{"id":28437364,"url":"https://github.com/ianpangdev/ecobici-data-science-workflow","last_synced_at":"2026-05-01T02:32:53.288Z","repository":{"id":291040290,"uuid":"973962530","full_name":"IanPangDev/ecobici-data-science-workflow","owner":"IanPangDev","description":"Este proyecto analiza los registros de viajes del sistema Ecobici de la Ciudad de México mediante un flujo de trabajo basado en CRISP-DM. Incluye un proceso ETL para extraer, transformar y cargar los datos en una base MongoDB Atlas, permitiendo su análisis y modelado.","archived":false,"fork":false,"pushed_at":"2025-05-03T04:29:33.000Z","size":2056,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-05-01T02:32:38.791Z","etag":null,"topics":["data-science","etl","etl-pipeline","machine-learning","machine-learning-algorithms","mongoatlas","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/IanPangDev.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-04-28T03:48:34.000Z","updated_at":"2025-05-03T04:29:36.000Z","dependencies_parsed_at":"2025-06-28T01:31:27.900Z","dependency_job_id":"bd51b2f4-0ff2-45c9-96ab-a0ad33b80944","html_url":"https://github.com/IanPangDev/ecobici-data-science-workflow","commit_stats":null,"previous_names":["ianpangdev/ecobici-data-science-workflow"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/IanPangDev/ecobici-data-science-workflow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IanPangDev%2Fecobici-data-science-workflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IanPangDev%2Fecobici-data-science-workflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IanPangDev%2Fecobici-data-science-workflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IanPangDev%2Fecobici-data-science-workflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/IanPangDev","download_url":"https://codeload.github.com/IanPangDev/ecobici-data-science-workflow/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IanPangDev%2Fecobici-data-science-workflow/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32483406,"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":["data-science","etl","etl-pipeline","machine-learning","machine-learning-algorithms","mongoatlas","python"],"created_at":"2025-06-05T23:41:29.410Z","updated_at":"2026-05-01T02:32:53.270Z","avatar_url":"https://github.com/IanPangDev.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ecobici-data-science-workflow\n\n## Descripción general\nEste proyecto analiza los registros de viajes del sistema ECOBICI de la Ciudad de México utilizando un flujo de trabajo basado en la metodología **CRISP-DM**. Incluye dos procesos **ETL** que permiten extraer, transformar y cargar los datos en una base de datos **MongoDB Atlas** para su posterior análisis y modelado.\n\n## Tecnologías\n- Python  \n- MongoDB Atlas\n\n## Estructura del proyecto\n- **etl_historico**: Conjunto de scripts responsables del proceso ETL que transforma registros históricos desde archivos CSV hacia MongoDB Atlas.  \n- **etl_station**: Conjunto de scripts que realizan el proceso ETL a partir de la API con informacion de las estaciones de ECOBICI hacia MongoDB Atlas.  \n- **Models**: Contiene las clases que representan cada colección almacenada en MongoDB Atlas.\n\n## Modelos de predicción\n\n### Predicción de estaciones de arribo\nSe utilizó un modelo **RandomForest**. Las variables consideradas fueron:\n\n- `genero`: Género del usuario por viaje  \n- `start_cluster`: Clúster de las estaciones de retiro  \n- `stop_cluster`: Clúster de las estaciones de arribo  \n- `hora_retiro_sin`: Hora de retiro representada de forma cíclica (seno)  \n- `hora_retiro_cos`: Hora de retiro representada de forma cíclica (coseno)\n\n### Pronóstico de cantidad de retiros por día\nTambién se empleó un modelo **RandomForest**. Las variables utilizadas fueron:\n\n- `fecha`: Fecha del retiro  \n- `conteo`: Número de retiros registrados en esa fecha\n\n### Dashboard de análisis\n\n\u003ca href='https://app.powerbi.com/view?r=eyJrIjoiY2E0ZGU3YzYtNzdhYi00ZjdmLWFlN2UtN2NkZTcxZjVmZmIxIiwidCI6IjVmMjgyOTEwLTE3NmYtNDU5ZC1hYjdkLWI3NDRhYTZlZmMwNyIsImMiOjR9' align=\"center\"\u003e\u003cimg src=\"img\\dashboard.png\"\u003e\u003c/img\u003e\u003c/a\u003e","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fianpangdev%2Fecobici-data-science-workflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fianpangdev%2Fecobici-data-science-workflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fianpangdev%2Fecobici-data-science-workflow/lists"}