Questions tagged [amazon-sagemaker-clarify]

12 questions
2
votes
1 answer

SageMaker Model Monitor and SageMaker Clarify

Is there a relationship between SageMaker Model Monitor and SageMaker Clarify? For example, Model monitor uses Clarify or vice versa? My confusion is when I read model monitor documentation, I see bias detection and explainability and when I read…
0
votes
1 answer

How to integrate SageMaker Clarify Explainability and HPO in AWS Sagemaker?

I'm wondering to use Sagemaker clarify explainability in combination with HPO. I saw the sagemaker examples using the 'experiments.run ([docs link][1]), but I did not figure out how to adapt for HPO task. Thank you all for any help. Short docs…
0
votes
0 answers

S3 bucket given in input data source is not in the same region as Processing job. Please ensure bucket exists in the selected region (us-east-1)

I've created a Glue Job and am using the boto3 Sagemaker client to create a Sagemaker processing job. For one of my processing inputs I need to use an query results from an Athena table. I'm receiving an error saying that the table is not located in…
0
votes
0 answers

How to use "sagemaker.workflow.quality_check_step.ModelQualityCheckConfig" for a Logistic Regression problem

I would like to know, how to use "sagemaker.workflow.quality_check_step.ModelQualityCheckConfig" for a Logistic Regression problem. In this link: sagemaker-pipeline-model-monitor-clarify-steps.ipynb, there is an example that shows how to use this…
0
votes
0 answers

Model Monitor Capture data - EndpointOutput Encoding is BASE64

https://docs.aws.amazon.com/sagemaker/latest/dg/model-monitor-data-capture-endpoint.html I have followed the steps mentioned in this link and it appears I cannot change the encoding for EndpointOutput in datacapture file. It's coming BASE64 for…
0
votes
1 answer

Aws Model Quality Monitoring without Endpoints

Is there any possible ways to do model monitoring in aws without an endpoint? Kindly share any good notebook regarding this if you knew Aws not gives any explainable example regarding Batch Model monitoring.
0
votes
0 answers

SageMaker ModelExplainabilityMonitor baseline job gives error ValueError: Expected 2D array, got 1D array instead:

I am trying to create a SageMaker ModelExplainabilityMonitor for one of my ML model. In order to run the baseline for ModelExplaniabilityMonitor the suggest_baseline() method requires DataConfig, ModelConfig and ShapConfig. In the ShapConfig I need…
0
votes
1 answer

SageMaker Clarify with imported models

is it possible to use SageMaker Clarify bias and explainability analysis with imported models, like TensorFlow models?Given that the Tensor flow model has been trained from elsewhere?
0
votes
0 answers

Use SageMaker Clarify with TensorFlow

We want to use SageMaker Clarify with TensorFlow or Keras. We do not know if that is. If it is possible, is there any guide or examples?
0
votes
0 answers

SageMaker Clarify Bias Detection for Continuous Features

How does SageMaker Clarify bias detection work for features that are continuous? Does it bin continuous variables automatically or do users need to bin them themselves before running the bias detection job? Using the fairness and explainability…
0
votes
1 answer

SageMaker Clarify Bias Detection for multiple facets and labels

In the Fairness and Explainability with SageMaker Clarify example, I am running a bias analysis on the 'Sex' facet ,where the facet value is 0, and the label is 0: bias_config = clarify.BiasConfig(label_values_or_threshold=[0], …
-2
votes
1 answer

Sagemaker Model Monitoring - Model Quality for Isolation forest model

I am having an unsupervised learning model - isolation forest model which gives me two value 1, -1 (anomaly detection). I want to build model quality on this. However I see it only support BinaryClassification, Multiclass and Regrression. Can I…