{"id":31740377,"url":"https://github.com/nyx1311/timelstm","last_synced_at":"2026-04-27T16:32:32.454Z","repository":{"id":317814414,"uuid":"1068958937","full_name":"Nyx1311/TimeLSTM","owner":"Nyx1311","description":"TimeLSTM: An interactive Streamlit app for multi-step time series forecasting using LSTM networks, featuring data preprocessing, visualization, GPU-accelerated model training, and automated result export.","archived":false,"fork":false,"pushed_at":"2025-10-03T07:32:33.000Z","size":18717,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-03T08:39:00.523Z","etag":null,"topics":["deep-learning","deep-neural-networks","lstm-neural-networks","numpy","pandas","ploty","python3","scikit-learn-python","statsmodels","streamlit","torch","tqdm"],"latest_commit_sha":null,"homepage":"","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/Nyx1311.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"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":"2025-10-03T07:18:11.000Z","updated_at":"2025-10-03T07:35:51.000Z","dependencies_parsed_at":"2025-10-03T08:49:05.395Z","dependency_job_id":null,"html_url":"https://github.com/Nyx1311/TimeLSTM","commit_stats":null,"previous_names":["nyx1311/timelstm"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Nyx1311/TimeLSTM","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Nyx1311%2FTimeLSTM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Nyx1311%2FTimeLSTM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Nyx1311%2FTimeLSTM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Nyx1311%2FTimeLSTM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Nyx1311","download_url":"https://codeload.github.com/Nyx1311/TimeLSTM/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Nyx1311%2FTimeLSTM/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279001320,"owners_count":26083040,"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":"2025-10-09T02:00:07.460Z","response_time":59,"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":["deep-learning","deep-neural-networks","lstm-neural-networks","numpy","pandas","ploty","python3","scikit-learn-python","statsmodels","streamlit","torch","tqdm"],"created_at":"2025-10-09T10:18:22.938Z","updated_at":"2026-04-27T16:32:32.422Z","avatar_url":"https://github.com/Nyx1311.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n**TimeLSTM**\n\nAn interactive **Streamlit** application for **multi-step time series forecasting** using **LSTM (Long Short-Term Memory) networks**.\nDesigned for both data science professionals and non-technical users, this project makes deep learning–powered forecasting **accessible, customizable, and intuitive**.\n\n---\n\n**✨ Features**\n\n* 📂 **Data Handling**\n\n  * Upload CSV files with auto date-detection \u0026 mixed datatype support.\n\n* 🧹 **Preprocessing**\n\n  * Handles missing values, categorical encoding, and feature scaling.\n\n* 📊 **Exploration \u0026 Visualization**\n\n  * Interactive time series plots, histograms, correlation heatmaps, and seasonal decomposition.\n\n* 🧠 **LSTM Model**\n\n  * Customizable architecture (layers, neurons, forecast horizon) with GPU acceleration.\n\n* ⚡ **Training Framework**\n\n  * Adjustable epochs, batch size, and learning rate with real-time monitoring.\n\n* 📈 **Results Analysis**\n\n  * MSE, RMSE, MAE metrics, residual error inspection, and forecast visualization.\n\n* 💾 **Export \u0026 Deployment**\n\n  * Save results as CSV/plots, persistent model storage for reuse.\n\n---\n\n**⚙️ How It Works**\n\n1. **Streamlit UI** – Provides an interactive web-based interface for model training and forecasting.\n\n2. **Data Pipeline** – Upload, preprocess, and visualize datasets before training.\n\n3. **LSTM Training** – Uses PyTorch to train customizable models with GPU support.\n\n4. **Evaluation** – Generates forecast plots, error metrics, and residual analysis.\n\n5. **Export Options** – Save trained models, forecasts, and plots for future use.\n\n---\n\n**🌍 Use Cases**\n\n* 💹 **Finance** – Stock price prediction (multi-day horizon).\n\n* 🔌 **Energy** – Electricity demand forecasting for smart grids.\n\n* 🛒 **Retail** – Product demand prediction for inventory optimization.\n\n* 🏥 **Healthcare** – Patient admission forecasting with seasonal trends.\n\n---\n\n**🛠️ Requirements**\n\n* Python 3.8+\n\n* Streamlit\n\n* PyTorch\n\n* Pandas, scikit-learn, statsmodels, Plotly\n\nInstall dependencies:\n\n```bash\npip install -r requirements.txt\n```\n\n---\n\n**🚀 Getting Started**\n\n```bash\ngit clone https://github.com/Nyx1311/TimeLSTM.git\ncd TimeLSTM\n\npip install -r requirements.txt\n\nstreamlit run app.py\n```\n\n---\n\n**🤝 Contributing**\n\nPull requests are welcome!\nFor major changes, open an issue first to discuss improvements.\n\n---\n\n**📜 License**\n\nThis project is licensed under the **MIT License**.\n\n---\nTest app at https://timelstm.streamlit.app/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnyx1311%2Ftimelstm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnyx1311%2Ftimelstm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnyx1311%2Ftimelstm/lists"}