python package to explore the color of language
comp-syn is a python package which provides a novel methodology to explore relationships between abstract concepts and color. We provide functionalities to create a dataset for word - image associations through Google Cloud and WordNet, as and demonstrate a variety of image and word related analyses. We introduce constructs such as Colorgrams as a tool for analysis, as well as the ability to create color representational vectors for images, and words as aggregations of images. Our work demonstrates a strong relationship between abstract semantic domains and colors, and supports claims for collective cognition and embodied cognition. The package allows you to explore these relationships yourself!
The theoretical frameword is described in:
Douglas Guilbeault , Ethan Nadler, Mark Chu, Ruggiero Lo Sardo, Aabir Abubaker Kar, and Bhargav Srinivasa Desikan. “Color Associations in Abstract Semantic Domains.” Forthcoming in Cognition (2020).
The work arose through a collaboration between the contributors at the Santa Fe Institute’s Complex System Summer School 2019.
Documentation and Examples
The notebooks directory showcases the usage of compsyn, with examples and basic usage.
We currently provide functionality to download and organise image data to be loaded as vector objects, as well as a preliminary analysis using them.
Run pip install compsyn to download and install from PyPI.
Run python setup.py install for default installation.
Run pip install . to install from source.
- Python 2.7+, 3.4+
- numpy, scipy, scikit-learn, matplotlib, PIL
To use the package one would need to download the JzAzBz array to convert the images to the appropriate vector form. It can be downloaded here (link). We provide sample images downloaded from Google Images to test the functionality.
Release history Release notifications | RSS feed
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size compsyn-0.1.3-py3-none-any.whl (14.5 kB)||File type Wheel||Python version py3||Upload date||Hashes View|
|Filename, size compsyn-0.1.3.tar.gz (13.4 kB)||File type Source||Python version None||Upload date||Hashes View|