{ "cells": [ { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "ename": "KeyboardInterrupt", "evalue": "Interrupted by user", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", "Cell \u001b[1;32mIn[2], line 31\u001b[0m\n\u001b[0;32m 29\u001b[0m problems_indexes \u001b[39m=\u001b[39m \u001b[39mlist\u001b[39m(df[df\u001b[39m.\u001b[39mcolumns[\u001b[39m0\u001b[39m]][\u001b[39m2\u001b[39m:])\n\u001b[0;32m 30\u001b[0m \u001b[39mfor\u001b[39;00m p \u001b[39min\u001b[39;00m problems_indexes:\n\u001b[1;32m---> 31\u001b[0m t \u001b[39m=\u001b[39m \u001b[39minput\u001b[39;49m(\u001b[39m\"\u001b[39;49m\u001b[39m答题纸区域\u001b[39;49m\u001b[39m\"\u001b[39;49m\u001b[39m+\u001b[39;49mp\u001b[39m+\u001b[39;49m\u001b[39m\"\u001b[39;49m\u001b[39m的题号为(1-\u001b[39;49m\u001b[39m\"\u001b[39;49m\u001b[39m+\u001b[39;49m\u001b[39mstr\u001b[39;49m(\u001b[39mlen\u001b[39;49m(problems_list))\u001b[39m+\u001b[39;49m\u001b[39m\"\u001b[39;49m\u001b[39m, a为自动对应点前的题号):\u001b[39;49m\u001b[39m\"\u001b[39;49m)\n\u001b[0;32m 32\u001b[0m \u001b[39mif\u001b[39;00m t\u001b[39m.\u001b[39mupper() \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mA\u001b[39m\u001b[39m\"\u001b[39m:\n\u001b[0;32m 33\u001b[0m correspondence_dict[p] \u001b[39m=\u001b[39m problems_list[\u001b[39mint\u001b[39m(re\u001b[39m.\u001b[39mfindall(\u001b[39mr\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m([\u001b[39m\u001b[39m\\\u001b[39m\u001b[39md]+?)\u001b[39m\u001b[39m\\\u001b[39m\u001b[39m.\u001b[39m\u001b[39m\"\u001b[39m,p)[\u001b[39m0\u001b[39m])\u001b[39m-\u001b[39m\u001b[39m1\u001b[39m]\n", "File \u001b[1;32mc:\\Users\\weiye\\.conda\\envs\\mathdept\\lib\\site-packages\\ipykernel\\kernelbase.py:1175\u001b[0m, in \u001b[0;36mKernel.raw_input\u001b[1;34m(self, prompt)\u001b[0m\n\u001b[0;32m 1171\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_allow_stdin:\n\u001b[0;32m 1172\u001b[0m \u001b[39mraise\u001b[39;00m StdinNotImplementedError(\n\u001b[0;32m 1173\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mraw_input was called, but this frontend does not support input requests.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m 1174\u001b[0m )\n\u001b[1;32m-> 1175\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_input_request(\n\u001b[0;32m 1176\u001b[0m \u001b[39mstr\u001b[39;49m(prompt),\n\u001b[0;32m 1177\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_parent_ident[\u001b[39m\"\u001b[39;49m\u001b[39mshell\u001b[39;49m\u001b[39m\"\u001b[39;49m],\n\u001b[0;32m 1178\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mget_parent(\u001b[39m\"\u001b[39;49m\u001b[39mshell\u001b[39;49m\u001b[39m\"\u001b[39;49m),\n\u001b[0;32m 1179\u001b[0m password\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m,\n\u001b[0;32m 1180\u001b[0m )\n", "File \u001b[1;32mc:\\Users\\weiye\\.conda\\envs\\mathdept\\lib\\site-packages\\ipykernel\\kernelbase.py:1217\u001b[0m, in \u001b[0;36mKernel._input_request\u001b[1;34m(self, prompt, ident, parent, password)\u001b[0m\n\u001b[0;32m 1214\u001b[0m \u001b[39mbreak\u001b[39;00m\n\u001b[0;32m 1215\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mKeyboardInterrupt\u001b[39;00m:\n\u001b[0;32m 1216\u001b[0m \u001b[39m# re-raise KeyboardInterrupt, to truncate traceback\u001b[39;00m\n\u001b[1;32m-> 1217\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mKeyboardInterrupt\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mInterrupted by user\u001b[39m\u001b[39m\"\u001b[39m) \u001b[39mfrom\u001b[39;00m \u001b[39mNone\u001b[39m\n\u001b[0;32m 1218\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mException\u001b[39;00m:\n\u001b[0;32m 1219\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mlog\u001b[39m.\u001b[39mwarning(\u001b[39m\"\u001b[39m\u001b[39mInvalid Message:\u001b[39m\u001b[39m\"\u001b[39m, exc_info\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\n", "\u001b[1;31mKeyboardInterrupt\u001b[0m: Interrupted by user" ] } ], "source": [ "import zipfile,os,re,time\n", "import pandas as pd\n", "from pathlib import Path\n", "\n", "#设置工作目录, 要求工作目录中恰有一个.tex文件和一个.zip文件，其余不论\n", "filepath = \"数据导入作业文件\"\n", "\n", "#生成文件名tex_file和zip_file\n", "files = [os.path.join(filepath,f) for f in os.listdir(filepath)]\n", "tex_file = [f for f in files if \".tex\" in f or \".txt\" in f][0]\n", "zip_file = [f for f in files if \".zip\" in f][0]\n", "\n", "#获得题号数据，保存在problems_list中\n", "with open(tex_file,\"r\",encoding = \"utf8\") as f:\n", " tex_data = f.read()\n", "problems_list = re.findall(r\"\\(([\\d]{6})\\)\",tex_data)\n", "\n", "#在zip文件中找到包含正确率数据的文件\n", "zf = zipfile.ZipFile(zip_file)\n", "statfiles = [f.filename for f in zf.filelist if \"试题分析\" in f.filename]\n", "\n", "#生成答题纸区域编号与题目ID的对应\n", "correspondence_dict = {}\n", "if \"statsfile.xlsx\" in os.listdir(\"临时文件\"):\n", " os.remove(\"临时文件/statsfile.xlsx\")\n", "extractedpath = Path(zf.extract(statfiles[0]))\n", "extractedpath.rename(\"临时文件/statsfile.xlsx\")\n", "df = pd.read_excel(\"临时文件/statsfile.xlsx\")\n", "problems_indexes = list(df[df.columns[0]][2:])\n", "for p in problems_indexes:\n", " t = input(\"答题纸区域\"+p+\"的题号为(1-\"+str(len(problems_list))+\", a为自动对应点前的题号):\")\n", " if t.upper() == \"A\":\n", " correspondence_dict[p] = problems_list[int(re.findall(r\"([\\d]+?)\\.\",p)[0])-1]\n", " elif not (int(t)<1 or int(t)>len(problems_list)):\n", " correspondence_dict[p] = problems_list[int(t)-1] \n", "\n", "outputstr = \"usages\\n\\n\"\n", "\n", "for sf in statfiles:\n", " #读取文件生成区域列表与难度列表\n", " classname = \"2023届高三\"+re.findall(r\"高三([\\d]*?)班\",sf)[0].zfill(2)+\"班\"\n", " date = str(time.localtime().tm_year)+str(time.localtime().tm_mon).zfill(2)+str(time.localtime().tm_mday).zfill(2)\n", " if \"statsfile.xlsx\" in os.listdir(\"临时文件\"):\n", " os.remove(\"临时文件/statsfile.xlsx\")\n", " extractedpath = Path(zf.extract(sf))\n", " extractedpath.rename(\"临时文件/statsfile.xlsx\")\n", " df = pd.read_excel(\"临时文件/statsfile.xlsx\")\n", " difficulties = list(df[df.columns[9]][2:])\n", " problems_indexes = list(df[df.columns[0]][2:])\n", " #生成该班级题目ID对应难度列表组成的字典\n", " class_difficulty = {}\n", " for i in range(len(difficulties)):\n", " if problems_indexes[i] in correspondence_dict:\n", " if not correspondence_dict[problems_indexes[i]] in class_difficulty:\n", " class_difficulty[correspondence_dict[problems_indexes[i]]] = [difficulties[i]]\n", " else:\n", " class_difficulty[correspondence_dict[problems_indexes[i]]].append(difficulties[i])\n", " #添加到输出字符串中\n", " for id in class_difficulty:\n", " outputstr += id + \"\\n\" + date + \"\\t\" + classname + \"\\t\" + \"\\t\".join([(\"%.3f\" %float(v)) for v in class_difficulty[id]]) + \"\\n\\n\"\n", "\n", "with open(\"临时文件/自动转换结果.txt\",\"w\",encoding = \"utf8\") as f:\n", " f.write(outputstr)\n", "with open(\"../文本文件/metadata.txt\",\"w\",encoding = \"utf8\") as f:\n", " f.write(outputstr)\n", "zf.close()\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "mathdept", "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": "3.8.15" }, "orig_nbformat": 4, "vscode": { "interpreter": { "hash": "42dd566da87765ddbe9b5c5b483063747fec4aacc5469ad554706e4b742e67b2" } } }, "nbformat": 4, "nbformat_minor": 2 }