wangweiye
/
mathdeptv2
Archived
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
This repository has been archived on 2024-06-23.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

247 lines
16 KiB
Plaintext
Raw Blame History

{
"cells": [
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"题号: 040001 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.962\n",
"题号: 040002 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t1.000\n",
"题号: 040003 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.962\n",
"题号: 040004 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t1.000\n",
"题号: 040005 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t1.000\n",
"题号: 040006 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.231\n",
"题号: 040007 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.885\n",
"题号: 040008 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.885\n",
"题号: 040009 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.923\n",
"题号: 040011 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.923\n",
"题号: 040012 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.000\n",
"题号: 040013 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.615\n",
"题号: 040014 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.385\n",
"题号: 040015 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.712\t0.808\n",
"题号: 040016 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.885\t0.308\n",
"题号: 040017 , 字段: usages 中已添加数据: 202302217\t2024届高二10班\t0.962\t0.769\t0.462\n",
"题号: 040001 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.944\n",
"题号: 040002 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.972\n",
"题号: 040003 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t1.000\n",
"题号: 040004 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.722\n",
"题号: 040005 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.889\n",
"题号: 040006 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.528\n",
"题号: 040007 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.694\n",
"题号: 040008 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t1.000\n",
"题号: 040009 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t1.000\n",
"题号: 040011 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.889\n",
"题号: 040012 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.111\n",
"题号: 040013 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.833\n",
"题号: 040014 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.583\n",
"题号: 040015 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t1.000\t0.833\n",
"题号: 040016 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.958\t0.889\n",
"题号: 040017 , 字段: usages 中已添加数据: 202302217\t2024届高二01班\t0.944\t0.889\t0.708\n",
"题号: 040001 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.655\n",
"题号: 040002 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.828\n",
"题号: 040003 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.655\n",
"题号: 040004 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.483\n",
"题号: 040005 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.966\n",
"题号: 040006 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.310\n",
"题号: 040007 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.828\n",
"题号: 040008 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.966\n",
"题号: 040009 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.897\n",
"题号: 040011 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.793\n",
"题号: 040012 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.000\n",
"题号: 040013 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.690\n",
"题号: 040014 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.345\n",
"题号: 040015 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.983\t0.741\n",
"题号: 040016 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t0.931\t0.293\n",
"题号: 040017 , 字段: usages 中已添加数据: 202302217\t2024届高二12班\t1.000\t0.483\t0.534\n",
"题号: 040001 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.974\n",
"题号: 040002 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t1.000\n",
"题号: 040003 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.974\n",
"题号: 040004 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.795\n",
"题号: 040005 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.872\n",
"题号: 040006 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.615\n",
"题号: 040007 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.769\n",
"题号: 040008 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t1.000\n",
"题号: 040009 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.974\n",
"题号: 040011 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.821\n",
"题号: 040012 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.154\n",
"题号: 040013 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.974\n",
"题号: 040014 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.718\n",
"题号: 040015 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.872\t0.718\n",
"题号: 040016 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.949\t0.590\n",
"题号: 040017 , 字段: usages 中已添加数据: 202302217\t2024届高二02班\t0.923\t0.782\t0.590\n",
"题号: 040001 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.950\n",
"题号: 040002 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.975\n",
"题号: 040003 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.950\n",
"题号: 040004 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.950\n",
"题号: 040005 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.875\n",
"题号: 040006 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.250\n",
"题号: 040007 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.925\n",
"题号: 040008 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t1.000\n",
"题号: 040009 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.950\n",
"题号: 040011 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.950\n",
"题号: 040012 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.050\n",
"题号: 040013 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.675\n",
"题号: 040014 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.500\n",
"题号: 040015 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.725\t0.938\n",
"题号: 040016 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.975\t0.388\n",
"题号: 040017 , 字段: usages 中已添加数据: 202302217\t2024届高二06班\t0.925\t0.825\t0.588\n",
"题号: 040001 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.975\n",
"题号: 040002 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.925\n",
"题号: 040003 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.925\n",
"题号: 040004 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.075\n",
"题号: 040005 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.750\n",
"题号: 040006 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.425\n",
"题号: 040007 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.775\n",
"题号: 040008 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.950\n",
"题号: 040009 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.775\n",
"题号: 040011 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.575\n",
"题号: 040012 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.075\n",
"题号: 040013 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.625\n",
"题号: 040014 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.425\n",
"题号: 040015 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.662\t0.787\n",
"题号: 040016 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.762\t0.438\n",
"题号: 040017 , 字段: usages 中已添加数据: 202302217\t2024届高二07班\t0.762\t0.537\t0.388\n",
"题号: 040001 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.652\n",
"题号: 040002 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t1.000\n",
"题号: 040003 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.609\n",
"题号: 040004 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.304\n",
"题号: 040005 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.870\n",
"题号: 040006 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.391\n",
"题号: 040007 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.783\n",
"题号: 040008 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.957\n",
"题号: 040009 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.957\n",
"题号: 040011 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.913\n",
"题号: 040012 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.087\n",
"题号: 040013 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.696\n",
"题号: 040014 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.522\n",
"题号: 040015 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.848\t0.652\n",
"题号: 040016 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.891\t0.348\n",
"题号: 040017 , 字段: usages 中已添加数据: 202302217\t2024届高二08班\t0.957\t0.391\t0.435\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": "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": "3.9.15"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "ff3c292c316ba85de6f1ad75f19c731e79d694e741b6f515ec18f14996fe48dc"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue View Git Blame Copy Permalink