Files
tunmnlu/task_2/others-answer/omsa-main/ISYE-6740-OAN/homework3/Untitled.ipynb
louiscklaw 9035c1312b update,
2025-02-01 02:09:32 +08:00

83 lines
2.1 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 119,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import json\n",
"from pandas.io.json import json_normalize\n",
"\n",
"with open('./data/freeformatter-out.json',encoding='utf-8') as json_file:\n",
" data = json.load(json_file)"
]
},
{
"cell_type": "code",
"execution_count": 104,
"metadata": {},
"outputs": [],
"source": [
"def flatten_json(nested_json, exclude=['']):\n",
" \"\"\"Flatten json object with nested keys into a single level.\n",
" Args:\n",
" nested_json: A nested json object.\n",
" exclude: Keys to exclude from output.\n",
" Returns:\n",
" The flattened json object if successful, None otherwise.\n",
" \"\"\"\n",
" out = {}\n",
"\n",
" def flatten(x, name='', exclude=exclude):\n",
" if type(x) is dict:\n",
" for a in x:\n",
" if a not in exclude: flatten(x[a], name + a + '_')\n",
" elif type(x) is list:\n",
" i = 0\n",
" for a in x:\n",
" flatten(a, name + str(i) + '_')\n",
" i += 1\n",
" else:\n",
" out[name[:-1]] = x\n",
"\n",
" flatten(nested_json)\n",
" return out\n"
]
},
{
"cell_type": "code",
"execution_count": 118,
"metadata": {},
"outputs": [],
"source": [
"#flat_json = flatten_json(data,['postmeta'])\n",
"flat_json = pd.DataFrame([flatten_json(x) for x in data['channel']['item']])\n",
"flat_json.to_csv('./freeform.csv')"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "'Python Interactive'",
"language": "python",
"name": "17501b92-bb2a-435d-aa93-fcc8fde404f5"
},
"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": 4
}