Questions tagged with Amazon SageMaker

Content language: English

Sort by most recent

Browse through the questions and answers listed below or filter and sort to narrow down your results.

I want to use the model monitor in the sagemaker pipeline to get the results of statistics.json and constraints.json

### Summary. - I would like to know what the CSV format is for getting aws sagemaker model quality metrics (regression metrics). ### Contents - The model monitor in sagemaker is used to evaluate models (own models, batch processing). At this time, I believe that using the AWS mechanism, I can get statistics.json and constraints.json as a result. In the model monitor mechanism, there are three parameters for "problem_type" in the following script. I think there are three parameters for "regression", "BinaryClassification" and "MulticlassClassification", but I don't know what CSV format to send the content in for "regression", and I'm not sure if AWS will handle it appropriately. Question. Incidentally, in the case of classification, 'BinaryClassification' and 'MulticlassClassification' results from the creation of appropriate CSVs. `The CSV in the case of classification is created below.` ```py probability, prediction, label [0.99,0.88], 0, 0 [0.34,0.77], 1, 0 ・・・ ``` - I don't know what kind of CSV content I should send to get the 'Regression' results. Here are some excerpts from and the CSV content we are currently testing. `Here are some excerpts from '` ```py model_quality_check_config = ModelQualityCheckConfig(, dataset_format=DatasetFormat.csv(header=False), output_s3_uri= f"sagemaker/monitor/", problem_type='Regression', inference_attribute= "_c1", ground_truth_attribute= "_c0" ) model_quality_check_step = QualityCheckStep( name="ModelQualityCheckStep", depends_on = ["lambdacsvtransform"], skip_check=skip_check_model_quality, register_new_baseline=register_new_baseline_model_quality, quality_check_config=model_quality_check_config, check_job_config=check_job_config, supplied_baseline_statistics=supplied_baseline_statistics_model_quality, supplied_baseline_constraints=supplied_baseline_constraints_model_quality, model_package_group_name="group" ) ``` `CSV(Regression)` ```py "_c0", "_c0" 0.88, 0.99 0.66, 0.87 ・・・ ```
asked a month ago