This repository has been archived on 2024-06-23. You can view files and clone it, but cannot push or open issues or pull requests.
mathdeptv2/工具/批量添加题库字段数据.ipynb

303 lines
22 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.949\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.769\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.974\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.949\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.641\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.923\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.513\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.487\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.590\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.692\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.641\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.949\t0.333\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.821\t0.718\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三10班\t0.436\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.952\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.762\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.952\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.952\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.809\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.905\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.809\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.476\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.714\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.476\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.571\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.238\t0.191\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.857\t0.762\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三11班\t0.333\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.950\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.800\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t1.000\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.950\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.750\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.950\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.750\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.600\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.750\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.650\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.750\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t1.000\t0.500\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.850\t0.650\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三12班\t0.600\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.968\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.806\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t1.000\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.968\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t1.000\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t1.000\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.871\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.806\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.935\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.677\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.903\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.968\t0.806\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.968\t1.000\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三01班\t0.742\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.968\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.806\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.935\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.968\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.903\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.968\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.710\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.710\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.903\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.516\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.677\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.355\t0.516\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.903\t0.677\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三02班\t0.548\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t1.000\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.655\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.966\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.966\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.897\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t1.000\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.690\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.897\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.793\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.586\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.759\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.345\t0.655\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.897\t0.690\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三03班\t0.655\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.966\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.690\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.931\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t1.000\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.793\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.966\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.724\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.759\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.828\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.655\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.690\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.448\t0.517\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.828\t0.966\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三04班\t0.655\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.868\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.763\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.974\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.974\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.789\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.947\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.763\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.658\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.763\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.842\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.816\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.316\t0.316\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.868\t0.737\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三05班\t0.474\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.925\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.750\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.975\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t1.000\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.825\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.950\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.675\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.700\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.725\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.775\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.775\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.925\t0.675\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.925\t0.875\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三06班\t0.650\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.939\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.697\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.909\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.909\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.758\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.849\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.879\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.576\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.515\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.697\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.697\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.242\t0.364\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.879\t0.788\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三07班\t0.545\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.900\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.733\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t1.000\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t1.000\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.967\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.933\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.833\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.833\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.833\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.600\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.467\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.433\t0.600\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.933\t0.933\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三08班\t0.700\n",
"题号: 012834 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t1.000\n",
"题号: 012835 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.656\n",
"题号: 012836 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.938\n",
"题号: 012837 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.906\n",
"题号: 012857 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.719\n",
"题号: 012858 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.875\n",
"题号: 012859 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.844\n",
"题号: 012839 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.531\n",
"题号: 012841 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.688\n",
"题号: 012842 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.562\n",
"题号: 012843 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.562\n",
"题号: 014190 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.969\t0.531\n",
"题号: 014191 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.906\t0.688\n",
"题号: 012856 , 字段: usages 中已添加数据: 20230223\t2023届高三09班\t0.469\n"
]
}
],
"source": [
"import os,re,json\n",
"\n",
"\"\"\"---明确数据文件位置---\"\"\"\n",
"datafile = \"文本文件/metadata.txt\"\n",
"# 双回车分隔,记录内单回车分隔列表,首行为字段名\n",
"\"\"\"---文件位置结束---\"\"\"\n",
"\n",
"def trim(string):\n",
" string = re.sub(r\"^[ \\t\\n]*\",\"\",string)\n",
" string = re.sub(r\"[ \\t\\n]*$\",\"\",string)\n",
" return string\n",
"def FloatToInt(string):\n",
" f = float(string)\n",
" if abs(f-round(f))<0.01:\n",
" f = round(f)\n",
" return f\n",
"\n",
"with open(datafile,\"r\",encoding=\"utf8\") as f:\n",
" data = f.read().strip()\n",
"pos = data.index(\"\\n\")\n",
"field = data[:pos].strip()\n",
"appending_data = data[pos:]\n",
"\n",
"with open(r\"../题库0.3/Problems.json\",\"r\",encoding = \"utf8\") as f:\n",
" database = f.read()\n",
"pro_dict = json.loads(database)\n",
"with open(r\"../题库0.3/LessonObj.json\",\"r\",encoding = \"utf8\") as f:\n",
" database = f.read()\n",
"obj_dict = json.loads(database)\n",
"\n",
"#该字段列表可能需要更新\n",
"fields = [\"content\",\"objs\",\"tags\",\"genre\",\"ans\",\"solution\",\"duration\",\"usages\",\"origin\",\"edit\",\"same\",\"related\",\"remark\",\"space\"]\n",
"\n",
"if field in fields:\n",
" field_type = type(pro_dict[\"000001\"][field])\n",
" datalist = [record.strip() for record in appending_data.split(\"\\n\\n\") if len(trim(record)) > 0]\n",
" for record in datalist:\n",
" id = re.findall(r\"^[\\d]{1,}\",record)[0]\n",
" data = record[len(id):].strip()\n",
" id = id.zfill(6)\n",
" if not id in pro_dict:\n",
" print(\"题号:\",id,\"不在数据库中.\")\n",
" break\n",
" \n",
" #字符串类型字段添加数据\n",
" elif field_type == str and data in pro_dict[id][field]:\n",
" print(\"题号:\",id,\", 字段:\",field,\"中已有该数据:\",data)\n",
" elif field_type == str and not data in pro_dict[id][field] and not field == \"ans\" and not field == \"space\":\n",
" origin_data = pro_dict[id][field]\n",
" new_data = trim(origin_data + \"\\n\" + data)\n",
" pro_dict[id][field] = new_data\n",
" print(\"题号:\",id,\", 字段:\",field,\"中已添加数据:\",data)\n",
" elif field_type == str and not data in pro_dict[id][field] and field == \"ans\" or field == \"space\":\n",
" pro_dict[id][field] = data\n",
" print(\"题号:\",id,\", 字段:\",field,\"中已修改数据:\",data)\n",
" \n",
" #数值类型字段添加数据\n",
" elif (field_type == int or field_type == float) and abs(float(data) - pro_dict[id][field])<0.01:\n",
" print(\"题号:\",id,\", 字段:\",field,\"中已有该数据:\",FloatToInt(data))\n",
" elif (field_type == int or field_type == float) and abs(float(data) - pro_dict[id][field])>=0.01:\n",
" pro_dict[id][field] = FloatToInt(data)\n",
" print(\"题号:\",id,\", 字段:\",field,\"中已修改数据:\",FloatToInt(data))\n",
" \n",
" #列表类型字段添加数据\n",
" elif field_type == list:\n",
" cell_data_list = [d.strip() for d in data.split(\"\\n\")]\n",
" for cell_data in cell_data_list:\n",
" if cell_data in pro_dict[id][field]:\n",
" print(\"题号:\",id,\", 字段:\",field,\"中已有该数据:\",cell_data)\n",
" elif not field == \"objs\":\n",
" pro_dict[id][field].append(cell_data)\n",
" print(\"题号:\",id,\", 字段:\",field,\"中已添加数据:\",cell_data)\n",
" else:\n",
" if not cell_data in obj_dict and not cell_data.upper() == \"KNONE\":\n",
" print(\"题号:\",id,\", 字段:\",field,\"目标编号有误:\",cell_data)\n",
" else:\n",
" pro_dict[id][field].append(cell_data.upper())\n",
" print(\"题号:\",id,\", 字段:\",field,\"中已添加数据:\",cell_data.upper())\n",
"\n",
"with open(r\"../题库0.3/Problems.json\",\"w\",encoding = \"utf8\") as f:\n",
" f.write(json.dumps(pro_dict,indent=4,ensure_ascii=False))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "pythontest",
"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": "3.9.15"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "91219a98e0e9be72efb992f647fe78b593124968b75db0b865552d6787c8db93"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}