{"id":13419585,"url":"https://github.com/kootenpv/whereami","last_synced_at":"2025-05-14T02:09:07.197Z","repository":{"id":11150443,"uuid":"68537488","full_name":"kootenpv/whereami","owner":"kootenpv","description":"Uses WiFi signals :signal_strength: and machine learning to predict where you are ","archived":false,"fork":false,"pushed_at":"2023-11-30T10:27:09.000Z","size":66,"stargazers_count":5126,"open_issues_count":15,"forks_count":248,"subscribers_count":101,"default_branch":"master","last_synced_at":"2025-04-10T11:01:46.089Z","etag":null,"topics":["access-point","cross-platform","distance","hacktoberfest","hacktoberfest2021","indoor-positioning","whereami","wifi-signal"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kootenpv.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}},"created_at":"2016-09-18T17:50:24.000Z","updated_at":"2025-04-08T11:34:00.000Z","dependencies_parsed_at":"2024-01-29T09:19:20.645Z","dependency_job_id":"244de731-ff9d-4dad-88c1-e7d1e69eea15","html_url":"https://github.com/kootenpv/whereami","commit_stats":{"total_commits":74,"total_committers":10,"mean_commits":7.4,"dds":"0.16216216216216217","last_synced_commit":"a9503431136f61bcbb21e249847d30be2b9cd33a"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kootenpv%2Fwhereami","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kootenpv%2Fwhereami/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kootenpv%2Fwhereami/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kootenpv%2Fwhereami/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kootenpv","download_url":"https://codeload.github.com/kootenpv/whereami/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254053240,"owners_count":22006717,"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":["access-point","cross-platform","distance","hacktoberfest","hacktoberfest2021","indoor-positioning","whereami","wifi-signal"],"created_at":"2024-07-30T22:01:18.060Z","updated_at":"2025-05-14T02:09:02.183Z","avatar_url":"https://github.com/kootenpv.png","language":"Python","funding_links":[],"categories":["Python","Python (1887)","Archs","📚 Project Purpose"],"sub_categories":["Hardware","Machine Learning (Intermediate-Level"],"readme":"## whereami\n\n[![Build Status](https://travis-ci.org/kootenpv/whereami.svg?branch=master)](https://travis-ci.org/kootenpv/whereami)\n[![Coverage Status](https://coveralls.io/repos/github/kootenpv/whereami/badge.svg?branch=master)](https://coveralls.io/github/kootenpv/whereami?branch=master)\n[![PyPI](https://img.shields.io/pypi/v/whereami.svg?style=flat-square)](https://pypi.python.org/pypi/whereami/)\n[![PyPI](https://img.shields.io/pypi/pyversions/whereami.svg?style=flat-square)](https://pypi.python.org/pypi/whereami/)\n\nUses WiFi signals and machine learning (sklearn's RandomForest) to predict where you are. Even works for small distances like 2-10 meters.\n\nYour computer will known whether you are on Couch #1 or Couch #2.\n\n## Cross-platform\n\nWorks on OSX, Windows, Linux (tested on Ubuntu/Arch Linux).\n\nThe package [access_points](https://github.com/kootenpv/access_points) was created in the process to allow scanning wifi in a cross platform manner. Using `access_points` at command-line will allow you to scan wifi yourself and get JSON output.\n`whereami` builds on top of it.\n\n### Installation\n\n    pip install whereami\n\n### Usage\n\n```bash\n# in your bedroom, takes a sample\nwhereami learn -l bedroom\n\n# in your kitchen, takes a sample\nwhereami learn -l kitchen\n\n# get a list of already learned locations\nwhereami locations\n\n# cross-validated accuracy on historic data\nwhereami crossval\n# 0.99319\n\n# use in other applications, e.g. by piping the most likely answer:\nwhereami predict | say\n# Computer Voice says: \"bedroom\"\n\n# probabilities per class\nwhereami predict_proba\n# {\"bedroom\": 0.99, \"kitchen\": 0.01}\n```\n\nIf you want to delete some of the last lines, or the data in general, visit your `$USER/.whereami` folder.\n\n### Python\n\nAny of the functionality is available in python as well. Generally speaking, commands can be imported:\n\n    from whereami import learn\n    from whereami import get_pipeline\n    from whereami import predict, predict_proba, crossval, locations\n\n### Accuracy\nk\nGenerally it should work really well. I've been able to learn using only 7 access points at home (test using `access_points -n`). At organizations you might see 70+.\n\nDistance: anything around ~10 meters or more should get \u003e99% accuracy.\n\nIf you're adventurous and you want to learn to distinguish between couch #1 and couch #2 (i.e. 2 meters apart), it is the most robust when you switch locations and train in turn. E.g. first in Spot A, then in Spot B then start again with A.\nDoing this in spot A, then spot B and then immediately using \"predict\" will yield spot B as an answer usually. No worries, the effect of this temporal overfitting disappears over time. And, in fact, this is only a real concern for the very short distances. Just take a sample after some time in both locations and it should become very robust.\n\nHeight: Surprisingly, vertical difference in location is typically even more distinct than horizontal differences.\n\n### Related Projects\n- The [wherearehue](https://github.com/DeastinY/wherearehue) project can be used to toggle Hue light bulbs based on the learned locations.\n\n###  Almost entirely \"copied\" from:\n\nhttps://github.com/schollz/find\n\nThat project used to be in Python, but is now written in Go. `whereami` is in Python with lessons learned implemented.\n\n### Tests\n\nIt's possible to locally run tests for python 2.7, 3.4 and 3.5 using tox.\n\n    git clone https://github.com/kootenpv/whereami\n    cd whereami\n    python setup.py install\n    tox\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkootenpv%2Fwhereami","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkootenpv%2Fwhereami","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkootenpv%2Fwhereami/lists"}