2022/05/26 - Amazon Forecast Service - 2 updated api methods
Changes Introduced a new field in Auto Predictor as Time Alignment Boundary. It helps in aligning the timestamps generated during Forecast exports
{'TimeAlignmentBoundary': {'DayOfMonth': 'integer',
'DayOfWeek': 'MONDAY | TUESDAY | WEDNESDAY | '
'THURSDAY | FRIDAY | SATURDAY | SUNDAY',
'Hour': 'integer',
'Month': 'JANUARY | FEBRUARY | MARCH | APRIL | MAY '
'| JUNE | JULY | AUGUST | SEPTEMBER | '
'OCTOBER | NOVEMBER | DECEMBER'}}
Creates an Amazon Forecast predictor.
Amazon Forecast creates predictors with AutoPredictor, which involves applying the optimal combination of algorithms to each time series in your datasets. You can use CreateAutoPredictor to create new predictors or upgrade/retrain existing predictors.
Creating new predictors
The following parameters are required when creating a new predictor:
PredictorName - A unique name for the predictor.
DatasetGroupArn - The ARN of the dataset group used to train the predictor.
ForecastFrequency - The granularity of your forecasts (hourly, daily, weekly, etc).
ForecastHorizon - The number of time-steps that the model predicts. The forecast horizon is also called the prediction length.
When creating a new predictor, do not specify a value for ReferencePredictorArn.
Upgrading and retraining predictors
The following parameters are required when retraining or upgrading a predictor:
PredictorName - A unique name for the predictor.
ReferencePredictorArn - The ARN of the predictor to retrain or upgrade.
When upgrading or retraining a predictor, only specify values for the ReferencePredictorArn and PredictorName.
See also: AWS API Documentation
Request Syntax
client.create_auto_predictor(
PredictorName='string',
ForecastHorizon=123,
ForecastTypes=[
'string',
],
ForecastDimensions=[
'string',
],
ForecastFrequency='string',
DataConfig={
'DatasetGroupArn': 'string',
'AttributeConfigs': [
{
'AttributeName': 'string',
'Transformations': {
'string': 'string'
}
},
],
'AdditionalDatasets': [
{
'Name': 'string',
'Configuration': {
'string': [
'string',
]
}
},
]
},
EncryptionConfig={
'RoleArn': 'string',
'KMSKeyArn': 'string'
},
ReferencePredictorArn='string',
OptimizationMetric='WAPE'|'RMSE'|'AverageWeightedQuantileLoss'|'MASE'|'MAPE',
ExplainPredictor=True|False,
Tags=[
{
'Key': 'string',
'Value': 'string'
},
],
MonitorConfig={
'MonitorName': 'string'
},
TimeAlignmentBoundary={
'Month': 'JANUARY'|'FEBRUARY'|'MARCH'|'APRIL'|'MAY'|'JUNE'|'JULY'|'AUGUST'|'SEPTEMBER'|'OCTOBER'|'NOVEMBER'|'DECEMBER',
'DayOfMonth': 123,
'DayOfWeek': 'MONDAY'|'TUESDAY'|'WEDNESDAY'|'THURSDAY'|'FRIDAY'|'SATURDAY'|'SUNDAY',
'Hour': 123
}
)
string
[REQUIRED]
A unique name for the predictor
integer
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.
list
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.
(string) --
list
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.
(string) --
string
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.
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.
dict
The data configuration for your dataset group and any additional datasets.
DatasetGroupArn (string) -- [REQUIRED]
The ARN of the dataset group used to train the predictor.
AttributeConfigs (list) --
Aggregation and filling options for attributes in your dataset group.
(dict) --
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"}
}
AttributeName (string) -- [REQUIRED]
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.
Transformations (dict) -- [REQUIRED]
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, max
frontfill: none
middlefill: zero, nan (not a number), value, median, mean, min, max
backfill: zero, nan, value, median, mean, min, max
The 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, max
backfill: zero, value, median, mean, min, max
futurefill: zero, value, median, mean, min, max
To 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".
(string) --
(string) --
AdditionalDatasets (list) --
Additional built-in datasets like Holidays and the Weather Index.
(dict) --
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.
Name (string) -- [REQUIRED]
The name of the additional dataset. Valid names: "holiday" and "weather".
Configuration (dict) --
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:
"AL" - ALBANIA
"AR" - ARGENTINA
"AT" - AUSTRIA
"AU" - AUSTRALIA
"BA" - BOSNIA HERZEGOVINA
"BE" - BELGIUM
"BG" - BULGARIA
"BO" - BOLIVIA
"BR" - BRAZIL
"BY" - BELARUS
"CA" - CANADA
"CL" - CHILE
"CO" - COLOMBIA
"CR" - COSTA RICA
"HR" - CROATIA
"CZ" - CZECH REPUBLIC
"DK" - DENMARK
"EC" - ECUADOR
"EE" - ESTONIA
"ET" - ETHIOPIA
"FI" - FINLAND
"FR" - FRANCE
"DE" - GERMANY
"GR" - GREECE
"HU" - HUNGARY
"IS" - ICELAND
"IN" - INDIA
"IE" - IRELAND
"IT" - ITALY
"JP" - JAPAN
"KZ" - KAZAKHSTAN
"KR" - KOREA
"LV" - LATVIA
"LI" - LIECHTENSTEIN
"LT" - LITHUANIA
"LU" - LUXEMBOURG
"MK" - MACEDONIA
"MT" - MALTA
"MX" - MEXICO
"MD" - MOLDOVA
"ME" - MONTENEGRO
"NL" - NETHERLANDS
"NZ" - NEW ZEALAND
"NI" - NICARAGUA
"NG" - NIGERIA
"NO" - NORWAY
"PA" - PANAMA
"PY" - PARAGUAY
"PE" - PERU
"PL" - POLAND
"PT" - PORTUGAL
"RO" - ROMANIA
"RU" - RUSSIA
"RS" - SERBIA
"SK" - SLOVAKIA
"SI" - SLOVENIA
"ZA" - SOUTH AFRICA
"ES" - SPAIN
"SE" - SWEDEN
"CH" - SWITZERLAND
"UA" - UKRAINE
"AE" - UNITED ARAB EMIRATES
"US" - UNITED STATES
"UK" - UNITED KINGDOM
"UY" - URUGUAY
"VE" - VENEZUELA
(string) --
(list) --
(string) --
dict
An AWS Key Management Service (KMS) key and an AWS 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.
RoleArn (string) -- [REQUIRED]
The ARN of the IAM role that Amazon Forecast can assume to access the AWS KMS key.
Passing a role across AWS accounts is not allowed. If you pass a role that isn't in your account, you get an InvalidInputException error.
KMSKeyArn (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the KMS key.
string
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.
string
The accuracy metric used to optimize the predictor.
boolean
Create an Explainability resource for the predictor.
list
Optional metadata to help you categorize and organize your predictors. Each tag consists of a key and an optional value, both of which you define. Tag keys and values are case sensitive.
The following restrictions apply to tags:
For each resource, each tag key must be unique and each tag key must have one value.
Maximum number of tags per resource: 50.
Maximum key length: 128 Unicode characters in UTF-8.
Maximum value length: 256 Unicode characters in UTF-8.
Accepted characters: all letters and numbers, spaces representable in UTF-8, and + - = . _ : / @. If your tagging schema is used across other services and resources, the character restrictions of those services also apply.
Key prefixes cannot include any upper or lowercase combination of aws: or AWS:. Values can have this prefix. If a tag value has aws as its prefix but the key does not, 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. You cannot edit or delete tag keys with this prefix.
(dict) --
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:
Maximum number of tags per resource - 50.
For each resource, each tag key must be unique, and each tag key can have only one value.
Maximum key length - 128 Unicode characters in UTF-8.
Maximum value length - 256 Unicode characters in UTF-8.
If your tagging schema is used across multiple services and resources, remember that other services may have restrictions on allowed characters. Generally allowed characters are: letters, numbers, and spaces representable in UTF-8, and the following characters: + - = . _ : / @.
Tag keys and values are case sensitive.
Do not use aws:, AWS:, or any upper or lowercase combination of such as a prefix for keys as it is reserved for AWS 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.
Key (string) -- [REQUIRED]
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.
Value (string) -- [REQUIRED]
The optional part of a key-value pair that makes up a tag. A value acts as a descriptor within a tag category (key).
dict
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.
MonitorName (string) -- [REQUIRED]
The name of the monitor resource.
dict
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.
Month (string) --
The month to use for time alignment during aggregation. The month must be in uppercase.
DayOfMonth (integer) --
The day of the month to use for time alignment during aggregation.
DayOfWeek (string) --
The day of week to use for time alignment during aggregation. The day must be in uppercase.
Hour (integer) --
The hour of day to use for time alignment during aggregation.
dict
Response Syntax
{
'PredictorArn': 'string'
}
Response Structure
(dict) --
PredictorArn (string) --
The Amazon Resource Name (ARN) of the predictor.
{'TimeAlignmentBoundary': {'DayOfMonth': 'integer',
'DayOfWeek': 'MONDAY | TUESDAY | WEDNESDAY | '
'THURSDAY | FRIDAY | SATURDAY | SUNDAY',
'Hour': 'integer',
'Month': 'JANUARY | FEBRUARY | MARCH | APRIL | MAY '
'| JUNE | JULY | AUGUST | SEPTEMBER | '
'OCTOBER | NOVEMBER | DECEMBER'}}
Describes a predictor created using the CreateAutoPredictor operation.
See also: AWS API Documentation
Request Syntax
client.describe_auto_predictor(
PredictorArn='string'
)
string
[REQUIRED]
The Amazon Resource Name (ARN) of the predictor.
dict
Response Syntax
{
'PredictorArn': 'string',
'PredictorName': 'string',
'ForecastHorizon': 123,
'ForecastTypes': [
'string',
],
'ForecastFrequency': 'string',
'ForecastDimensions': [
'string',
],
'DatasetImportJobArns': [
'string',
],
'DataConfig': {
'DatasetGroupArn': 'string',
'AttributeConfigs': [
{
'AttributeName': 'string',
'Transformations': {
'string': 'string'
}
},
],
'AdditionalDatasets': [
{
'Name': 'string',
'Configuration': {
'string': [
'string',
]
}
},
]
},
'EncryptionConfig': {
'RoleArn': 'string',
'KMSKeyArn': 'string'
},
'ReferencePredictorSummary': {
'Arn': 'string',
'State': 'Active'|'Deleted'
},
'EstimatedTimeRemainingInMinutes': 123,
'Status': 'string',
'Message': 'string',
'CreationTime': datetime(2015, 1, 1),
'LastModificationTime': datetime(2015, 1, 1),
'OptimizationMetric': 'WAPE'|'RMSE'|'AverageWeightedQuantileLoss'|'MASE'|'MAPE',
'ExplainabilityInfo': {
'ExplainabilityArn': 'string',
'Status': 'string'
},
'MonitorInfo': {
'MonitorArn': 'string',
'Status': 'string'
},
'TimeAlignmentBoundary': {
'Month': 'JANUARY'|'FEBRUARY'|'MARCH'|'APRIL'|'MAY'|'JUNE'|'JULY'|'AUGUST'|'SEPTEMBER'|'OCTOBER'|'NOVEMBER'|'DECEMBER',
'DayOfMonth': 123,
'DayOfWeek': 'MONDAY'|'TUESDAY'|'WEDNESDAY'|'THURSDAY'|'FRIDAY'|'SATURDAY'|'SUNDAY',
'Hour': 123
}
}
Response Structure
(dict) --
PredictorArn (string) --
The Amazon Resource Name (ARN) of the predictor
PredictorName (string) --
The name of the predictor.
ForecastHorizon (integer) --
The number of time-steps that the model predicts. The forecast horizon is also called the prediction length.
ForecastTypes (list) --
The forecast types used during predictor training. Default value is ["0.1","0.5","0.9"].
(string) --
ForecastFrequency (string) --
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.
ForecastDimensions (list) --
An array of dimension (field) names that specify the attributes used to group your time series.
(string) --
DatasetImportJobArns (list) --
An array of the ARNs of the dataset import jobs used to import training data for the predictor.
(string) --
DataConfig (dict) --
The data configuration for your dataset group and any additional datasets.
DatasetGroupArn (string) --
The ARN of the dataset group used to train the predictor.
AttributeConfigs (list) --
Aggregation and filling options for attributes in your dataset group.
(dict) --
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"}
}
AttributeName (string) --
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.
Transformations (dict) --
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, max
frontfill: none
middlefill: zero, nan (not a number), value, median, mean, min, max
backfill: zero, nan, value, median, mean, min, max
The 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, max
backfill: zero, value, median, mean, min, max
futurefill: zero, value, median, mean, min, max
To 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".
(string) --
(string) --
AdditionalDatasets (list) --
Additional built-in datasets like Holidays and the Weather Index.
(dict) --
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.
Name (string) --
The name of the additional dataset. Valid names: "holiday" and "weather".
Configuration (dict) --
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:
"AL" - ALBANIA
"AR" - ARGENTINA
"AT" - AUSTRIA
"AU" - AUSTRALIA
"BA" - BOSNIA HERZEGOVINA
"BE" - BELGIUM
"BG" - BULGARIA
"BO" - BOLIVIA
"BR" - BRAZIL
"BY" - BELARUS
"CA" - CANADA
"CL" - CHILE
"CO" - COLOMBIA
"CR" - COSTA RICA
"HR" - CROATIA
"CZ" - CZECH REPUBLIC
"DK" - DENMARK
"EC" - ECUADOR
"EE" - ESTONIA
"ET" - ETHIOPIA
"FI" - FINLAND
"FR" - FRANCE
"DE" - GERMANY
"GR" - GREECE
"HU" - HUNGARY
"IS" - ICELAND
"IN" - INDIA
"IE" - IRELAND
"IT" - ITALY
"JP" - JAPAN
"KZ" - KAZAKHSTAN
"KR" - KOREA
"LV" - LATVIA
"LI" - LIECHTENSTEIN
"LT" - LITHUANIA
"LU" - LUXEMBOURG
"MK" - MACEDONIA
"MT" - MALTA
"MX" - MEXICO
"MD" - MOLDOVA
"ME" - MONTENEGRO
"NL" - NETHERLANDS
"NZ" - NEW ZEALAND
"NI" - NICARAGUA
"NG" - NIGERIA
"NO" - NORWAY
"PA" - PANAMA
"PY" - PARAGUAY
"PE" - PERU
"PL" - POLAND
"PT" - PORTUGAL
"RO" - ROMANIA
"RU" - RUSSIA
"RS" - SERBIA
"SK" - SLOVAKIA
"SI" - SLOVENIA
"ZA" - SOUTH AFRICA
"ES" - SPAIN
"SE" - SWEDEN
"CH" - SWITZERLAND
"UA" - UKRAINE
"AE" - UNITED ARAB EMIRATES
"US" - UNITED STATES
"UK" - UNITED KINGDOM
"UY" - URUGUAY
"VE" - VENEZUELA
(string) --
(list) --
(string) --
EncryptionConfig (dict) --
An AWS Key Management Service (KMS) key and an AWS 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.
RoleArn (string) --
The ARN of the IAM role that Amazon Forecast can assume to access the AWS KMS key.
Passing a role across AWS accounts is not allowed. If you pass a role that isn't in your account, you get an InvalidInputException error.
KMSKeyArn (string) --
The Amazon Resource Name (ARN) of the KMS key.
ReferencePredictorSummary (dict) --
The ARN and state of the reference predictor. This parameter is only valid for retrained or upgraded predictors.
Arn (string) --
The ARN of the reference predictor.
State (string) --
Whether the reference predictor is Active or Deleted.
EstimatedTimeRemainingInMinutes (integer) --
The estimated time remaining in minutes for the predictor training job to complete.
Status (string) --
The status of the predictor. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
CREATE_STOPPING, CREATE_STOPPED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
Message (string) --
In the event of an error, a message detailing the cause of the error.
CreationTime (datetime) --
The timestamp of the CreateAutoPredictor request.
LastModificationTime (datetime) --
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.
OptimizationMetric (string) --
The accuracy metric used to optimize the predictor.
ExplainabilityInfo (dict) --
Provides the status and ARN of the Predictor Explainability.
ExplainabilityArn (string) --
The Amazon Resource Name (ARN) of the Explainability.
Status (string) --
The status of the Explainability. States include:
ACTIVE
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
CREATE_STOPPING, CREATE_STOPPED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
MonitorInfo (dict) --
A object with the Amazon Resource Name (ARN) and status of the monitor resource.
MonitorArn (string) --
The Amazon Resource Name (ARN) of the monitor resource.
Status (string) --
The status of the monitor. States include:
ACTIVE
ACTIVE_STOPPING, ACTIVE_STOPPED
UPDATE_IN_PROGRESS
CREATE_PENDING, CREATE_IN_PROGRESS, CREATE_FAILED
DELETE_PENDING, DELETE_IN_PROGRESS, DELETE_FAILED
TimeAlignmentBoundary (dict) --
The time boundary Forecast uses when aggregating data.
Month (string) --
The month to use for time alignment during aggregation. The month must be in uppercase.
DayOfMonth (integer) --
The day of the month to use for time alignment during aggregation.
DayOfWeek (string) --
The day of week to use for time alignment during aggregation. The day must be in uppercase.
Hour (integer) --
The hour of day to use for time alignment during aggregation.