BP2024/preprocessing/id_addition.ipynb
2024-04-09 15:39:11 +02:00

104 lines
2.5 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"import os"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def open_json(filename):\n",
" with open(filename, 'r') as json_file:\n",
" return json.load(json_file)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"def add_ids(json_file):\n",
" id_counter = 1\n",
" for post in json_file:\n",
" post[\"id\"] = id_counter\n",
" id_counter += 1\n",
" if 'comments' in post:\n",
" for comment in post['comments']:\n",
" comment[\"id\"] = id_counter\n",
" id_counter += 1\n",
" if 'replies' in comment:\n",
" for reply in comment['replies']:\n",
" reply[\"id\"] = id_counter\n",
" id_counter += 1\n",
" if 'replies' in reply:\n",
" for sec_reply in reply['replies']:\n",
" sec_reply[\"id\"] = id_counter\n",
" id_counter += 1\n",
" return json_file"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"def create_json(filename, data):\n",
" with open(filename, 'w', encoding = \"utf-8\", ) as file:\n",
" json.dump(data, file, indent=4, separators=(',',': '))"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"for json_file in os.listdir(\"json_data\"):\n",
" data = open_json(f'json_data/{json_file}')\n",
" data = add_ids(data)\n",
" create_json(f'json_data_id/{json_file}', data)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "sentiment",
"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": "3.9.16"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}