aws-sdk-sagemaker 1.175.0 → 1.176.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ded8df879b09c28afc104def41071b5cc2e6a71203a6e22f6690b57a64b0090d
-  data.tar.gz: beee8a7492809d230e990f7a9ffaa19e0660c1581a550c9e414cb47ccdb7d20b
+  metadata.gz: b11b07add56f85c6f243d0bb5625b83fb317f8c16b23c9835046f445246624d9
+  data.tar.gz: 1b437a3a9d8f8e23e313a2deb12267c5ea702d648cba09d8bea942787449734f
 SHA512:
-  metadata.gz: 3f5ce239b868319df2f30e6b1d728b49c5e318926f8b7fddde04ab1daff32a1a8dde545fe31cd87547665717906c16b60dcae549ab8f820e81a37b5d137f05e3
-  data.tar.gz: e703f72d9a827260db39b0ef1a92feac98f487778d5f6b791d787f3628feb077d86af02724d3b4a3ee97f00e48753fd16e81783bf1e2a924d75abfa644db54ce
+  metadata.gz: c4a2d3d9cee2273b34f4c4adce3aad3e2de44b6683ee7bf89273df96865a35ad29d62ebdb808635fcc1705c13d91bc95b56875e5325e3e8d135dd3de345fef38
+  data.tar.gz: c91d6b9501a9718817346a1e676582a914d70e4bfb2e6a0ed55b19eadaf141e97806132e871b3405f53987bfd3021da3cfd6cdef7192cfadfb7dabebcd854134

data/CHANGELOG.md

@@ -1,6 +1,11 @@
 Unreleased Changes
 ------------------
 
+1.176.0 (2023-05-02)
+------------------
+
+* Feature - Amazon Sagemaker Autopilot supports training models with sample weights and additional objective metrics.
+
 1.175.0 (2023-04-27)
 ------------------
 

data/VERSION

@@ -1 +1 @@
-1.175.0
+1.176.0

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

@@ -1280,6 +1280,7 @@ module Aws::SageMaker
     #         target_attribute_name: "TargetAttributeName", # required
     #         content_type: "ContentType",
     #         channel_type: "training", # accepts training, validation
+    #         sample_weight_attribute_name: "SampleWeightAttributeName",
     #       },
     #     ],
     #     output_data_config: { # required
@@ -9929,6 +9930,7 @@ module Aws::SageMaker
     #   resp.input_data_config[0].target_attribute_name #=> String
     #   resp.input_data_config[0].content_type #=> String
     #   resp.input_data_config[0].channel_type #=> String, one of "training", "validation"
+    #   resp.input_data_config[0].sample_weight_attribute_name #=> String
     #   resp.output_data_config.kms_key_id #=> String
     #   resp.output_data_config.s3_output_path #=> String
     #   resp.role_arn #=> String
@@ -23470,7 +23472,7 @@ module Aws::SageMaker
         params: params,
         config: config)
       context[:gem_name] = 'aws-sdk-sagemaker'
-      context[:gem_version] = '1.175.0'
+      context[:gem_version] = '1.176.0'
       Seahorse::Client::Request.new(handlers, context)
     end
 

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

@@ -1648,6 +1648,7 @@ module Aws::SageMaker
     SageMakerImageVersionAlias = Shapes::StringShape.new(name: 'SageMakerImageVersionAlias')
     SageMakerImageVersionAliases = Shapes::ListShape.new(name: 'SageMakerImageVersionAliases')
     SagemakerServicecatalogStatus = Shapes::StringShape.new(name: 'SagemakerServicecatalogStatus')
+    SampleWeightAttributeName = Shapes::StringShape.new(name: 'SampleWeightAttributeName')
     SamplingPercentage = Shapes::IntegerShape.new(name: 'SamplingPercentage')
     ScheduleConfig = Shapes::StructureShape.new(name: 'ScheduleConfig')
     ScheduleExpression = Shapes::StringShape.new(name: 'ScheduleExpression')
@@ -2235,6 +2236,7 @@ module Aws::SageMaker
     AutoMLChannel.add_member(:target_attribute_name, Shapes::ShapeRef.new(shape: TargetAttributeName, required: true, location_name: "TargetAttributeName"))
     AutoMLChannel.add_member(:content_type, Shapes::ShapeRef.new(shape: ContentType, location_name: "ContentType"))
     AutoMLChannel.add_member(:channel_type, Shapes::ShapeRef.new(shape: AutoMLChannelType, location_name: "ChannelType"))
+    AutoMLChannel.add_member(:sample_weight_attribute_name, Shapes::ShapeRef.new(shape: SampleWeightAttributeName, location_name: "SampleWeightAttributeName"))
     AutoMLChannel.struct_class = Types::AutoMLChannel
 
     AutoMLContainerDefinition.add_member(:image, Shapes::ShapeRef.new(shape: ContainerImage, required: true, location_name: "Image"))

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

@@ -1939,6 +1939,27 @@ module Aws::SageMaker
     #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-datasets-problem-types.html#autopilot-data-sources-training-or-validation
     #   @return [String]
     #
+    # @!attribute [rw] sample_weight_attribute_name
+    #   If specified, this column name indicates which column of the dataset
+    #   should be treated as sample weights for use by the objective metric
+    #   during the training, evaluation, and the selection of the best
+    #   model. This column is not considered as a predictive feature. For
+    #   more information on Autopilot metrics, see [Metrics and
+    #   validation][1].
+    #
+    #   Sample weights should be numeric, non-negative, with larger values
+    #   indicating which rows are more important than others. Data points
+    #   that have invalid or no weight value are excluded.
+    #
+    #   Support for sample weights is available in [Ensembling][2] mode
+    #   only.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-metrics-validation.html
+    #   [2]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_AutoMLAlgorithmConfig.html
+    #   @return [String]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/AutoMLChannel AWS API Documentation
     #
     class AutoMLChannel < Struct.new(
@@ -1946,7 +1967,8 @@ module Aws::SageMaker
       :compression_type,
       :target_attribute_name,
       :content_type,
-      :channel_type)
+      :channel_type,
+      :sample_weight_attribute_name)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -2217,177 +2239,13 @@ module Aws::SageMaker
     #
     # @!attribute [rw] metric_name
     #   The name of the objective metric used to measure the predictive
-    #   quality of a machine learning system. This metric is optimized
-    #   during training to provide the best estimate for model parameter
-    #   values from data.
-    #
-    #   Here are the options:
-    #
-    #   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, 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 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 yields
-    #     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.
+    #   quality of a machine learning system. During training, the model's
+    #   parameters are updated iteratively to optimize its performance based
+    #   on the feedback provided by the objective metric when evaluating the
+    #   model on the validation dataset.
+    #
+    #   For the list of all available metrics supported by Autopilot, see
+    #   [Autopilot metrics][1].
     #
     #   If you do not specify a metric explicitly, the default behavior is
     #   to automatically use:
@@ -2397,6 +2255,10 @@ module Aws::SageMaker
     #   * `F1`: for binary classification
     #
     #   * `Accuracy`: for multiclass classification.
+    #
+    #
+    #
+    #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-metrics-validation.html#autopilot-metrics
     #   @return [String]
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/AutoMLJobObjective AWS API Documentation

data/lib/aws-sdk-sagemaker.rb

@@ -53,6 +53,6 @@ require_relative 'aws-sdk-sagemaker/customizations'
 # @!group service
 module Aws::SageMaker
 
-  GEM_VERSION = '1.175.0'
+  GEM_VERSION = '1.176.0'
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: aws-sdk-sagemaker
 version: !ruby/object:Gem::Version
-  version: 1.175.0
+  version: 1.176.0
 platform: ruby
 authors:
 - Amazon Web Services
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-04-27 00:00:00.000000000 Z
+date: 2023-05-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-core