{"id":21678223,"url":"https://github.com/sharedstreets/speed-prediction","last_synced_at":"2025-04-12T05:15:08.479Z","repository":{"id":91603944,"uuid":"210664397","full_name":"sharedstreets/speed-prediction","owner":"sharedstreets","description":"An OSRM predictive speed profiler using Uber Movement Speed data","archived":false,"fork":false,"pushed_at":"2019-09-25T16:49:31.000Z","size":37,"stargazers_count":17,"open_issues_count":1,"forks_count":3,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-04-12T05:14:56.994Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://sharedstreets.github.io/speed-prediction/","language":"JavaScript","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/sharedstreets.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":"2019-09-24T17:50:17.000Z","updated_at":"2023-07-21T08:58:02.000Z","dependencies_parsed_at":null,"dependency_job_id":"5125f2df-4bda-4a91-bc32-db5423c3bd60","html_url":"https://github.com/sharedstreets/speed-prediction","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sharedstreets%2Fspeed-prediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sharedstreets%2Fspeed-prediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sharedstreets%2Fspeed-prediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sharedstreets%2Fspeed-prediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sharedstreets","download_url":"https://codeload.github.com/sharedstreets/speed-prediction/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248519557,"owners_count":21117761,"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":"2024-11-25T14:27:21.300Z","updated_at":"2025-04-12T05:15:08.468Z","avatar_url":"https://github.com/sharedstreets.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# speed-prediction\nAn OSRM predictive speed profiler using Uber Movement Speed data\n\n### [Demo](https://sharedstreets.github.io/speed-prediction/)\n\n![screenshot](https://i.imgur.com/GVLmS3a.png)\n\n## Install\n\n```sh\ngit clone \ngit@github.com:sharedstreets/speed-prediction.git\ncd speed-prediction\nnpm install\n```\n\n## Download\n\nDownload all Uber speed files for a city into your project directory, along with an OSM extract for the corresponding area.\n\n## Run\n\nThis will run the process with 8GB of RAM. It is not necessary to provide more RAM, and the process will likely run with much less. Expect the entire process to take about 2 hours for a major metropolitan area.\n\n```sh\ntime node --max-old-space-size=8192 index.js\n```\n\n## Format\n\nThe output format is the standard OSRM csv format for traffic profiles described [here](https://github.com/Project-OSRM/osrm-backend/wiki/Traffic). There is one profile per day of week and hour of day, 0 indexed. For example, Sunday at midnight is described in the profile `0-0`, whereas the Tuesday noon profile is described in `2-12`. OSRM is designed to load exactly one profile at a time, so for ETA or isochrone analysis, you would cycle through your times of interest, loading a new profile after each batch.\n\n## Analysis Demo\n\nTo demonstrate how these profiles can be used, a demo script is provided, called `demo.js`. This demo assumes you have downloaded and processed profiles for San Francisco, CA. The script will load each profile in succession, use OSRM to generate a predicted ETA for each control route, then output the data into a set of charts. These charts show how congestion changes over the course of a typical week across routes of interest.\n\n## License\n\nThis code is provided under the MIT license. Note that this library uses OpenStreetMap data, licensed under the ODBL, as well as Uber Movement data, licensed under CC BY-NC 3.0 US. Both licenses require attribution and additional restrictions should be analyzed before using.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsharedstreets%2Fspeed-prediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsharedstreets%2Fspeed-prediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsharedstreets%2Fspeed-prediction/lists"}