Machine Learned Auto brightness
Project description
brightml: Machine-Learned Auto brightness
The goal of this package is to automatically manage brightness on laptops, with "zero config"; using machine learning. Some do not even realise that what is "on" your screen, matters. White screens (like browser) vs coding (in black) should be accounted for.
All you have to do is to change brightness when it is not good enough yet; brightml learns.
It will learn to generalize based on your personal needs. To do this, it uses:
- Brightness of screen
- Ambient light sensor (if available)
- Hour of day
- whereami (indoor wifi positioning)
- Battery feature (only if discharging)
- Active application name
- Active window title
Features
- Cross-OS (within Linux)
- Cross-vendor (intel, nvidia)
- Cross-hardware (with or without ambient light sensor, linux on macbook works)
- Seamless integration: No need to change key bindings as it monitors brightness change by user
- Uses asyncio, event-based (change of window immediately triggers prediction; no timer)
- Updates brightness on focusing different windows and on scrolling
Goals
- Provide service files to enable by startup (systemd: done)
- Add a command to show "feature importance"
- More extensibility (plugin based)
- Cross-platform (OSX)
Installation
pip install brightml
Bonus: set up whereami <https://github.com/kootenpv/whereami>
_ to include indoor positioning in the predictions.
pip install brightml[whereami]
Usage
Eventually we need to get some service files for the different Operating Systems, so the process starts on boot.
For now, just ready for preview, run on command line:
sudo brightml
This will run brightml in the foreground.
To instead just show current feature values, run:
pascal@archbook:~$ brightml features
{
"ambient_light": 1,
"whereami": "bed",
"datetime_hour": 21,
"datetime_timezone": "UTC+02:00",
"datetime_date": "2017-10-28",
"datetime_full": "2017-10-28 21:52:43+02:00",
"display_pixel_mean": 9.072666666666667,
"display_window_name": "pascal@archbook:~",
"display_window_class": "urxvt URxvt",
"battery": 95.94282414091828
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file brightml-0.2.11.tar.gz
.
File metadata
- Download URL: brightml-0.2.11.tar.gz
- Upload date:
- Size: 13.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.11.0 pkginfo/1.4.2 requests/2.18.4 setuptools/39.0.1 requests-toolbelt/0.8.0 tqdm/4.24.0 CPython/3.7.0a0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 57418bdfcdf88d46213a4305731b521049992ac9c06afa7c7300f2775d7a5b25 |
|
MD5 | 313545125f469740c0ee60500bf875f5 |
|
BLAKE2b-256 | 3700e7aef38d38da52e93b9181d64de6a5d47dfe550fd859eaa1be7ecdad9251 |
File details
Details for the file brightml-0.2.11-py2.py3-none-any.whl
.
File metadata
- Download URL: brightml-0.2.11-py2.py3-none-any.whl
- Upload date:
- Size: 17.4 kB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.11.0 pkginfo/1.4.2 requests/2.18.4 setuptools/39.0.1 requests-toolbelt/0.8.0 tqdm/4.24.0 CPython/3.7.0a0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d08655f3803eab1ccfcdf84fd5d3feef02b5a999c3eb40e428da574d05011c59 |
|
MD5 | 2fa9fdf8b95abfd8ede569f9948088a9 |
|
BLAKE2b-256 | e03655c8a9547eb0bda4b78645bcecdeddc61ae4fe24d9ef20f67f6ef5c2dcf8 |