{"id":34045661,"url":"https://github.com/amineouerfellii/econometron","last_synced_at":"2026-04-02T00:38:45.907Z","repository":{"id":296229923,"uuid":"992673643","full_name":"AmineOuerfellii/econometron","owner":"AmineOuerfellii","description":"A Python package for time series forecasting and economic analysis, providing tools for simulation, estimation, and model evaluation with a focus on scalability and research applications.","archived":false,"fork":false,"pushed_at":"2025-08-31T16:26:15.000Z","size":21712,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-28T00:36:57.370Z","etag":null,"topics":["data-science","deep-learning","dsge-models","econometrics","forecasting","localprojections","macroeconometrics","prediction","projection-methods","time-series"],"latest_commit_sha":null,"homepage":"http://econometron.netlify.app","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AmineOuerfellii.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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-05-29T14:31:12.000Z","updated_at":"2026-02-20T03:33:27.000Z","dependencies_parsed_at":"2025-06-18T05:22:25.607Z","dependency_job_id":"2e82c6ea-8716-4e05-843e-35c4f57d8686","html_url":"https://github.com/AmineOuerfellii/econometron","commit_stats":null,"previous_names":["amineouerfellii/econometron"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/AmineOuerfellii/econometron","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmineOuerfellii%2Feconometron","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmineOuerfellii%2Feconometron/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmineOuerfellii%2Feconometron/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmineOuerfellii%2Feconometron/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AmineOuerfellii","download_url":"https://codeload.github.com/AmineOuerfellii/econometron/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmineOuerfellii%2Feconometron/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31293461,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-01T21:15:39.731Z","status":"ssl_error","status_checked_at":"2026-04-01T21:15:34.046Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["data-science","deep-learning","dsge-models","econometrics","forecasting","localprojections","macroeconometrics","prediction","projection-methods","time-series"],"created_at":"2025-12-13T23:16:29.311Z","updated_at":"2026-04-02T00:38:45.859Z","avatar_url":"https://github.com/AmineOuerfellii.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n![Econometron Logo](/econometron.png)\n\n# Econometron: A Python package for Econometric and Time Series Analysis\n[![PyPI Version](https://img.shields.io/pypi/v/econometron?color=blue\u0026label=PyPI)](https://pypi.org/project/econometron/)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/)\n## Introduction\n\nEconometron is a Python library designed for econometric modeling, time series analysis, and dynamic stochastic general equilibrium (DSGE) model solving and estimation. It provides a wide range of tools for researchers, economists, and data scientists to build, estimate, and analyze complex multivariate time series models and non-linear DSGE models. With a focus on flexibility and performance, Econometron supports both classical and modern approaches, including state-of-the-art neural network-based forecasting and robust statistical methods.\n\nWhether you're modeling economic time series, performing impulse response function (IRF) analysis, or solving non-linear DSGE models, Econometron offers a unified and efficient framework to streamline your workflow.\n\n## Key Features\n\n### Multivariate Statistical Time Series Models\n- **VAR (Vector Autoregression):** Model the dynamic relationships between multiple time series.  \n- **SVAR (Structural Vector Autoregression):** Incorporate structural restrictions for causal inference and policy analysis.  \n- **VARMA (Vector Autoregressive Moving Average):** Combine autoregressive and moving average components for enhanced flexibility.  \n- **VARIMA (Vector Autoregressive Integrated Moving Average):** Handle non-stationary time series with differencing.  \n\n### VARMA Identification\n- **Echelon Form Identification:** Implements the echelon form approach for identifying VARMA models, ensuring robust and unique parameter estimation in Python.\n\n### Neural Network-Based Forecasting\n- **N-BEATS (Neural Basis Expansion Analysis for Time Series):** A state-of-the-art deep learning model for univariate and multivariate time series forecasting.  \n- **N-BEATS + RevIN:** Enhances N-BEATS with Reversible Instance Normalization (RevIN) for improved generalization and robustness.\n\n### State Space Models\n- Flexible framework for modeling complex dynamic systems using state space representations, suitable for both linear and non-linear systems.\n\n### Estimation Methods\n- **Bayesian Estimation:** Leverage Bayesian techniques for parameter estimation, incorporating prior knowledge and uncertainty quantification.  \n- **Maximum Likelihood Estimation (MLE):** Optimize model parameters using likelihood-based methods for precise inference.\n\n### Impulse Response Functions (IRF)\n- **Local Projection IRF:** Compute impulse response functions using local projection methods, ideal for non-linear and robust analysis.\n\n### Non-Linear DSGE Model Solving\n- **Projection Methods:** Solve non-linear DSGE models using advanced numerical techniques:  \n  - Galerkin Method: Project solutions onto a basis of functions for accurate approximation.  \n  - Collocation Method: Solve at specific points to approximate the policy function.  \n  - Least Squares Method: Minimize residuals to find optimal solutions.\n\n\n## Getting Started\nTo use Econometron, install it via pip:\n\n```bash\npip install econometron\n````\n\n### Example: Fitting a VAR Model\n\n```python\nfrom econometron.Models.VectorAutoReg import VAR\n\n# Load your time series data\ndata = ...  # Your multivariate time series data\nmodel = VAR(data=data,max_p=2,check_stationnarity=True)\nresults = model.fit()\n```\n\nFor detailed documentation, tutorials, and examples, visit the [Econometron Documentation](https://econometron.netlify.app).\n\n\n\n## Why Econometron?\n\n* **Comprehensive:** Covers a wide range of econometric models, from classical VAR to cutting-edge neural network approaches.\n* **Flexible:** Supports both statistical and machine learning-based methods for time series analysis.\n* **Robust:** Implements state-of-the-art estimation and identification techniques for reliable results.\n* **User-Friendly:** Designed with Python's ecosystem in mind, integrating seamlessly with libraries like NumPy, Pandas, and PyTorch.\n\n\n\n## Code of Conduct\n\nWe are committed to fostering a welcoming and inclusive community. All participants are expected to:\n\n* Be respectful and considerate in interactions.\n* Avoid harassment or discriminatory behavior.\n* Use constructive feedback and maintain professionalism.\n* Respect the community and project’s guidelines.\n\nViolations may result in removal from the project or community channels. Please read the full [Code of Conduct](/CODE_OF_CONDUCT.md) for details.\n\n\n\n## Contributing\n\nContributions are highly valued. To contribute:\n\n1. Fork the repository.\n2. Create a new branch for your feature or bug fix.\n3. Implement your changes with clear, well-documented code.\n4. Run all tests to ensure stability.\n5. Submit a pull request describing your changes in detail.\n\nFor more information, see the full [Contributing Guide](/CONTRIBUTING.md).\n\n\n\n## License\n\nEconometron is licensed under the MIT License. See the LICENSE file for more information.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famineouerfellii%2Feconometron","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famineouerfellii%2Feconometron","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famineouerfellii%2Feconometron/lists"}