{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from itertools import islice\n",
"from pathlib import Path\n",
"from sys import argv\n",
"from textdistance import EntropyNCD\n",
"\n",
"# read files\n",
"licenses = dict()\n",
"for path in Path('choosealicense.com', '_licenses').iterdir():\n",
" licenses[path.stem] = path.read_text()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"distances = []\n",
"for name1, content1 in licenses.items():\n",
" for name2, content2 in licenses.items():\n",
" distances.append((name1, name2, EntropyNCD(qval=None)(content1, content2)))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import plotnine as gg\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(distances, columns=['name1', 'name2', 'distance'])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"(\n",
" gg.ggplot(df)\n",
" + gg.geom_tile(gg.aes(x='name1', y='name2', fill='distance'))\n",
" + gg.scale_fill_continuous(palette=lambda *args: gg.scale_fill_continuous().palette(*args)[::-1])\n",
" + gg.theme(\n",
" figure_size=(12, 8), \n",
" axis_text_x=gg.element_text(angle=90),\n",
" )\n",
")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Generated by dwww version 1.15 on Wed Jun 26 06:28:11 CEST 2024.