Evaluate Tasks

The Gretel Evaluate tasks available

Task	Description	Notebook
sqs	Evaluate the quality of synthetic data using any two datsets to generate a Synthetic Data Quality Report.	generate-quality-report-with-evaluate
classification	Analyze synthetic data vs. real data trained on AutoML classifiers. The Gretel Synthetic Data Utility Report provides a detailed table of classification metrics.	evaluate-synthetic-data-classification
regression	Analyze synthetic data vs. real data trained on AutoML regression models. The Gretel Synthetic Data Utility Report provides a detailed table of regression metrics.	evaluate-synthetic-data-regression
text	Compare synthetic text data vs. training data. You can use this task to compare any natural language text you generate - including from non-Gretel LLM models	evaluate text quality (open in Colab)