SDMetrics
SDMetrics copied to clipboard
sdv-dev
Metrics to evaluate quality and efficacy of synthetic datasets.
**Suggested tests** - **Conditional probability distribution** in simulated vs. - conditional probability of Event A|B is calculated as the probability of seeing Event B within X days of Event A’s...
- Where sequence length is defined as the number of rows in the entity column per ID for single-table data. For multi-table this is defined as the sum of number...
### Problem Description The current Metrics implemented in SDV do not specifically measure the quality of sequences generated with CPAR. ### Expected behavior MSAS is a metric for sequential data...
### Problem Description Create the multi table QualityReport class. Implement the `generate` method and functionality. The `generate` method should take in the real and synthetic dataframes for computing the following:...
### Problem Description Add `plot_column` visualization utility method that takes in the real and synthetic data for one column and plots it. Plot a stacked line graph or histogram depending...
### Problem Description Add multi table QualityReport visualization methods. These methods are available in the report object, even if it's saved and loaded at a later time. Add the following...
### Problem Description Add get score methods for multi table Quality Report, so that the user can programmatically drill deeper and get the score info. Add the following methods: -...
### Problem Description Add save and load behavior to single table QualityReport, without saving the actual user data. ### Expected behavior ``` >>> report.save(filepath='my_quality_report.pkl') Warning: The quality report contains statistics...