{"id":25575551,"url":"https://github.com/soham-shee/loadlens","last_synced_at":"2025-04-12T15:20:45.685Z","repository":{"id":248351787,"uuid":"827545106","full_name":"soham-shee/LoadLens","owner":"soham-shee","description":"A Load Forecasting Prediction System with Frontend","archived":false,"fork":false,"pushed_at":"2025-02-09T19:55:35.000Z","size":5834,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-26T09:51:10.647Z","etag":null,"topics":["forecasting-models","forecasting-time-series","gru","gru-model","load-forecasting"],"latest_commit_sha":null,"homepage":"https://load-lens.streamlit.app","language":"Jupyter Notebook","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/soham-shee.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}},"created_at":"2024-07-11T21:34:44.000Z","updated_at":"2025-02-09T19:55:38.000Z","dependencies_parsed_at":null,"dependency_job_id":"6ff23924-6788-422e-ae23-0609b2bb5182","html_url":"https://github.com/soham-shee/LoadLens","commit_stats":null,"previous_names":["soham-shee/loadlens"],"tags_count":0,"template":false,"template_full_name":"github/codespaces-jupyter","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soham-shee%2FLoadLens","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soham-shee%2FLoadLens/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soham-shee%2FLoadLens/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/soham-shee%2FLoadLens/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/soham-shee","download_url":"https://codeload.github.com/soham-shee/LoadLens/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248586217,"owners_count":21128998,"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","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":["forecasting-models","forecasting-time-series","gru","gru-model","load-forecasting"],"created_at":"2025-02-21T02:37:52.648Z","updated_at":"2025-04-12T15:20:45.677Z","avatar_url":"https://github.com/soham-shee.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Load Lens 😎\n\n[![kaggle](https://camo.githubusercontent.com/0d9d4c150c1ea613d3bf3f89ea6f9323ed808b60ffef0ce7d942913aa33a256a/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4b6167676c652d3230413545383f7374796c653d666f722d7468652d6261646765266c6f676f3d6b6167676c65266c6f676f436f6c6f723d7768697465)](https://www.kaggle.com/code/sohamshee/gru-model-load-forecasting)\\\nThis ML model is designed for load forecasting using Gated Recurrent Units (GRU). This user-friendly\napp empowers users to input their past values data, specify the number of epochs, and set the \nbatch size for training a GRU-based model. \nBy leveraging the GRU architecture, the app efficiently captures temporal dependencies in the \ndata, making it ideal for accurate load forecasting. Once the model is trained, users can easily \ndownload the trained model for future use, ensuring they have a reliable tool at their fingertips\nfor predicting load demand.\n\nIn addition to model training, this app offers a robust suite of features to enhance usability \nand flexibility. Users can upload a previously trained model alongside a CSV file to retrain \nthe model, accommodating new data and improving prediction accuracy. This iterative approach \nensures the model remains up-to-date with the latest trends and patterns. Furthermore, the app \nallows users to upload an existing model to forecast future values based on specified inputs, \nproviding quick and precise predictions. Whether you are training a new model, retraining with \nadditional data, or forecasting future values, this app offers a comprehensive solution for load \nforecasting needs.\n## Run Locally\n\nClone the project\n\n```bash\n  git clone https://github.com/soham-shee/LoadLens.git\n```\n\nInstall dependencies\n\n```bash\n  pip install -r 'requirements.txt'\n```\n\nStart the server\n\n```bash\n  streamlit run App.py\n```\n\nTo directly start it (Alternative Method)\n```bash\n  ./run_app.sh\n```\n\n## Demo\n\nhttps://load-lens.streamlit.app/\n\n## Acknowledgements\n\n - [Load Forecast Dataset (Panama Case Study)](https://www.kaggle.com/datasets/saurabhshahane/electricity-load-forecasting)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoham-shee%2Floadlens","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsoham-shee%2Floadlens","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsoham-shee%2Floadlens/lists"}