failed. While data is being imported to the dataset, LastModificationTime is the current
query time.
String forecastExportJobArn
The Amazon Resource Name (ARN) of the forecast export job.
String forecastExportJobArn
The ARN of the forecast export job.
String forecastExportJobName
The name of the forecast export job.
String forecastArn
The Amazon Resource Name (ARN) of the exported forecast.
DataDestination destination
The path to the AWS S3 bucket where the forecast is exported.
String message
If an error occurred, an informational message about the error.
String status
The status of the forecast export job. One of the following states:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
The Status of the forecast export job must be ACTIVE before you can access the forecast
in your Amazon S3 bucket.
Date creationTime
When the forecast export job was created.
Date lastModificationTime
When the last successful export job finished.
String forecastArn
The Amazon Resource Name (ARN) of the forecast.
String forecastArn
The same forecast ARN as given in the request.
String forecastName
The name of the forecast.
String predictorArn
The ARN of the predictor used to generate the forecast.
String datasetGroupArn
The ARN of the dataset group that provided the data used to train the predictor.
String status
The status of the forecast. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
The Status of the forecast must be ACTIVE before you can query or export the forecast.
String message
If an error occurred, an informational message about the error.
Date creationTime
When the forecast creation task was created.
Date lastModificationTime
Initially, the same as CreationTime (status is CREATE_PENDING). Updated when inference
(creating the forecast) starts (status changed to CREATE_IN_PROGRESS), and when inference is
complete (status changed to ACTIVE) or fails (status changed to CREATE_FAILED).
String predictorArn
The Amazon Resource Name (ARN) of the predictor that you want information about.
String predictorArn
The ARN of the predictor.
String predictorName
The name of the predictor.
String algorithmArn
The Amazon Resource Name (ARN) of the algorithm used for model training.
Integer forecastHorizon
The number of time-steps of the forecast. The forecast horizon is also called the prediction length.
Boolean performAutoML
Whether the predictor is set to perform AutoML.
Boolean performHPO
Whether the predictor is set to perform HPO.
Map<K,V> trainingParameters
The training parameters to override for model training. The parameters that you can override are listed in the individual algorithms in aws-forecast-choosing-recipes.
EvaluationParameters evaluationParameters
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.
HyperParameterTuningJobConfig hPOConfig
The hyperparameter override values for the algorithm.
InputDataConfig inputDataConfig
Describes the dataset group that contains the data to use to train the predictor.
FeaturizationConfig featurizationConfig
The featurization configuration.
EncryptionConfig encryptionConfig
An AWS Key Management Service (KMS) key and the AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the key.
List<E> datasetImportJobArns
An array of ARNs of the dataset import jobs used to import training data for the predictor.
List<E> autoMLAlgorithmArns
When PerformAutoML is specified, the ARN of the chosen algorithm.
String status
The status of the predictor. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
UPDATE_PENDING, UPDATE_IN_PROGRESS, UPDATE_FAILED
The Status of the predictor must be ACTIVE before using the predictor to create a
forecast.
String message
If an error occurred, an informational message about the error.
Date creationTime
When the model training task was created.
Date lastModificationTime
Initially, the same as CreationTime (status is CREATE_PENDING). Updated when training
starts (status changed to CREATE_IN_PROGRESS), and when training is complete (status changed to
ACTIVE) or fails (status changed to CREATE_FAILED).
String roleArn
The ARN of the AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the AWS KMS key.
Cross-account pass role is not allowed. If you pass a role that doesn't belong to your account, an
InvalidInputException is thrown.
String kMSKeyArn
The Amazon Resource Name (ARN) of an AWS Key Management Service (KMS) key.
Integer numberOfBacktestWindows
The number of times to split the input data. The default is 1. The range is 1 through 5.
Integer backTestWindowOffset
The point from the end of the dataset where you want to split the data for model training and evaluation. The value is specified as the number of data points.
String algorithmArn
The Amazon Resource Name (ARN) of the algorithm that was evaluated.
List<E> testWindows
The array of test windows used for evaluating the algorithm. The NumberOfBacktestWindows from the
EvaluationParameters object determines the number of windows in the array.
String attributeName
The name of the schema attribute specifying the data field to be featurized. In this release, only the
target field of the TARGET_TIME_SERIES dataset type is supported. For example, for the
RETAIL domain, the target is demand, and for the CUSTOM domain, the target
is target_value.
List<E> featurizationPipeline
An array FeaturizationMethod objects that specifies the feature transformation methods. For this
release, the number of methods is limited to one.
String forecastFrequency
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.
List<E> forecastDimensions
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.
List<E> featurizations
An array of featurization (transformation) information for the fields of a dataset. In this release, only a single featurization is supported.
String featurizationMethodName
The name of the method. In this release, "filling" is the only supported method.
Map<K,V> featurizationMethodParameters
The method parameters (key-value pairs). Specify these to override the default values. The following list shows the parameters and their valid values. Bold signifies the default value.
aggregation: sum, avg, first, min, max
frontfill: none
middlefill: zero, nan (not a number)
backfill: zero, nan
String forecastExportJobArn
The Amazon Resource Name (ARN) of the forecast export job.
String forecastExportJobName
The name of the forecast export job.
DataDestination destination
The path to the S3 bucket where the forecast is stored.
String status
The status of the forecast export job. One of the following states:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
The Status of the forecast export job must be ACTIVE before you can access the forecast
in your Amazon S3 bucket.
String message
If an error occurred, an informational message about the error.
Date creationTime
When the forecast export job was created.
Date lastModificationTime
When the last successful export job finished.
String forecastArn
The ARN of the forecast.
String forecastName
The name of the forecast.
String predictorArn
The ARN of the predictor used to generate the forecast.
String datasetGroupArn
The Amazon Resource Name (ARN) of the dataset group that provided the data used to train the predictor.
String status
The status of the forecast. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
The Status of the forecast must be ACTIVE before you can query or export the forecast.
String message
If an error occurred, an informational message about the error.
Date creationTime
When the forecast creation task was created.
Date lastModificationTime
Initially, the same as CreationTime (status is CREATE_PENDING). Updated when inference
(creating the forecast) starts (status changed to CREATE_IN_PROGRESS), and when inference is
complete (status changed to ACTIVE) or fails (status changed to CREATE_FAILED).
String predictorArn
The Amazon Resource Name (ARN) of the predictor to get metrics for.
ParameterRanges parameterRanges
Specifies the ranges of valid values for the hyperparameters.
String name
The name of the hyperparameter to tune.
Integer maxValue
The maximum tunable value of the hyperparameter.
Integer minValue
The minimum tunable value of the hyperparameter.
String scalingType
The scale that hyperparameter tuning uses to search the hyperparameter range. For information about choosing a hyperparameter scale, see Hyperparameter Scaling. One of the following values:
Amazon Forecast hyperparameter tuning chooses the best scale for the hyperparameter.
Hyperparameter tuning searches the values in the hyperparameter range by using a linear scale.
Hyperparameter tuning searches the values in the hyperparameter range by using a logarithmic scale.
Logarithmic scaling works only for ranges that have only values greater than 0.
Not supported for IntegerParameterRange.
Reverse logarithmic scaling works only for ranges that are entirely within the range 0 <= x < 1.0.
String nextToken
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.
Integer maxResults
The number of items to return in the response.
List<E> filters
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, respectively, from the
list, the predictors that match the statement. The match statement consists of a key and a value. In this
release, Name is the only valid key, which filters on the DatasetImportJobName
property.
Condition - IS or IS_NOT
Key - Name
Value - the value to match
For example, to list all dataset import jobs named my_dataset_import_job, you would specify:
"Filters": [ { "Condition": "IS", "Key": "Name", "Value": "my_dataset_import_job" } ]
String nextToken
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.
Integer maxResults
The number of items to return in the response.
List<E> filters
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, respectively, from the
list, the predictors that match the statement. The match statement consists of a key and a value. In this
release, Name is the only valid key, which filters on the ForecastExportJobName
property.
Condition - IS or IS_NOT
Key - Name
Value - the value to match
For example, to list all forecast export jobs named my_forecast_export_job, you would specify:
"Filters": [ { "Condition": "IS", "Key": "Name", "Value": "my_forecast_export_job" } ]
String nextToken
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.
Integer maxResults
The number of items to return in the response.
List<E> filters
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, respectively, from the
list, the predictors that match the statement. The match statement consists of a key and a value. In this
release, Name is the only valid key, which filters on the ForecastName property.
Condition - IS or IS_NOT
Key - Name
Value - the value to match
For example, to list all forecasts named my_forecast, you would specify:
"Filters": [ { "Condition": "IS", "Key": "Name", "Value": "my_forecast" } ]
String nextToken
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.
Integer maxResults
The number of items to return in the response.
List<E> filters
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, respectively, from the
list, the predictors that match the statement. The match statement consists of a key and a value. In this
release, Name is the only valid key, which filters on the PredictorName property.
Condition - IS or IS_NOT
Key - Name
Value - the value to match
For example, to list all predictors named my_predictor, you would specify:
"Filters": [ { "Condition": "IS", "Key": "Name", "Value": "my_predictor" } ]
List<E> categoricalParameterRanges
Specifies the tunable range for each categorical hyperparameter.
List<E> continuousParameterRanges
Specifies the tunable range for each continuous hyperparameter.
List<E> integerParameterRanges
Specifies the tunable range for each integer hyperparameter.
String predictorArn
The ARN of the predictor.
String predictorName
The name of the predictor.
String datasetGroupArn
The Amazon Resource Name (ARN) of the dataset group that contains the data used to train the predictor.
String status
The status of the predictor. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
UPDATE_PENDING, UPDATE_IN_PROGRESS, UPDATE_FAILED
The Status of the predictor must be ACTIVE before using the predictor to create a
forecast.
String message
If an error occurred, an informational message about the error.
Date creationTime
When the model training task was created.
Date lastModificationTime
Initially, the same as CreationTime (status is CREATE_PENDING). Updated when training
starts (status changed to CREATE_IN_PROGRESS), and when training is complete (status changed to
ACTIVE) or fails (status changed to CREATE_FAILED).
String path
The path to an Amazon Simple Storage Service (Amazon S3) bucket or file(s) in an Amazon S3 bucket.
String roleArn
The ARN of the AWS Identity and Access Management (IAM) role that Amazon Forecast can assume to access the Amazon S3 bucket or file(s).
Cross-account pass role is not allowed. If you pass a role that doesn't belong to your account, an
InvalidInputException is thrown.
String kMSKeyArn
The Amazon Resource Name (ARN) of an AWS Key Management Service (KMS) key.
Integer count
The number of values in the field.
Integer countDistinct
The number of distinct values in the field.
Integer countNull
The number of null values in the field.
Integer countNan
The number of NAN (not a number) values in the field.
String min
For a numeric field, the minimum value in the field.
String max
For a numeric field, the maximum value in the field.
Double avg
For a numeric field, the average value in the field.
Double stddev
For a numeric field, the standard deviation.
Double quantile
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.
Double lossValue
The difference between the predicted value and actual value over the quantile, weighted (normalized) by dividing by the sum over all quantiles.
Date testWindowStart
The timestamp that defines the start of the window.
Date testWindowEnd
The timestamp that defines the end of the window.
Integer itemCount
The number of data points within the window.
String evaluationType
The type of evaluation.
SUMMARY - The average metrics across all windows.
COMPUTED - The metrics for the specified window.
Metrics metrics
Copyright © 2019. All rights reserved.