20230811

高考数据导入.ipynb

@@ -1299,26 +1299,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": null,
    "metadata": {
-    "execution": {
-     "iopub.execute_input": "2022-08-04T03:53:00.735786Z",
-     "iopub.status.busy": "2022-08-04T03:53:00.735257Z",
-     "iopub.status.idle": "2022-08-04T03:53:10.194351Z",
-     "shell.execute_reply": "2022-08-04T03:53:10.192776Z",
-     "shell.execute_reply.started": "2022-08-04T03:53:00.735737Z"
-    },
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ok\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import pymysql\n",
     "import pymongo\n",
@@ -1376,6 +1361,191 @@
     "print('ok')"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 导入2023年录取数据"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 导入2023年一分一段表"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import openpyxl\n",
+    "import json\n",
+    "\n",
+    "\n",
+    "wb = openpyxl.load_workbook('./data/2023年一分一段表.xlsx')\n",
+    "sheet = wb.active\n",
+    "i = 1\n",
+    "dict1 = {}\n",
+    "for n in range(4,sheet.max_row):\n",
+    "        m_score = sheet.cell(n,1).value\n",
+    "        m_num = sheet.cell(n,2).value\n",
+    "        m_sum = sheet.cell(n,3).value\n",
+    "        m_max = m_sum - m_num + 1\n",
+    "        dict1[m_score] = {'num_person':m_num,'max_rank':m_max,'min_rank':m_sum}\n",
+    "filename = 'data/2023年一分一段表.json'\n",
+    "with open(filename,'w') as fl:\n",
+    "    json.dump(dict1,fl) \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-07-26T13:07:34.650896Z",
+     "iopub.status.busy": "2023-07-26T13:07:34.650369Z",
+     "iopub.status.idle": "2023-07-26T13:07:34.656873Z",
+     "shell.execute_reply": "2023-07-26T13:07:34.655204Z",
+     "shell.execute_reply.started": "2023-07-26T13:07:34.650847Z"
+    }
+   },
+   "source": [
+    "### 导出2023年录取数据并生成分数"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import openpyxl\n",
+    "import json\n",
+    "\n",
+    "filename = 'data/2023年一分一段表.json'\n",
+    "with open(filename,'r') as fl:\n",
+    "    m_xx = json.load(fl)\n",
+    "\n",
+    "for k, v in m_xx.items():\n",
+    "    list1 = []\n",
+    "    list1 = (v['min_rank'],v['max_rank'])\n",
+    "    yfyd[int(k)] = list1\n",
+    "dict1 = {}\n",
+    "filename = 'data/山东省2023年普通类常规批第1次志愿投档情况表.xlsx'\n",
+    "wb = openpyxl.load_workbook(filename)\n",
+    "sheet = wb.active\n",
+    "data1 =list(sheet.values)\n",
+    "del data1[0:2]\n",
+    "m_num = 1\n",
+    "i = 1\n",
+    "for items in data1:\n",
+    "    m_rank = items[3]    \n",
+    "    list1 = []\n",
+    "    print(items[0])\n",
+    "    for k, v in yfyd.items():\n",
+    "        if m_rank >=v[1] and m_rank <=v[0]:\n",
+    "            m_num = int(k)\n",
+    "            break\n",
+    "    list1 = (items[0],items[1],items[2],items[3],m_num)\n",
+    "    dict1[i] = list1\n",
+    "    i += 1 \n",
+    "with open('data/2023.json','w') as fl2:\n",
+    "    json.dump(dict1,fl2) \n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 2023年专业录取分数及位次"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-07-26T14:40:10.969625Z",
+     "iopub.status.busy": "2023-07-26T14:40:10.969096Z",
+     "iopub.status.idle": "2023-07-26T14:40:29.882965Z",
+     "shell.execute_reply": "2023-07-26T14:40:29.881763Z",
+     "shell.execute_reply.started": "2023-07-26T14:40:10.969577Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ok\n",
+      "ok\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "import pymongo\n",
+    "import decimal\n",
+    "\n",
+    "myclient = pymongo.MongoClient('mongodb://localhost:27017/')\n",
+    "mydb = myclient[\"gaokao\"]\n",
+    "mycol1 = mydb[\"admission_ls\"]\n",
+    "mycol = mydb[\"admission_2023\"]\n",
+    "\n",
+    "m_col = {}\n",
+    "m_spe = {}\n",
+    "m_xx = {}\n",
+    "filename = 'data/2023.json'\n",
+    "with open(filename,'r') as fl:\n",
+    "    dict1 = json.load(fl)\n",
+    "\n",
+    "for k, v in dict1.items():\n",
+    "    m_xx = {}\n",
+    "    m_xx['col_code'] = v[1][:4]\n",
+    "    m_xx['col_name'] = v[1][4:]\n",
+    "    m_xx['spe_code'] = v[0][:2]\n",
+    "    m_xx['spe_name'] = v[0][2:]\n",
+    "    m_xx['plan'] = v[2]\n",
+    "    m_xx['num_min'] = v[4] \n",
+    "    m_xx['rank_min'] = v[3]\n",
+    "    m_xx['nian'] = '2023'\n",
+    "    mycol1.insert_one(m_xx)\n",
+    "    #print(m_xx)\n",
+    "print('ok')\n",
+    "mydoc = mycol1.find().sort(\"rank_min\")\n",
+    "i = 1 \n",
+    "for x in mydoc:\n",
+    "    m_xx = {}\n",
+    "    m_xx['pos'] = i\n",
+    "    m_xx['col_code'] = x['col_code']\n",
+    "    m_xx['col_name'] = x['col_name'] \n",
+    "    m_xx['spe_code'] = x['spe_code']\n",
+    "    m_xx['spe_name'] = x['spe_name']\n",
+    "    m_xx['plan'] = x['plan']\n",
+    "    m_xx['num_min'] = x['num_min']\n",
+    "    m_xx['rank_min'] = x['rank_min']\n",
+    "    m_xx['nian'] = '2023'\n",
+    "    mycol.insert_one(m_xx)\n",
+    "    i+=1\n",
+    "print('ok')    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "metadata": {