nlp-lab/Project/Tools/EmojiCounting.ipynb

172 lines
3.3 KiB
Plaintext
Raw Normal View History

2018-07-19 17:49:00 +02:00
{
"cells": [
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
"outputs": [],
"source": [
2018-07-19 17:53:16 +02:00
"%matplotlib ipympl"
2018-07-19 17:49:00 +02:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Count emoji occurences"
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
2018-07-19 17:53:16 +02:00
"outputs": [],
2018-07-19 17:49:00 +02:00
"source": [
"import numpy as np\n",
"import json\n",
"import glob\n",
"import matplotlib\n",
"import matplotlib.pyplot as plt\n",
2018-07-20 11:30:28 +02:00
"from __future__ import unicode_literals\n"
2018-07-19 17:49:00 +02:00
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
"outputs": [],
"source": [
2018-07-20 11:30:28 +02:00
"json_root = \"./emoji_counts/\""
2018-07-19 17:49:00 +02:00
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
"outputs": [],
"source": [
"json_files = sorted(glob.glob(json_root + \"/*.json\"))"
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
2018-07-20 11:30:28 +02:00
"outputs": [],
2018-07-19 17:49:00 +02:00
"source": [
"json_files"
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
"outputs": [],
"source": [
"json_lists = []"
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
"outputs": [],
"source": [
"for path in json_files:\n",
" with open(path) as f:\n",
" data = json.load(f)\n",
" json_lists.append(data)"
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
"outputs": [],
"source": [
"merged_dict = {}\n"
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
"outputs": [],
"source": [
"for j in json_lists:\n",
" for emoji in j.keys():\n",
" if emoji in merged_dict:\n",
" merged_dict[emoji] = merged_dict[emoji] + j[emoji]\n",
" else:\n",
" merged_dict[emoji] = j[emoji]"
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
"outputs": [],
"source": [
2018-07-20 11:30:28 +02:00
"n_top = 50"
2018-07-19 17:49:00 +02:00
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
"outputs": [],
"source": [
"keysort = np.argsort(list(merged_dict.values()))[-n_top:]"
]
},
{
"cell_type": "code",
2018-07-20 11:30:28 +02:00
"execution_count": null,
2018-07-19 17:49:00 +02:00
"metadata": {},
2018-07-20 11:30:28 +02:00
"outputs": [],
2018-07-19 17:49:00 +02:00
"source": [
2018-07-20 11:30:28 +02:00
"matplotlib.rc('font', family='EmojiOne Color')\n",
"plt.figure(figsize=(10,5))\n",
2018-07-19 17:49:00 +02:00
"plt.bar(np.array(list(merged_dict.keys()))[keysort], np.array(list(merged_dict.values()))[keysort], color='g')\n",
"plt.savefig(\"histogram.png\", bbox_inches='tight')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}