aws-sdk-sagemaker 1.157.0 → 1.158.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b082ca52f03d7d82732093787abd9b675047c9a234b33d06420bcdf21719061e
-  data.tar.gz: c2cf439c12b984fb3a8593b8ead44ea6e8d5359f97d6c155d51a4b6716cf6bce
+  metadata.gz: afa3d9aad52d2754e4e54670bff15a1be4f111158df8df74341671fa4f4a5573
+  data.tar.gz: 609ae29dcd112366ce30892884bafc2ea3c5d7a8dea344374783928d7865582a
 SHA512:
-  metadata.gz: ccc8fa1c3a21c62ad46ccbd3e9908d6955a2382fa656ea2a56a894950c457bb5a3afce895b537dc8f47cdd717211da5d1731a6d5cfd1b9a3eef86c0c9732703f
-  data.tar.gz: a1a16740daeb725a07b7b695b2e59f2c0a919dca9d943bed10c373fe6864af213387af2b994188869624bc2aca0197768ac87b772261ae03d91bb9527329ddea
+  metadata.gz: 036e5c82c6a7a42f3e10141e8c00a2687011434939868f4990b847474b04ec3a4ddd35a3307eb3c44a864ef0bd140836b2bf11223078ccc43aecf02f26c81d75
+  data.tar.gz: c557948a687fe872b8c85c3ba5084c2ac42717fc3f811171d1ea3ecd220f7ae5a714807fb6f285372168f7618b9168d6e9c4a2bda7ea19f125c5668ddf62d54e

data/CHANGELOG.md

@@ -1,6 +1,11 @@
 Unreleased Changes
 ------------------
 
+1.158.0 (2022-12-20)
+------------------
+
+* Feature - Amazon SageMaker Autopilot adds support for new objective metrics in CreateAutoMLJob API.
+
 1.157.0 (2022-12-19)
 ------------------
 

data/VERSION

@@ -1 +1 @@
-1.157.0
+1.158.0

data/lib/aws-sdk-sagemaker/client.rb

@@ -1260,7 +1260,7 @@ module Aws::SageMaker
     #     },
     #     problem_type: "BinaryClassification", # accepts BinaryClassification, MulticlassClassification, Regression
     #     auto_ml_job_objective: {
-    #       metric_name: "Accuracy", # required, accepts Accuracy, MSE, F1, F1macro, AUC
+    #       metric_name: "Accuracy", # required, accepts Accuracy, MSE, F1, F1macro, AUC, RMSE, MAE, R2, BalancedAccuracy, Precision, PrecisionMacro, Recall, RecallMacro
     #     },
     #     auto_ml_job_config: {
     #       completion_criteria: {
@@ -2702,11 +2702,16 @@ module Aws::SageMaker
       req.send_request(options)
     end
 
-    # Creates an SageMaker *experiment*. An experiment is a collection of
+    # Creates a SageMaker *experiment*. An experiment is a collection of
     # *trials* that are observed, compared and evaluated as a group. A trial
     # is a set of steps, called *trial components*, that produce a machine
     # learning model.
     #
+    # <note markdown="1"> In the Studio UI, trials are referred to as *run groups* and trial
+    # components are referred to as *runs*.
+    #
+    #  </note>
+    #
     # The goal of an experiment is to determine the components that produce
     # the best model. Multiple trials are performed, each one isolating and
     # measuring the impact of a change to one or more inputs, while keeping
@@ -9545,7 +9550,7 @@ module Aws::SageMaker
     #   resp.output_data_config.kms_key_id #=> String
     #   resp.output_data_config.s3_output_path #=> String
     #   resp.role_arn #=> String
-    #   resp.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC"
+    #   resp.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
     #   resp.problem_type #=> String, one of "BinaryClassification", "MulticlassClassification", "Regression"
     #   resp.auto_ml_job_config.completion_criteria.max_candidates #=> Integer
     #   resp.auto_ml_job_config.completion_criteria.max_runtime_per_training_job_in_seconds #=> Integer
@@ -9567,7 +9572,7 @@ module Aws::SageMaker
     #   resp.partial_failure_reasons[0].partial_failure_message #=> String
     #   resp.best_candidate.candidate_name #=> String
     #   resp.best_candidate.final_auto_ml_job_objective_metric.type #=> String, one of "Maximize", "Minimize"
-    #   resp.best_candidate.final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC"
+    #   resp.best_candidate.final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
     #   resp.best_candidate.final_auto_ml_job_objective_metric.value #=> Float
     #   resp.best_candidate.objective_status #=> String, one of "Succeeded", "Pending", "Failed"
     #   resp.best_candidate.candidate_steps #=> Array
@@ -9587,7 +9592,7 @@ module Aws::SageMaker
     #   resp.best_candidate.candidate_properties.candidate_artifact_locations.explainability #=> String
     #   resp.best_candidate.candidate_properties.candidate_artifact_locations.model_insights #=> String
     #   resp.best_candidate.candidate_properties.candidate_metrics #=> Array
-    #   resp.best_candidate.candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC"
+    #   resp.best_candidate.candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
     #   resp.best_candidate.candidate_properties.candidate_metrics[0].value #=> Float
     #   resp.best_candidate.candidate_properties.candidate_metrics[0].set #=> String, one of "Train", "Validation", "Test"
     #   resp.best_candidate.candidate_properties.candidate_metrics[0].standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "LogLoss", "InferenceLatency"
@@ -9596,7 +9601,7 @@ module Aws::SageMaker
     #   resp.generate_candidate_definitions_only #=> Boolean
     #   resp.auto_ml_job_artifacts.candidate_definition_notebook_location #=> String
     #   resp.auto_ml_job_artifacts.data_exploration_notebook_location #=> String
-    #   resp.resolved_attributes.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC"
+    #   resp.resolved_attributes.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
     #   resp.resolved_attributes.problem_type #=> String, one of "BinaryClassification", "MulticlassClassification", "Regression"
     #   resp.resolved_attributes.completion_criteria.max_candidates #=> Integer
     #   resp.resolved_attributes.completion_criteria.max_runtime_per_training_job_in_seconds #=> Integer
@@ -14645,7 +14650,7 @@ module Aws::SageMaker
     #   resp.candidates #=> Array
     #   resp.candidates[0].candidate_name #=> String
     #   resp.candidates[0].final_auto_ml_job_objective_metric.type #=> String, one of "Maximize", "Minimize"
-    #   resp.candidates[0].final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC"
+    #   resp.candidates[0].final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
     #   resp.candidates[0].final_auto_ml_job_objective_metric.value #=> Float
     #   resp.candidates[0].objective_status #=> String, one of "Succeeded", "Pending", "Failed"
     #   resp.candidates[0].candidate_steps #=> Array
@@ -14665,7 +14670,7 @@ module Aws::SageMaker
     #   resp.candidates[0].candidate_properties.candidate_artifact_locations.explainability #=> String
     #   resp.candidates[0].candidate_properties.candidate_artifact_locations.model_insights #=> String
     #   resp.candidates[0].candidate_properties.candidate_metrics #=> Array
-    #   resp.candidates[0].candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC"
+    #   resp.candidates[0].candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
     #   resp.candidates[0].candidate_properties.candidate_metrics[0].value #=> Float
     #   resp.candidates[0].candidate_properties.candidate_metrics[0].set #=> String, one of "Train", "Validation", "Test"
     #   resp.candidates[0].candidate_properties.candidate_metrics[0].standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "LogLoss", "InferenceLatency"
@@ -22700,7 +22705,7 @@ module Aws::SageMaker
         params: params,
         config: config)
       context[:gem_name] = 'aws-sdk-sagemaker'
-      context[:gem_version] = '1.157.0'
+      context[:gem_version] = '1.158.0'
       Seahorse::Client::Request.new(handlers, context)
     end
 

data/lib/aws-sdk-sagemaker/types.rb

@@ -2015,66 +2015,171 @@ module Aws::SageMaker
     #
     #   Here are the options:
     #
-    #   * `MSE`\: The mean squared error (MSE) is the average of the squared
-    #     differences between the predicted and actual values. It is used
-    #     for regression. MSE values are always positive: the better a model
-    #     is at predicting the actual values, the smaller the MSE value is.
-    #     When the data contains outliers, they tend to dominate the MSE,
-    #     which might cause subpar prediction performance.
-    #
-    #   * `Accuracy`\: The ratio of the number of correctly classified items
-    #     to the total number of (correctly and incorrectly) classified
-    #     items. It is used for binary and multiclass classification. It
-    #     measures how close the predicted class values are to the actual
-    #     values. Accuracy values vary between zero and one: one indicates
-    #     perfect accuracy and zero indicates perfect inaccuracy.
-    #
-    #   * `F1`\: The F1 score is the harmonic mean of the precision and
-    #     recall. It is used for binary classification into classes
+    #   Accuracy
+    #
+    #   : The ratio of the number of correctly classified items to the total
+    #     number of (correctly and incorrectly) classified items. It is used
+    #     for both binary and multiclass classification. Accuracy measures
+    #     how close the predicted class values are to the actual values.
+    #     Values for accuracy metrics vary between zero (0) and one (1). A
+    #     value of 1 indicates perfect accuracy, and 0 indicates perfect
+    #     inaccuracy.
+    #
+    #   AUC
+    #
+    #   : The area under the curve (AUC) metric is used to compare and
+    #     evaluate binary classification by algorithms that return
+    #     probabilities, such as logistic regression. To map the
+    #     probabilities into classifications, these are compared against a
+    #     threshold value.
+    #
+    #     The relevant curve is the receiver operating characteristic curve
+    #     (ROC curve). The ROC curve plots the true positive rate (TPR) of
+    #     predictions (or recall) against the false positive rate (FPR) as a
+    #     function of the threshold value, above which a prediction is
+    #     considered positive. Increasing the threshold results in fewer
+    #     false positives, but more false negatives.
+    #
+    #     AUC is the area under this ROC curve. Therefore, AUC provides an
+    #     aggregated measure of the model performance across all possible
+    #     classification thresholds. AUC scores vary between 0 and 1. A
+    #     score of 1 indicates perfect accuracy, and a score of one half
+    #     (0.5) indicates that the prediction is not better than a random
+    #     classifier.
+    #
+    #   BalancedAccuracy
+    #
+    #   : `BalancedAccuracy` is a metric that measures the ratio of accurate
+    #     predictions to all predictions. This ratio is calculated after
+    #     normalizing true positives (TP) and true negatives (TN) by the
+    #     total number of positive (P) and negative (N) values. It is used
+    #     in both binary and multiclass classification and is defined as
+    #     follows: 0.5*((TP/P)+(TN/N)), with values ranging from 0 to 1.
+    #     `BalancedAccuracy` gives a better measure of accuracy when the
+    #     number of positives or negatives differ greatly from each other in
+    #     an imbalanced dataset. For example, when only 1% of email is spam.
+    #
+    #   F1
+    #
+    #   : The `F1` score is the harmonic mean of the precision and recall,
+    #     defined as follows: F1 = 2 * (precision * recall) / (precision +
+    #     recall). It is used for binary classification into classes
     #     traditionally referred to as positive and negative. Predictions
-    #     are said to be true when they match their actual (correct) class
-    #     and false when they do not. Precision is the ratio of the true
-    #     positive predictions to all positive predictions (including the
-    #     false positives) in a data set and measures the quality of the
-    #     prediction when it predicts the positive class. Recall (or
-    #     sensitivity) is the ratio of the true positive predictions to all
-    #     actual positive instances and measures how completely a model
-    #     predicts the actual class members in a data set. The standard F1
-    #     score weighs precision and recall equally. But which metric is
-    #     paramount typically depends on specific aspects of a problem. F1
-    #     scores vary between zero and one: one indicates the best possible
-    #     performance and zero the worst.
-    #
-    #   * `AUC`\: The area under the curve (AUC) metric is used to compare
-    #     and evaluate binary classification by algorithms such as logistic
-    #     regression that return probabilities. A threshold is needed to map
-    #     the probabilities into classifications. The relevant curve is the
-    #     receiver operating characteristic curve that plots the true
-    #     positive rate (TPR) of predictions (or recall) against the false
-    #     positive rate (FPR) as a function of the threshold value, above
-    #     which a prediction is considered positive. Increasing the
-    #     threshold results in fewer false positives but more false
-    #     negatives. AUC is the area under this receiver operating
-    #     characteristic curve and so provides an aggregated measure of the
-    #     model performance across all possible classification thresholds.
-    #     The AUC score can also be interpreted as the probability that a
-    #     randomly selected positive data point is more likely to be
-    #     predicted positive than a randomly selected negative example. AUC
-    #     scores vary between zero and one: a score of one indicates perfect
-    #     accuracy and a score of one half indicates that the prediction is
-    #     not better than a random classifier. Values under one half predict
-    #     less accurately than a random predictor. But such consistently bad
-    #     predictors can simply be inverted to obtain better than random
-    #     predictors.
-    #
-    #   * `F1macro`\: The F1macro score applies F1 scoring to multiclass
-    #     classification. In this context, you have multiple classes to
-    #     predict. You just calculate the precision and recall for each
-    #     class as you did for the positive class in binary classification.
-    #     Then, use these values to calculate the F1 score for each class
-    #     and average them to obtain the F1macro score. F1macro scores vary
-    #     between zero and one: one indicates the best possible performance
-    #     and zero the worst.
+    #     are said to be true when they match their actual (correct) class,
+    #     and false when they do not.
+    #
+    #     Precision is the ratio of the true positive predictions to all
+    #     positive predictions, and it includes the false positives in a
+    #     dataset. Precision measures the quality of the prediction when it
+    #     predicts the positive class.
+    #
+    #     Recall (or sensitivity) is the ratio of the true positive
+    #     predictions to all actual positive instances. Recall measures how
+    #     completely a model predicts the actual class members in a dataset.
+    #
+    #     F1 scores vary between 0 and 1. A score of 1 indicates the best
+    #     possible performance, and 0 indicates the worst.
+    #
+    #   F1macro
+    #
+    #   : The `F1macro` score applies F1 scoring to multiclass
+    #     classification problems. It does this by calculating the precision
+    #     and recall, and then taking their harmonic mean to calculate the
+    #     F1 score for each class. Lastly, the F1macro averages the
+    #     individual scores to obtain the `F1macro` score. `F1macro` scores
+    #     vary between 0 and 1. A score of 1 indicates the best possible
+    #     performance, and 0 indicates the worst.
+    #
+    #   MAE
+    #
+    #   : The mean absolute error (MAE) is a measure of how different the
+    #     predicted and actual values are, when they're averaged over all
+    #     values. MAE is commonly used in regression analysis to understand
+    #     model prediction error. If there is linear regression, MAE
+    #     represents the average distance from a predicted line to the
+    #     actual value. MAE is defined as the sum of absolute errors divided
+    #     by the number of observations. Values range from 0 to infinity,
+    #     with smaller numbers indicating a better model fit to the data.
+    #
+    #   MSE
+    #
+    #   : The mean squared error (MSE) is the average of the squared
+    #     differences between the predicted and actual values. It is used
+    #     for regression. MSE values are always positive. The better a model
+    #     is at predicting the actual values, the smaller the MSE value is
+    #
+    #   Precision
+    #
+    #   : Precision measures how well an algorithm predicts the true
+    #     positives (TP) out of all of the positives that it identifies. It
+    #     is defined as follows: Precision = TP/(TP+FP), with values ranging
+    #     from zero (0) to one (1), and is used in binary classification.
+    #     Precision is an important metric when the cost of a false positive
+    #     is high. For example, the cost of a false positive is very high if
+    #     an airplane safety system is falsely deemed safe to fly. A false
+    #     positive (FP) reflects a positive prediction that is actually
+    #     negative in the data.
+    #
+    #   PrecisionMacro
+    #
+    #   : The precision macro computes precision for multiclass
+    #     classification problems. It does this by calculating precision for
+    #     each class and averaging scores to obtain precision for several
+    #     classes. `PrecisionMacro` scores range from zero (0) to one (1).
+    #     Higher scores reflect the model's ability to predict true
+    #     positives (TP) out of all of the positives that it identifies,
+    #     averaged across multiple classes.
+    #
+    #   R2
+    #
+    #   : R2, also known as the coefficient of determination, is used in
+    #     regression to quantify how much a model can explain the variance
+    #     of a dependent variable. Values range from one (1) to negative one
+    #     (-1). Higher numbers indicate a higher fraction of explained
+    #     variability. `R2` values close to zero (0) indicate that very
+    #     little of the dependent variable can be explained by the model.
+    #     Negative values indicate a poor fit and that the model is
+    #     outperformed by a constant function. For linear regression, this
+    #     is a horizontal line.
+    #
+    #   Recall
+    #
+    #   : Recall measures how well an algorithm correctly predicts all of
+    #     the true positives (TP) in a dataset. A true positive is a
+    #     positive prediction that is also an actual positive value in the
+    #     data. Recall is defined as follows: Recall = TP/(TP+FN), with
+    #     values ranging from 0 to 1. Higher scores reflect a better ability
+    #     of the model to predict true positives (TP) in the data, and is
+    #     used in binary classification.
+    #
+    #     Recall is important when testing for cancer because it's used to
+    #     find all of the true positives. A false positive (FP) reflects a
+    #     positive prediction that is actually negative in the data. It is
+    #     often insufficient to measure only recall, because predicting
+    #     every output as a true positive will yield a perfect recall score.
+    #
+    #   RecallMacro
+    #
+    #   : The RecallMacro computes recall for multiclass classification
+    #     problems by calculating recall for each class and averaging scores
+    #     to obtain recall for several classes. RecallMacro scores range
+    #     from 0 to 1. Higher scores reflect the model's ability to predict
+    #     true positives (TP) in a dataset. Whereas, a true positive
+    #     reflects a positive prediction that is also an actual positive
+    #     value in the data. It is often insufficient to measure only
+    #     recall, because predicting every output as a true positive will
+    #     yield a perfect recall score.
+    #
+    #   RMSE
+    #
+    #   : Root mean squared error (RMSE) measures the square root of the
+    #     squared difference between predicted and actual values, and it's
+    #     averaged over all values. It is used in regression analysis to
+    #     understand model prediction error. It's an important metric to
+    #     indicate the presence of large model errors and outliers. Values
+    #     range from zero (0) to infinity, with smaller numbers indicating a
+    #     better model fit to the data. RMSE is dependent on scale, and
+    #     should not be used to compare datasets of different sizes.
     #
     #   If you do not specify a metric explicitly, the default behavior is
     #   to automatically use:
@@ -9976,7 +10081,13 @@ module Aws::SageMaker
     #   @return [Array<Types::AutoMLPartialFailureReason>]
     #
     # @!attribute [rw] best_candidate
-    #   Returns the job's best `AutoMLCandidate`.
+    #   The best model candidate selected by SageMaker Autopilot using both
+    #   the best objective metric and lowest [InferenceLatency][1] for an
+    #   experiment.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-metrics-validation.html
     #   @return [Types::AutoMLCandidate]
     #
     # @!attribute [rw] auto_ml_job_status
@@ -14654,8 +14765,8 @@ module Aws::SageMaker
     #   @return [String]
     #
     # @!attribute [rw] sources
-    #   A list of the Amazon Resource Name (ARN) and, if applicable, job
-    #   type for multiple sources of an experiment run.
+    #   A list of ARNs and, if applicable, job types for multiple sources of
+    #   an experiment run.
     #   @return [Array<Types::TrialComponentSource>]
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeTrialComponentResponse AWS API Documentation
@@ -16336,8 +16447,8 @@ module Aws::SageMaker
     # * CreateTransformJob
     #
     # @!attribute [rw] experiment_name
-    #   The name of an existing experiment to associate the trial component
-    #   with.
+    #   The name of an existing experiment to associate with the trial
+    #   component.
     #   @return [String]
     #
     # @!attribute [rw] trial_name
@@ -16351,8 +16462,8 @@ module Aws::SageMaker
     #   @return [String]
     #
     # @!attribute [rw] run_name
-    #   The name of the experiment run to associate the trial component
-    #   with.
+    #   The name of the experiment run to associate with the trial
+    #   component.
     #   @return [String]
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ExperimentConfig AWS API Documentation
@@ -19034,8 +19145,8 @@ module Aws::SageMaker
     # @!attribute [rw] parameter_ranges
     #   The ParameterRanges object that specifies the ranges of
     #   hyperparameters that this tuning job searches over to find the
-    #   optimal configuration for the highest model performance against
-    #   .your chosen objective metric.
+    #   optimal configuration for the highest model performance against your
+    #   chosen objective metric.
     #   @return [Types::ParameterRanges]
     #
     # @!attribute [rw] training_job_early_stopping_type

data/lib/aws-sdk-sagemaker.rb

@@ -53,6 +53,6 @@ require_relative 'aws-sdk-sagemaker/customizations'
 # @!group service
 module Aws::SageMaker
 
-  GEM_VERSION = '1.157.0'
+  GEM_VERSION = '1.158.0'
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: aws-sdk-sagemaker
 version: !ruby/object:Gem::Version
-  version: 1.157.0
+  version: 1.158.0
 platform: ruby
 authors:
 - Amazon Web Services
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-12-19 00:00:00.000000000 Z
+date: 2022-12-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-core