185 lines
5.8 KiB
Plaintext
185 lines
5.8 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"0.789\t1\t005886\n",
|
|
"0.805\t2\t006207\n",
|
|
"0.812\t3\t006137\n",
|
|
"0.798\t4\t012269\n",
|
|
"0.817\t5\t010989\n",
|
|
"0.888\t6\t021503\n",
|
|
"0.815\t7\t021484\n",
|
|
"0.959\t8\t003206\n",
|
|
"0.839\t9\t011090\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import os,re,difflib,Levenshtein,time,json\n",
|
|
"\n",
|
|
"# 重要!!! 范围\n",
|
|
"old_problems_range = \"1:30000\"\n",
|
|
"threshold = 0.85\n",
|
|
"\n",
|
|
"# 待比对的文件\n",
|
|
"filename = r\"C:\\Users\\weiye\\Documents\\wwy sync\\临时工作区\\自拟题目9.tex\"\n",
|
|
"\n",
|
|
"#生成数码列表, 逗号分隔每个区块, 区块内部用:表示整数闭区间\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",
|
|
"#字符串预处理\n",
|
|
"def pre_treating(string):\n",
|
|
" string = re.sub(r\"\\\\begin\\{center\\}[\\s\\S]*?\\\\end\\{center\\}\",\"\",string)\n",
|
|
" string = re.sub(r\"(bracket\\{\\d+\\})|(blank\\{\\d+\\})|(fourch)|(twoch)|(onech)|(mathrm)|(text)\",\"\",string)\n",
|
|
" string = re.sub(r\"[\\s\\\\\\{\\}\\$\\(\\)\\[\\]]\",\"\",string)\n",
|
|
" string = re.sub(r\"[\\n\\t]\",\"\",string)\n",
|
|
" string = re.sub(r\"(displaystyle)|(overrightarrow)\",\"\",string)\n",
|
|
" string = re.sub(r\"[,\\.:;?]\",\"\",string)\n",
|
|
" return string\n",
|
|
"\n",
|
|
"#difflab字符串比较\n",
|
|
"def difflab_get_equal_rate(str1, str2):\n",
|
|
" return difflib.SequenceMatcher(None, str1, str2).ratio()\n",
|
|
"\n",
|
|
"#Levenshtein jaro字符串比较\n",
|
|
"def jaro_get_equal_rate(str1,str2):\n",
|
|
" return Levenshtein.jaro(str1,str2)\n",
|
|
"\n",
|
|
"#Levenshtein 字符串比较\n",
|
|
"def Lev_get_equal_rate(str1,str2):\n",
|
|
" return Levenshtein.ratio(str1,str2)\n",
|
|
"\n",
|
|
"def GenerateProblemListFromString(problem_string):\n",
|
|
" try:\n",
|
|
" data = re.findall(r\"\\\\begin\\{document\\}([\\s\\S]*?)\\\\end\\{document\\}\",problem_string)[0]\n",
|
|
" except:\n",
|
|
" data = problem_string\n",
|
|
" data = re.sub(r\"\\n{2,}\",\"\\n\",data)\n",
|
|
" data = re.sub(r\"\\\\item\",r\"\\\\enditem\\\\item\",data)\n",
|
|
" data = re.sub(r\"\\\\end\\{enumerate\\}\",r\"\\\\enditem\",data)\n",
|
|
" ProblemList_raw = [p.strip() for p in re.findall(r\"\\\\item([\\s\\S]*?)\\\\enditem\",data)]\n",
|
|
" ProblemsList = []\n",
|
|
" for p in ProblemList_raw:\n",
|
|
" startpos = data.index(p)\n",
|
|
" tempdata = data[:startpos]\n",
|
|
" suflist = re.findall(r\"\\n\\%[\\dA-Za-z]+\",tempdata)\n",
|
|
" if len(suflist) > 0:\n",
|
|
" suffix = suflist[-1].replace(\"%\",\"\").strip()\n",
|
|
" else:\n",
|
|
" suffix = \"\"\n",
|
|
" ProblemsList.append((p,suffix))\n",
|
|
" return ProblemsList\n",
|
|
"\n",
|
|
"\n",
|
|
"#指定对比方法\n",
|
|
"sim_test = jaro_get_equal_rate\n",
|
|
"\n",
|
|
"#读入题库\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",
|
|
"\n",
|
|
"with open(filename,\"r\",encoding=\"u8\") as f:\n",
|
|
" newdatabase = f.read()\n",
|
|
"new_pro_list = GenerateProblemListFromString(newdatabase)\n",
|
|
"\n",
|
|
"pro_dict_treated = {}\n",
|
|
"idrange_raw = generate_number_set(old_problems_range)\n",
|
|
"idrange = [id for id in pro_dict if id in idrange_raw]\n",
|
|
"for p in idrange:\n",
|
|
" pro_dict_treated[p] = pre_treating(pro_dict[p][\"content\"])\n",
|
|
"\n",
|
|
"new_dict_treated = {}\n",
|
|
"for i in range(len(new_pro_list)):\n",
|
|
" new_dict_treated[i+1] = pre_treating(new_pro_list[i][0])\n",
|
|
"\n",
|
|
"for i in new_dict_treated:\n",
|
|
" new_p = new_dict_treated[i]\n",
|
|
" maxsim = 0\n",
|
|
" for p in pro_dict_treated:\n",
|
|
" old_p = pro_dict_treated[p]\n",
|
|
" sim = sim_test(new_p,old_p)\n",
|
|
" if sim > maxsim:\n",
|
|
" maxsim = sim\n",
|
|
" argmax = p\n",
|
|
" print(\"%.3f\\t%d\\t%s\" %(maxsim,i,argmax))\n",
|
|
" # print(\"\\n新题: %s\" %new_pro_list[i-1][0])\n",
|
|
" # print(\"\\n原题: %s\\n\\n\\n\" %pro_dict[][\"content\"])\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"999999"
|
|
]
|
|
},
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"len(idrange)"
|
|
]
|
|
},
|
|
{
|
|
"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": "ff3c292c316ba85de6f1ad75f19c731e79d694e741b6f515ec18f14996fe48dc"
|
|
}
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|