{"id":15646297,"url":"https://github.com/jonnoftw/traffic-prediction","last_synced_at":"2025-04-30T12:03:45.268Z","repository":{"id":140473951,"uuid":"68896778","full_name":"JonnoFTW/traffic-prediction","owner":"JonnoFTW","description":"Predict traffic flow with LSTM. For experimental purposes only, unsupported!","archived":false,"fork":false,"pushed_at":"2018-07-19T02:56:36.000Z","size":31,"stargazers_count":55,"open_issues_count":3,"forks_count":22,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-02-25T07:41:35.224Z","etag":null,"topics":["experimental","hyperas","hyperopt","lstm","traffic-prediction"],"latest_commit_sha":null,"homepage":"","language":"Python","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/JonnoFTW.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}},"created_at":"2016-09-22T07:39:22.000Z","updated_at":"2025-02-05T08:59:43.000Z","dependencies_parsed_at":null,"dependency_job_id":"bfa91125-7f4d-4cdb-99d8-0eb9402ca6ab","html_url":"https://github.com/JonnoFTW/traffic-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/JonnoFTW%2Ftraffic-prediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JonnoFTW%2Ftraffic-prediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JonnoFTW%2Ftraffic-prediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JonnoFTW%2Ftraffic-prediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JonnoFTW","download_url":"https://codeload.github.com/JonnoFTW/traffic-prediction/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242650896,"owners_count":20163610,"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":["experimental","hyperas","hyperopt","lstm","traffic-prediction"],"created_at":"2024-10-03T12:12:20.619Z","updated_at":"2025-03-09T05:30:29.186Z","avatar_url":"https://github.com/JonnoFTW.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LSTM Based Traffic Prediction\n\nThis project seeks to use LSTM for traffic prediction using the [Keras](https://keras.io/) frontend for [Theano](http://deeplearning.net/software/theano/). Hyperparameter optimisation is used to find the best set of parameters for the network.\n\n### Usage\n\nRun:\n\n```\npip install -r requirements.txt\n```\n\nThen edit [main.py](https://github.com/JonnoFTW/traffic-prediction/blob/master/main.py) so that it uses your own parameters for the network. It will attempt to store hyperparameter results in mongodb. You can use [show_results.py](https://github.com/JonnoFTW/traffic-prediction/blob/master/show_results.py) to view them. Please keep in mind this for experimentation only and not appropriate for production.\n\n\nRun using:\n```\npython main.pymain.py \u003csteps eg. 1\u003e \u003c/path/to/data.csv\u003e \u003ctrain_test_split eg. 0.75\u003e \u003cnum_epochs eg. 10\u003e \u003cmodel_trials eg. 20\u003e\n```\n\nThe CSV should have a the following format:\n```\ntimestamp,16,17,18,19,20,21\n2011-12-31 23:55:00,4,6,8,13,3,0\n2012-01-01 00:00:00,5,7,8,10,3,2\n2012-01-01 00:05:00,3,3,7,15,1,2\n2012-01-01 00:10:00,9,3,3,7,1,1\n2012-01-01 00:15:00,3,4,12,15,2,0\n2012-01-01 00:20:00,7,5,11,19,2,2\n```\nBasically, the first column must be a timestamp and the rest integer values.\n\n\nScripts are also provided to speed up processing via Sun Grid Engine. Though they are unreliable because of the length of time it takes for theano to compile the models. You will also need CUDA and a compatible card if you want the speedups they provide. ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjonnoftw%2Ftraffic-prediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjonnoftw%2Ftraffic-prediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjonnoftw%2Ftraffic-prediction/lists"}