sdmetrics
Metrics for Synthetic Data Generation Projects
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
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 · maintenance · safety
MIT (permissive) — 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.
last release 2026-07-24 (21 days) · last repo commit 2026-08-14 · 263 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 134,769 downloads/mo, #11,461 on PyPI
Alternatives
Verify before relying
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)- 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.
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 on this page. Verify before relying on it.
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
sdmetrics on PyPI
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 the current Python release <3.15,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packagesnumpypandasscikit-learnscipycopulastqdmplotly |
| Maintenance | Actively maintained 21 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 134,769 / month, #11,461 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 2 - Pre-AlphaIntended Audience :: DevelopersNatural Language :: EnglishProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: Python :: 3.9 |
Evidence: sdmetrics-0.28.2-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “synthetic data evaluation”
- sdmetricsSDMetrics evaluates synthetic data by computing quality and privacy…
- utilsforecastProvides utilities for time-series forecasting workflows, including…
- sdvSDV generates synthetic tabular data by learning patterns from real…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also sdv · deepecho · rdt · copulas · ctgan · data-designer · dbldatagen · oil-reservoir-synthesizer · pyannote-metrics · evidently