{"id":31788109,"url":"https://github.com/etsi-ai/etsi-watchdog","last_synced_at":"2025-10-10T14:14:34.926Z","repository":{"id":302025195,"uuid":"1008967823","full_name":"etsi-ai/etsi-watchdog","owner":"etsi-ai","description":"Real-time data drift detection and monitoring for machine learning pipelines.","archived":false,"fork":false,"pushed_at":"2025-08-02T14:49:54.000Z","size":82920,"stargazers_count":21,"open_issues_count":24,"forks_count":26,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-02T16:33:14.605Z","etag":null,"topics":["drift-detection","machine-learning","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/etsi-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-26T11:19:11.000Z","updated_at":"2025-08-02T14:49:58.000Z","dependencies_parsed_at":"2025-08-02T16:22:47.875Z","dependency_job_id":null,"html_url":"https://github.com/etsi-ai/etsi-watchdog","commit_stats":null,"previous_names":["etsi-ai/etsi-watchdog"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/etsi-ai/etsi-watchdog","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/etsi-ai%2Fetsi-watchdog","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/etsi-ai%2Fetsi-watchdog/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/etsi-ai%2Fetsi-watchdog/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/etsi-ai%2Fetsi-watchdog/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/etsi-ai","download_url":"https://codeload.github.com/etsi-ai/etsi-watchdog/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/etsi-ai%2Fetsi-watchdog/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279004178,"owners_count":26083688,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-10T02:00:06.843Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["drift-detection","machine-learning","python"],"created_at":"2025-10-10T14:14:31.671Z","updated_at":"2025-10-10T14:14:34.919Z","avatar_url":"https://github.com/etsi-ai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# etsi-watchdog\n\n[![PyPI](https://img.shields.io/pypi/v/etsi-watchdog.svg)](https://pypi.org/project/etsi-watchdog/)\n[![PyPI Downloads](https://static.pepy.tech/badge/etsi-watchdog)](https://pepy.tech/projects/etsi-watchdog)\n\n[📄 DOCS](https://etsi-ai.github.io/docs/etsi-watchdog.html)\n\n**Real-time data drift detection for machine learning pipelines.**\n\n`etsi-watchdog` is a production-ready Python library for drift detection, version comparison, and real-time monitoring of data streams. Designed for ML practitioners, data scientists, and AI engineers who need reliable data quality insights.\n\n---\n\n## ✨ Features\n\n- PSI-based Drift Detection (more algorithms coming)\n- Rolling Monitoring with time-frequency windowing\n- Version Drift Comparison between model/data snapshots\n- Built-in Visualization \u0026 JSON Export\n- Minimal Dependencies \u0026 Fast Performance\n- Clear API, suitable for both research and production\n\n---\n\n## 📦 Installation\n\n```bash\npip install etsi-watchdog\n```\n\n---\n\n## ⚡ Quickstart\n\n### 🔹 Drift Detection\n```python\nfrom etsi.watchdog import DriftCheck\nimport pandas as pd\n\nref = pd.read_csv(\"reference.csv\")\nlive = pd.read_csv(\"current.csv\")\n\ncheck = DriftCheck(ref)\nresults = check.run(live, features=[\"age\", \"salary\"])\n\nfor feat, result in results.items():\n    print(result.summary())\n    result.plot()\n```\n\n---\n\n### 🔹 Rolling Monitoring\n```python\nfrom etsi.watchdog import Monitor\n\nmonitor = Monitor(reference_df=ref)\nmonitor.enable_logging(\"logs/rolling_log.csv\")\n\nresults = monitor.watch_rolling(\n    df=live_data_stream,\n    window=50,\n    freq=\"D\",\n    features=[\"age\", \"salary\"]\n)\n```\n\n---\n\n### 🔹 Drift Comparison (A/B)\n```python\nfrom etsi.watchdog import DriftComparator\n\ncheck = DriftCheck(ref)\nv1 = check.run(live1, features=[\"age\", \"salary\"])\nv2 = check.run(live2, features=[\"age\", \"salary\"])\n\ncomp = DriftComparator(v1, v2)\nprint(comp.diff())\n```\n\n---\n\n## 🚀 etsi-watchdog v3 — Roadmap \u0026 Vision\n\n| Feature Area | Description |\n|--------------|-------------|\n| **Multi-Algorithm Support** | Support for additional drift metrics:\u003cbr\u003e- Jensen–Shannon Divergence (JSD)\u003cbr\u003e- Wasserstein Distance\u003cbr\u003e- Kolmogorov–Smirnov Test (K-S)\u003cbr\u003e- Tree-based drift (e.g., `DeepDrift`) |\n| **Plug-in Architecture** | Drift algorithms will be fully plug-and-play. Custom metric support via `register_drift_function()` API. |\n| **Real-Time Stream Hooks** | Support for Kafka/Redis/WebSockets to detect drift on live data streams. |\n| **Concept Drift Detection** | Integration with models to detect label or concept drift, not just feature distribution shift. |\n| **CLI \u0026 YAML Configs** | Full CLI support:\u003cbr\u003e`etsi-watchdog detect --ref ref.csv --live live.csv --features age salary`\u003cbr\u003e+ YAML-based configuration for automated pipelines. |\n| **Benchmark Suite** | Built-in benchmarking with synthetic datasets to evaluate metric sensitivity and response time. |\n| **Dashboard UI (Optional)** | Lightweight dashboard (Streamlit/FastAPI) for monitoring drift over time visually. |\n| **Drift Summary Reports** | Generate PDF/HTML reports with drift summary, top features, histograms, and timestamps. |\n| **Sklearn \u0026 Pandas Integration** | `DriftCheck` will support `.fit()`/`.transform()` methods like Scikit-learn transformers. |\n\n---\n\n## 🤝 Contributing\n\nContributions are welcome! 🙌  \nIf you have an idea for a drift metric, integration, or improvement, feel free to open an issue or pull request.\n\nPlease refer to [CONTRIBUTING.md](https://github.com/etsi-ai/etsi-watchdog/blob/main/CONTRIBUTING.md) for guidelines.\n\n---\n\n## 🧾 License\n\nLicensed under the **BSD-2-Clause License**.  \nSee the [LICENSE](./LICENSE) file for details.\n\n---\n\n## 👨‍💻 Maintainers\n\n- [@PRIYANSH](https://github.com/PriyanshSrivastava0305)\n---\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fetsi-ai%2Fetsi-watchdog","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fetsi-ai%2Fetsi-watchdog","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fetsi-ai%2Fetsi-watchdog/lists"}