import type { MetadataBearer as __MetadataBearer } from "@smithy/types"; import type { CreatePredictorRequest, CreatePredictorResponse } from "../models/models_0"; /** * @public */ export type { __MetadataBearer }; /** * @public * * The input for {@link CreatePredictorCommand}. */ export interface CreatePredictorCommandInput extends CreatePredictorRequest { } /** * @public * * The output of {@link CreatePredictorCommand}. */ export interface CreatePredictorCommandOutput extends CreatePredictorResponse, __MetadataBearer { } declare const CreatePredictorCommand_base: { new (input: CreatePredictorCommandInput): import("@smithy/core/client").CommandImpl; new (input: CreatePredictorCommandInput): import("@smithy/core/client").CommandImpl; getEndpointParameterInstructions(): import("@smithy/types").EndpointParameterInstructions; }; /** * *

This operation creates a legacy predictor that does not include all the predictor * functionalities provided by Amazon Forecast. To create a predictor that is compatible with all * aspects of Forecast, use CreateAutoPredictor.

* *

Creates an Amazon Forecast predictor.

*

In the request, provide a dataset group and either specify an algorithm or let Amazon Forecast * choose an algorithm for you using AutoML. If you specify an algorithm, you also can override * algorithm-specific hyperparameters.

*

Amazon Forecast uses the algorithm to train a predictor using the latest version of the datasets * in the specified dataset group. You can then generate a forecast using the CreateForecast operation.

*

To see the evaluation metrics, use the GetAccuracyMetrics operation.

*

You can specify a featurization configuration to fill and aggregate the data fields in the * TARGET_TIME_SERIES dataset to improve model training. For more information, see * FeaturizationConfig.

*

For RELATED_TIME_SERIES datasets, CreatePredictor verifies that the * DataFrequency specified when the dataset was created matches the * ForecastFrequency. TARGET_TIME_SERIES datasets don't have this restriction. * Amazon Forecast also verifies the delimiter and timestamp format. For more information, see howitworks-datasets-groups.

*

By default, predictors are trained and evaluated at the 0.1 (P10), 0.5 (P50), and 0.9 * (P90) quantiles. You can choose custom forecast types to train and evaluate your predictor by * setting the ForecastTypes.

*

* AutoML *

*

If you want Amazon Forecast to evaluate each algorithm and choose the one that minimizes the * objective function, set PerformAutoML to true. The * objective function is defined as the mean of the weighted losses over the * forecast types. By default, these are the p10, p50, and p90 quantile losses. For more * information, see EvaluationResult.

*

When AutoML is enabled, the following properties are disallowed:

* *

To get a list of all of your predictors, use the ListPredictors * operation.

* *

Before you can use the predictor to create a forecast, the Status of the * predictor must be ACTIVE, signifying that training has completed. To get the * status, use the DescribePredictor operation.

* * @example * Use a bare-bones client and the command you need to make an API call. * ```javascript * import { ForecastClient, CreatePredictorCommand } from "@aws-sdk/client-forecast"; // ES Modules import * // const { ForecastClient, CreatePredictorCommand } = require("@aws-sdk/client-forecast"); // CommonJS import * // import type { ForecastClientConfig } from "@aws-sdk/client-forecast"; * const config = {}; // type is ForecastClientConfig * const client = new ForecastClient(config); * const input = { // CreatePredictorRequest * PredictorName: "STRING_VALUE", // required * AlgorithmArn: "STRING_VALUE", * ForecastHorizon: Number("int"), // required * ForecastTypes: [ // ForecastTypes * "STRING_VALUE", * ], * PerformAutoML: true || false, * AutoMLOverrideStrategy: "LatencyOptimized" || "AccuracyOptimized", * PerformHPO: true || false, * TrainingParameters: { // TrainingParameters * "": "STRING_VALUE", * }, * EvaluationParameters: { // EvaluationParameters * NumberOfBacktestWindows: Number("int"), * BackTestWindowOffset: Number("int"), * }, * HPOConfig: { // HyperParameterTuningJobConfig * ParameterRanges: { // ParameterRanges * CategoricalParameterRanges: [ // CategoricalParameterRanges * { // CategoricalParameterRange * Name: "STRING_VALUE", // required * Values: [ // Values // required * "STRING_VALUE", * ], * }, * ], * ContinuousParameterRanges: [ // ContinuousParameterRanges * { // ContinuousParameterRange * Name: "STRING_VALUE", // required * MaxValue: Number("double"), // required * MinValue: Number("double"), // required * ScalingType: "Auto" || "Linear" || "Logarithmic" || "ReverseLogarithmic", * }, * ], * IntegerParameterRanges: [ // IntegerParameterRanges * { // IntegerParameterRange * Name: "STRING_VALUE", // required * MaxValue: Number("int"), // required * MinValue: Number("int"), // required * ScalingType: "Auto" || "Linear" || "Logarithmic" || "ReverseLogarithmic", * }, * ], * }, * }, * InputDataConfig: { // InputDataConfig * DatasetGroupArn: "STRING_VALUE", // required * SupplementaryFeatures: [ // SupplementaryFeatures * { // SupplementaryFeature * Name: "STRING_VALUE", // required * Value: "STRING_VALUE", // required * }, * ], * }, * FeaturizationConfig: { // FeaturizationConfig * ForecastFrequency: "STRING_VALUE", // required * ForecastDimensions: [ // ForecastDimensions * "STRING_VALUE", * ], * Featurizations: [ // Featurizations * { // Featurization * AttributeName: "STRING_VALUE", // required * FeaturizationPipeline: [ // FeaturizationPipeline * { // FeaturizationMethod * FeaturizationMethodName: "filling", // required * FeaturizationMethodParameters: { // FeaturizationMethodParameters * "": "STRING_VALUE", * }, * }, * ], * }, * ], * }, * EncryptionConfig: { // EncryptionConfig * RoleArn: "STRING_VALUE", // required * KMSKeyArn: "STRING_VALUE", // required * }, * Tags: [ // Tags * { // Tag * Key: "STRING_VALUE", // required * Value: "STRING_VALUE", // required * }, * ], * OptimizationMetric: "WAPE" || "RMSE" || "AverageWeightedQuantileLoss" || "MASE" || "MAPE", * }; * const command = new CreatePredictorCommand(input); * const response = await client.send(command); * // { // CreatePredictorResponse * // PredictorArn: "STRING_VALUE", * // }; * * ``` * * @param CreatePredictorCommandInput - {@link CreatePredictorCommandInput} * @returns {@link CreatePredictorCommandOutput} * @see {@link CreatePredictorCommandInput} for command's `input` shape. * @see {@link CreatePredictorCommandOutput} for command's `response` shape. * @see {@link ForecastClientResolvedConfig | config} for ForecastClient's `config` shape. * * @throws {@link InvalidInputException} (client fault) *

We can't process the request because it includes an invalid value or a value that exceeds * the valid range.

* * @throws {@link LimitExceededException} (client fault) *

The limit on the number of resources per account has been exceeded.

* * @throws {@link ResourceAlreadyExistsException} (client fault) *

There is already a resource with this name. Try again with a different name.

* * @throws {@link ResourceInUseException} (client fault) *

The specified resource is in use.

* * @throws {@link ResourceNotFoundException} (client fault) *

We can't find a resource with that Amazon Resource Name (ARN). Check the ARN and try * again.

* * @throws {@link ForecastServiceException} *

Base exception class for all service exceptions from Forecast service.

* * * @public */ export declare class CreatePredictorCommand extends CreatePredictorCommand_base { /** @internal type navigation helper, not in runtime. */ protected static __types: { api: { input: CreatePredictorRequest; output: CreatePredictorResponse; }; sdk: { input: CreatePredictorCommandInput; output: CreatePredictorCommandOutput; }; }; }