nlp_a2019_tp3/commentaires.ipynb

89 lines
1.8 KiB
Text
Raw Permalink Normal View History

2019-12-16 01:31:38 +00:00
{
"cells": [
{
"cell_type": "code",
2019-12-16 23:25:47 +00:00
"execution_count": null,
2019-12-16 01:31:38 +00:00
"metadata": {},
"outputs": [],
"source": [
"import parsing_functions as pf\n",
"import re\n",
"import pandas as pd\n",
"import time"
]
},
{
"cell_type": "code",
2019-12-16 23:25:47 +00:00
"execution_count": null,
2019-12-16 01:31:38 +00:00
"metadata": {},
"outputs": [],
"source": [
"listOfFiles = pf.getListOfFiles(\"data\")"
]
},
{
"cell_type": "code",
2019-12-16 23:25:47 +00:00
"execution_count": null,
2019-12-16 01:31:38 +00:00
"metadata": {},
"outputs": [],
"source": [
"commentaires = []\n",
"\n",
"for xlpath in listOfFiles:\n",
" comments_df = []\n",
" media, post_id = re.match(r\"data/([A-Z]+)/comments([0-9a-z\\-]+)\\.xlsx\",xlpath).groups()\n",
" comments_df = pf.get_comments(xlpath)\n",
" comments_df['media']=media\n",
" comments_df['post_id']=post_id\n",
" commentaires.append(comments_df)"
]
},
{
"cell_type": "code",
2019-12-16 23:25:47 +00:00
"execution_count": null,
2019-12-16 01:31:38 +00:00
"metadata": {},
"outputs": [],
"source": [
"commentaires_df = pd.concat(commentaires, ignore_index=True)"
]
},
{
"cell_type": "code",
2019-12-16 23:25:47 +00:00
"execution_count": null,
2019-12-16 01:31:38 +00:00
"metadata": {},
"outputs": [],
"source": [
"commentaires_df.to_csv(\"refined_data/commentaires_df.csv\")"
]
},
{
"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": "3.7.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}