---
id: sdmetrics
version: "0.28.2"
license: MIT
license_treatment: permissive
maintenance: active
---

# sdmetrics — Metrics for Synthetic Data Generation Projects

License: permissive · Maintenance: active · Downloads: 134.8K/mo

## What it is and what it does

SDMetrics is a library for evaluating synthetic data by comparing it to the original real data. It computes metrics across multiple dimensions—column shapes, pair trends, boundary adherence, row novelty—and packages them into interactive reports with visualizations. The library is model-agnostic: it works with any synthetic data regardless of the generation method, asking only for the real data, synthetic data, and metadata describing the schema.

The package sits within the Synthetic Data Vault ecosystem and is designed for teams that need to measure and communicate data quality and privacy. It includes both high-level report generators (QualityReport) and granular metric functions you can call directly. Reports can be saved, loaded, and shared; visualizations are built on Plotly.

Use it for:

- Generate a quality report comparing synthetic and real data to validate a synthetic data generation pipeline before deployment.
- Compute individual metrics like BoundaryAdherence or NewRowSynthesis to audit specific synthetic data properties.
- Save and share evaluation reports with stakeholders to document synthetic data fitness for downstream use.
- Benchmark multiple synthetic data generation models by running the same metrics across their outputs.
- Assess privacy risk by measuring how closely synthetic data reproduces real data patterns.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

SDMetrics evaluates synthetic data by computing quality and privacy metrics and generating comparison reports against real data, independent of how the synthetic data was created.

Yes. SDMetrics is actively maintained, has no known vulnerabilities, carries a permissive MIT license, and solves a concrete problem in synthetic data workflows. Install it if you generate or consume synthetic data and need to measure quality and privacy. The low install friction and model-agnostic design make it a practical fit for most data teams.

## Install

pip install sdmetrics
uv add sdmetrics
poetry add sdmetrics

## Installing sdmetrics

Before you install: Low friction: pure Python wheel with seven runtime dependencies (numpy, pandas, scikit-learn, scipy, copulas, tqdm, plotly). Active maintenance with a release 21 days ago and ongoing commits.

License in practice: MIT license permits commercial and private use with minimal restrictions—you may use, modify, and distribute the package freely provided you include the license notice.

Quickstart:

pip install sdmetrics

from sdmetrics import load_demo
from sdmetrics.reports.single_table import QualityReport

real_data, synthetic_data, metadata = load_demo(modality='single_table')
my_report = QualityReport()
my_report.generate(real_data, synthetic_data, metadata)

Verify before relying:

- Whether the library supports time-series or multi-table synthetic data evaluation beyond single-table reports.
- Performance characteristics when evaluating large datasets or high-dimensional data.
- Specific privacy metrics available and their theoretical foundations or compliance certifications.

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 134.8K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

synthetic data evaluation, quality metrics for synthetic data, privacy assessment synthetic data, synthetic data comparison reports, data generation validation, synthetic data benchmarking, model-agnostic data metrics, synthetic-data, data-quality, evaluation-metrics

[View on SkillFed](https://skillfed.io/packages/sdmetrics) · [View on PyPI](https://pypi.org/project/sdmetrics/)