{"id":25582443,"url":"https://github.com/pcanadas/pytorch-weather-prediction","last_synced_at":"2026-05-01T06:33:32.339Z","repository":{"id":278341572,"uuid":"935272896","full_name":"pcanadas/pytorch-weather-prediction","owner":"pcanadas","description":"Predicción de temperaturas usando una red LSTM en PyTorch. Procesamiento de datos climáticos, entrenamiento de modelo y visualización de resultados.","archived":false,"fork":false,"pushed_at":"2025-02-19T12:47:54.000Z","size":387,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-02T06:58:36.840Z","etag":null,"topics":["clima","climate-data","data-science","deep-learning","forecasting","lstm","machine-learning","neural-networks","prediccion-del-tiempo","pytorch","series-temporales","temperature-prediction","time-series","weather-forecast"],"latest_commit_sha":null,"homepage":"","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/pcanadas.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":"2025-02-19T07:19:22.000Z","updated_at":"2025-02-19T12:47:58.000Z","dependencies_parsed_at":"2025-02-19T09:38:46.337Z","dependency_job_id":null,"html_url":"https://github.com/pcanadas/pytorch-weather-prediction","commit_stats":null,"previous_names":["pcanadas/pytorch-weather-prediction"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pcanadas/pytorch-weather-prediction","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcanadas%2Fpytorch-weather-prediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcanadas%2Fpytorch-weather-prediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcanadas%2Fpytorch-weather-prediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcanadas%2Fpytorch-weather-prediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pcanadas","download_url":"https://codeload.github.com/pcanadas/pytorch-weather-prediction/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pcanadas%2Fpytorch-weather-prediction/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32487490,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"online","status_checked_at":"2026-05-01T02:00:05.856Z","response_time":64,"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":["clima","climate-data","data-science","deep-learning","forecasting","lstm","machine-learning","neural-networks","prediccion-del-tiempo","pytorch","series-temporales","temperature-prediction","time-series","weather-forecast"],"created_at":"2025-02-21T05:16:31.009Z","updated_at":"2026-05-01T06:33:32.323Z","avatar_url":"https://github.com/pcanadas.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# :thermometer: PyTorch Weather Prediction\n\n## :memo: Descripción\nEste proyecto utiliza una red neuronal LSTM en PyTorch para predecir temperaturas máximas y mínimas a partir de datos climáticos históricos. Se basa en datos recopilados diariamente durante el año 2024, que incluyen información sobre temperatura, precipitación, viento y humedad.\n\n## \t:sparkles: Características\n- Implementación de un modelo de **red neuronal LSTM** para la predicción de series temporales.\n- Preprocesamiento de datos climáticos desde archivos CSV.\n- Normalización de datos con **MinMaxScaler** de `sklearn`.\n- Entrenamiento del modelo con PyTorch.\n- Visualización de los resultados mediante gráficos.\n\n## :pushpin: Requisitos\nPara ejecutar este proyecto, es necesario tener instaladas las siguientes bibliotecas:\n\n- Python 3.8+\n\n- PyTorch\n\n- Pandas\n\n- Scikit-learn\n\n- Matplotlib (opcional, para visualización)\n\nInstala las dependencias con:\n\n```bash\npip install -r requirements.txt\n```\n\n## \t:rocket: Uso\n\n1. Coloca el archivo de datos en la carpeta data/.\n\n2. Ejecuta el script principal:\n```\npython main.py\n```\n\n3. El modelo entrenará y generará predicciones de temperaturas máximas y mínimas.\n\n## \t:bar_chart: Datos\n\nLos datos meteorológicos provienen de registros diarios e incluyen:\n\n- `t_max`: Temperatura máxima diaria\n\n- `t_min`: Temperatura mínima diaria\n\n- `precipitacion`: Nivel de precipitación (mm)\n\n- `viento`: Velocidad del viento (km/h)\n\n- `humedad`: Humedad relativa (%)\n\n## :file_folder: Estructura del repositorio\n\n```\n📂 pytorch-weather-prediction\n│── data/                         # Carpeta para almacenar los datos CSV\n│   ├── clima_limpio_2024.csv     # Datos climáticos usados\n│── 📄 main.ipynb    # Código completo del modelo en jupyter notebook\n│── 📄 main.py    # Código completo del modelo\n│── 📄 README.md    # Documentación del proyecto\n│── 📄 requirements.txt    # Lista de dependencias\n\n```\n\n## :mag: Notas\n* El modelo usa una ventana de 30 días para predecir las temperaturas.\n\n* La normalización se aplica para mejorar el rendimiento del modelo.\n\n## :chart_with_upwards_trend: Resultados\nTras el entrenamiento, el modelo logra aprender tendencias en la temperatura y genera predicciones razonables basadas en los datos históricos.\n\nEjemplo de gráfico de predicciones:\n\n![Predicción de temperaturas](https://github.com/pcanadas/pytorch-weather-prediction/blob/main/Figure_1.png)\n\n## :construction: Futuras mejoras\n- Incluir más variables climáticas para mejorar la precisión.\n- Optimizar los hiperparámetros del modelo.\n- Implementar una API para consultar predicciones en tiempo real.\n\n## \t:bust_in_silhouette: Autor\n**Patricia Cañadas**  \nSi tienes preguntas o sugerencias, no dudes en abrir un issue en el repositorio.\n\n## \t:scroll: Licencia\nEste proyecto está bajo la licencia MIT.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpcanadas%2Fpytorch-weather-prediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpcanadas%2Fpytorch-weather-prediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpcanadas%2Fpytorch-weather-prediction/lists"}