{"id":21594165,"url":"https://github.com/ornl/vivaldi","last_synced_at":"2025-03-18T10:42:15.721Z","repository":{"id":234493928,"uuid":"789011809","full_name":"ORNL/vivaldi","owner":"ORNL","description":"Vivaldi is a ML pipeline which generates 3D (height) at a building-by-building level from 2D morphology features","archived":false,"fork":false,"pushed_at":"2024-04-19T15:00:09.000Z","size":50,"stargazers_count":0,"open_issues_count":1,"forks_count":1,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-01-24T17:14:55.845Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ORNL.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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}},"created_at":"2024-04-19T14:28:42.000Z","updated_at":"2024-04-19T15:00:13.000Z","dependencies_parsed_at":"2024-04-19T15:58:15.673Z","dependency_job_id":null,"html_url":"https://github.com/ORNL/vivaldi","commit_stats":null,"previous_names":["ornl/vivaldi"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ORNL%2Fvivaldi","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ORNL%2Fvivaldi/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ORNL%2Fvivaldi/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ORNL%2Fvivaldi/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ORNL","download_url":"https://codeload.github.com/ORNL/vivaldi/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244206914,"owners_count":20416091,"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":[],"created_at":"2024-11-24T17:16:22.914Z","updated_at":"2025-03-18T10:42:15.689Z","avatar_url":"https://github.com/ORNL.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# vivaldi_bh - Model Name: Vivaldi \nPOC: Clinton Stipek - stipekcw@ornl.gov\n\n## Getting started\n\nThis project's goal is to ingest morphology features (2D) and infer height (3D) for individual buildings:\n\n1. The following breaks the vivald process into the respective steps\n    - Identify 2D buildings from AOI\n    - Generate morphology features using the Gauntlet feature morphology process\n        - Please see Taylor Hauser (hausertr@ornl.gov) for availability of Gauntlet features\n    - Run a recursive feature eliminator to streamline modelling process\n    - Hyper-tune parameters via bayesian optimization\n    - Infer building heights at a building-by-building level leveraging a XGBoost algorithm\n\n\n## Docker\n- There is a docker image for this project, to use the image please clone the repo and then go to vivaldi_bh/src for the docker files\n- once cloned and in the right file trajectory, run the following lines in order in cmd line:\n    1. docker-compose build vivaldi_bh\n    2. docker-compose up -d vivaldi_by\n    3. docker-compose exec vivaldi_bh python /files/vivaldi.py\n- please note that for command 3, the 'vivaldi.py' is the vivaldi process outlined in Getting Started\n- Please message Clinton Stipek (stipekcw@ornl.gov) for assistance\n\n## Script run order\n1. Run rfe.py (docker-compose exec vivaldi_by python /files/rfe.py - if using linux)\n2. Run vivaldi_bh.py (docker-compose exec vivaldi_bh python /files/vivaldi_bh.py - if using linux)\n\n## Data\n- The data that vivaldi works with is built off the Gauntlet process\n- Gauntlet v2 generates 65 morphological features that is in a tabular form at a building-by-building level \n- The Gauntlet features are stored in PostGresQL\n- Please see Taylor Hauser (hausertr@ornl.gov) for access to the data\n- Please see Clinton Stipek (stipekcw@ornl.gov) for gauntlet features necessary to run rfe and vivaldi_bh\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fornl%2Fvivaldi","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fornl%2Fvivaldi","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fornl%2Fvivaldi/lists"}