{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9ba0d5ce",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# 1. 数据采集\n",
    "# 从本地文件中读取数据  2分\n",
    "data = _____________\n",
    "print(\"数据采集完成，已加载到DataFrame中\")\n",
    "\n",
    "# 打印数据的前5条记录 2分\n",
    "print(_____________)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f1e1d2ae",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 2. 数据清洗与预处理\n",
    "# 处理缺失值（删除）  2分\n",
    "data = _____________\n",
    "\n",
    "# 数据类型转换\n",
    "data_____________ = _____________(int)       #Age数据类型转换为int 1分\n",
    "data_____________ = _____________(float)     #Speed数据类型转换为float 1分\n",
    "data_____________ = _____________(float)     #TravelDistance数据类型转换为float 1分\n",
    "data_____________ = _____________(float)     #TravelTime数据类型转换为float 1分\n",
    "\n",
    "# 处理异常值  2分\n",
    "data = data[(_____________(18, 70))  & \n",
    "            (_____________(0, 200)) & \n",
    "            (_____________(1, 1000)) & \n",
    "            (_____________(1, 1440))]\n",
    "\n",
    "# 保存清洗后的数据  1分\n",
    "_____________('cleaned_vehicle_traffic_data.csv', index=False)\n",
    "print(\"数据清洗完成，已保存为 'cleaned_vehicle_traffic_data.csv'\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0585f91c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 3. 数据合理性审核\n",
    "# 审核字段合理性 1分\n",
    "unreasonable_data = data[~((_____________(18, 70)) & \n",
    "                           (_____________(0, 200)) & \n",
    "                           (_____________(1, 1000)) & \n",
    "                           (_____________(1, 1440)))]\n",
    "print(\"不合理的数据:\\n\", unreasonable_data)\n",
    "\n",
    "# 4. 数据统计\n",
    "# 统计每种交通事件的发生次数  2分\n",
    "traffic_event_counts = _____________\n",
    "print(\"每种交通事件的发生次数:\\n\", traffic_event_counts)\n",
    "\n",
    "# 统计不同性别的平均车速、行驶距离和行驶时间  2分\n",
    "gender_stats = data._____________._____________\n",
    "print(\"不同性别的平均车速、行驶距离和行驶时间:\\n\", gender_stats)\n",
    "\n",
    "# 统计不同年龄段的驾驶员数  5分\n",
    "age_bins = [18, 26, 36, 46, 56, 66, np.inf]\n",
    "age_labels = ['18-25', '26-35', '36-45', '46-55', '56-65', '65+']\n",
    "data['AgeGroup'] = _____________(_____________,_____________,_____________, right=False)\n",
    "age_group_counts = _____________\n",
    "print(\"不同年龄段的驾驶员数:\\n\", age_group_counts)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.10.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}