{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os,re,json\n",
    "import pandas as pd\n",
    "#此处输入题号列表\n",
    "problems = r\"\"\"\n",
    "4080,4122,4312,4451,4557,4276,30019,4356,4320,4359,30020,4091,4400,8101,4157,4440,4370,4224,4328,4444,4247\n",
    "\n",
    "\n",
    "\"\"\"\n",
    "outputfile = r\"临时文件/使用记录结果对比.xlsx\"\n",
    "\n",
    "def generate_number_set(string):\n",
    "    string = re.sub(r\"[\\n\\s]\",\"\",string)\n",
    "    string_list = string.split(\",\")\n",
    "    numbers_list = []\n",
    "    for s in string_list:\n",
    "        if not \":\" in s:\n",
    "            numbers_list.append(s.zfill(6))\n",
    "        else:\n",
    "            start,end = s.split(\":\")\n",
    "            for ind in range(int(start),int(end)+1):\n",
    "                numbers_list.append(str(ind).zfill(6))\n",
    "    return numbers_list\n",
    "\n",
    "problem_list = generate_number_set(problems)\n",
    "with open(r\"d:/mathdeptv2/题库0.3/problems.json\",\"r\",encoding = \"utf8\") as f:\n",
    "    jsondata = f.read()\n",
    "pro_dict = json.loads(jsondata)\n",
    "class_list = []\n",
    "\n",
    "df = pd.DataFrame()\n",
    "\n",
    "for id in problem_list:\n",
    "    # print(pro_dict[id][\"content\"])\n",
    "    # print(pro_dict[id][\"usages\"])\n",
    "    for usage in pro_dict[id][\"usages\"]:\n",
    "        classname = re.findall(\"([\\S]*届[\\S]*)\",usage)[0]\n",
    "        if not classname in class_list:\n",
    "            class_list.append(classname)\n",
    "class_list.sort()\n",
    "df[\"班级\"] = class_list\n",
    "\n",
    "for id in problem_list:\n",
    "    parts = 1\n",
    "    for usage in pro_dict[id][\"usages\"]:\n",
    "        parts = max(parts,len(re.findall(r\"\\d\\.[\\d]{3}\",usage)))\n",
    "    # print(id,parts)\n",
    "    if parts == 1:\n",
    "        df[id] = [\"N/A\"]*len(class_list)\n",
    "        for c in range(len(class_list)):\n",
    "            for usage in pro_dict[id][\"usages\"]:\n",
    "                if class_list[c] in usage:\n",
    "                    df[id][c] = float(re.findall(r\"\\d\\.[\\d]{3}\",usage)[0])\n",
    "    else:\n",
    "        for j in range(parts):\n",
    "            df[id+\"_\"+str(j+1)] = [\"N/A\"]*len(class_list)\n",
    "        for c in range(len(class_list)):\n",
    "            for usage in pro_dict[id][\"usages\"]:\n",
    "                if class_list[c] in usage:\n",
    "                    results = re.findall(r\"\\d\\.[\\d]{3}\",usage)\n",
    "                    for t in range(len(results)):\n",
    "                        df[id+\"_\"+str(t+1)][c] = float(results[t])\n",
    "\n",
    "df.to_excel(outputfile,index = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.231"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "float(\"0.231\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.9.7 ('base')",
   "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": "3.9.7"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "e4cce46d6be9934fbd27f9ca0432556941ea5bdf741d4f4d64c6cd7f8dfa8fba"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}