{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "ab1efa37",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "数据库连接成功\n",
      "   可用表：['employees', 'orders', 'products']\n",
      "\n",
      "SQL 工具包已加载（4 个工具）：\n",
      "   - sql_db_query\n",
      "   - sql_db_schema\n",
      "   - sql_db_list_tables\n",
      "   - sql_db_query_checker\n",
      "<class 'list'>\n",
      "\n",
      "NL2SQL Agent 创建完成，可以开始提问了！\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "from langchain_community.utilities import SQLDatabase\n",
    "from langchain_community.agent_toolkits import SQLDatabaseToolkit\n",
    "from langchain_openai import ChatOpenAI\n",
    "from langchain.agents import create_agent  # langchain 1.3.1 的新 API\n",
    "from dotenv import load_dotenv\n",
    "load_dotenv()\n",
    "# ============================================================\n",
    "# 第一步：连接数据库\n",
    "# ============================================================\n",
    "# SQLDatabase.from_uri 接受标准的数据库连接 URI\n",
    "# LangChain 内部会用 SQLAlchemy 管理连接池\n",
    "\n",
    "\n",
    "\n",
    "db_uri = (\n",
    "    f\"mysql+pymysql://{os.getenv('DB_USER')}:{os.getenv('DB_PASSWORD')}\"\n",
    "    f\"@{os.getenv('DB_HOST')}:{os.getenv('DB_PORT')}/{os.getenv('DB_NAME')}\"\n",
    ")\n",
    "db = SQLDatabase.from_uri(db_uri)\n",
    "# print(f\"mysql+pymysql://{os.getenv('DB_USER')}:{os.getenv('DB_PASSWORD')}\")\n",
    "# print(f\"@{os.getenv('DB_HOST')}:{os.getenv('DB_PORT')}/{os.getenv('DB_NAME')}\")\n",
    "\n",
    "# 验证连接：打印可用的表名\n",
    "print(f\"数据库连接成功\")\n",
    "print(f\"   可用表：{db.get_usable_table_names()}\")\n",
    "\n",
    "# ============================================================\n",
    "# 第二步：初始化大模型\n",
    "# ============================================================\n",
    "llm = ChatOpenAI(\n",
    "    model=\"deepseek-v4-flash\",\n",
    "    api_key=os.getenv(\"OPENAI_API_KEY\"),\n",
    "    base_url=\"https://api.deepseek.com\",\n",
    "    temperature=0,  # SQL 生成需要确定性输出\n",
    ")\n",
    "\n",
    "# ============================================================\n",
    "# 第三步：创建 SQL 工具包\n",
    "# ============================================================\n",
    "# SQLDatabaseToolkit 会自动注册 4 个工具：\n",
    "#   1. sql_db_list_tables    — 列出数据库中所有表\n",
    "#   2. sql_db_schema         — 获取指定表的 DDL 结构\n",
    "#   3. sql_db_query_checker  — 检查 SQL 语法是否正确\n",
    "#   4. sql_db_query          — 执行 SQL 并返回结果\n",
    "toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",
    "tools = toolkit.get_tools()\n",
    "\n",
    "print(f\"\\nSQL 工具包已加载（{len(tools)} 个工具）：\")\n",
    "for t in tools:\n",
    "    print(f\"   - {t.name}\")\n",
    "\n",
    "print(type (tools))\n",
    "# ============================================================\n",
    "# 第四步：定义 System Prompt（Agent 的\"岗位说明书\"）\n",
    "# ============================================================\n",
    "SQL_AGENT_PROMPT = \"\"\"你是一名专业的 SQL 数据分析师。\n",
    "\n",
    "## 工作流程\n",
    "1. 先用 sql_db_list_tables 查看数据库中有哪些表\n",
    "2. 用 sql_db_schema 获取相关表的字段结构和类型\n",
    "3. 生成 SQL 之前，用 sql_db_query_checker 检查语法\n",
    "4. 确认无误后，用 sql_db_query 执行查询\n",
    "5. 用中文总结查询结果，给出简洁的业务洞察\n",
    "\n",
    "## 约束\n",
    "- 只使用数据库中实际存在的表和字段，不要凭空编造\n",
    "- 单次查询结果限制在 50 条以内\n",
    "- 如果查询出错，分析错误原因后重新生成 SQL\n",
    "- 回答要简洁专业，不要啰嗦\n",
    "\"\"\"\n",
    "\n",
    "# ============================================================\n",
    "# 第五步：组装 Agent（langchain 1.3.1 一行搞定）\n",
    "# ============================================================\n",
    "# create_agent 返回一个可直接调用的 Runnable，无需再套 AgentExecutor\n",
    "# 它内部自动处理工具调用、循环迭代、错误重试等逻辑\n",
    "sql_agent = create_agent(\n",
    "    model=llm,\n",
    "    tools=tools,\n",
    "    system_prompt=SQL_AGENT_PROMPT,\n",
    ")\n",
    "\n",
    "print(\"\\nNL2SQL Agent 创建完成，可以开始提问了！\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d7068f30",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "回答：公司目前共有 **5 名员工**。\n"
     ]
    }
   ],
   "source": [
    "response = sql_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"公司一共有多少名员工？\"}]\n",
    "})\n",
    "\n",
    "# 最终回答在最后一条消息里\n",
    "final_msg = response[\"messages\"][-1]\n",
    "print(f\"回答：{final_msg.content}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5989558d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "回答：查询结果如下：\n",
      "\n",
      "| 姓名 | 薪资 |\n",
      "|:---:|:---:|\n",
      "| 张三 | 20,000.00 |\n",
      "| 王五 | 16,000.00 |\n",
      "\n",
      "**业务洞察：**\n",
      "技术部共有 **2 名员工**，薪资总和为 36,000 元。其中：\n",
      "- **张三**（20,000 元）薪资最高，是技术部的核心骨干\n",
      "- **王五**（16,000 元）紧随其后，团队薪资差距不大（约 25%）\n"
     ]
    }
   ],
   "source": [
    "response = sql_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"列出技术部所有员工的姓名和薪资，按薪资从高到低排序\"}]\n",
    "})\n",
    "final_msg = response[\"messages\"][-1]\n",
    "print(f\"回答：{final_msg.content}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d3b36789",
   "metadata": {},
   "outputs": [],
   "source": [
    "response = sql_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"销售部的员工总共下了多少订单？订单总金额是多少？\"}]\n",
    "})\n",
    "final_msg = response[\"messages\"][-1]\n",
    "print(f\"回答：{final_msg.content}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "333a4697",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "最终回答：每个部门各有多少人？\n",
      "\n",
      "步骤 2 [AIMessage]：\n",
      "  调用工具：sql_db_list_tables\n",
      "  参数：{}\n",
      "  工具返回：employees, orders, products\n",
      "\n",
      "步骤 4 [AIMessage]：\n",
      "  调用工具：sql_db_schema\n",
      "  参数：{'table_names': 'employees'}\n",
      "  工具返回：\n",
      "CREATE TABLE employees (\n",
      "\tid INTEGER NOT NULL AUTO_INCREMENT, \n",
      "\tname VARCHAR(50) NOT NULL, \n",
      "\tdepartment VARCHAR(50) NOT NULL, \n",
      "\tsalary DECIMAL(10, 2) NOT NULL, \n",
      "\thire_date DATE, \n",
      "\tPRIMARY KEY (id)\n",
      ")E\n",
      "\n",
      "步骤 6 [AIMessage]：\n",
      "  调用工具：sql_db_query_checker\n",
      "  参数：{'query': 'SELECT department, COUNT(*) AS 人数 FROM employees GROUP BY department ORDER BY 人数 DESC'}\n",
      "  工具返回：SELECT department, COUNT(*) AS 人数 FROM employees GROUP BY department ORDER BY 人数 DESC\n",
      "\n",
      "步骤 8 [AIMessage]：\n",
      "  调用工具：sql_db_query\n",
      "  参数：{'query': 'SELECT department, COUNT(*) AS 人数 FROM employees GROUP BY department ORDER BY 人数 DESC'}\n",
      "  工具返回：[('技术部', 2), ('销售部', 2), ('人力资源', 1)]\n",
      "\n",
      "最终回答：查询结果如下：\n",
      "\n",
      "| 部门 | 人数 |\n",
      "|------|:----:|\n",
      "| 技术部 | 2 |\n",
      "| 销售部 | 2 |\n",
      "| 人力资源 | 1 |\n",
      "\n",
      "目前公司共有 **3 个部门**，总员工 **5 人**。其中技术部和销售部人数均为 2 人，人力资源部为 1 人，分布相对均衡。\n"
     ]
    }
   ],
   "source": [
    "response = sql_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"每个部门各有多少人？\"}]\n",
    "})\n",
    "\n",
    "for i, msg in enumerate(response[\"messages\"]):\n",
    "    msg_type = msg.__class__.__name__\n",
    "\n",
    "    # AIMessage 中如果有 tool_calls，说明 Agent 调用了工具\n",
    "    if hasattr(msg, \"tool_calls\") and msg.tool_calls:\n",
    "        print(f\"\\n步骤 {i+1} [{msg_type}]：\")\n",
    "        for tc in msg.tool_calls:\n",
    "            print(f\"  调用工具：{tc['name']}\")\n",
    "            print(f\"  参数：{tc.get('args', {})}\")\n",
    "\n",
    "    # ToolMessage 是工具返回的结果\n",
    "    elif msg_type == \"ToolMessage\":\n",
    "        print(f\"  工具返回：{msg.content[:200]}\")\n",
    "\n",
    "    # AIMessage 的最终文本回答\n",
    "    elif msg.content:\n",
    "        print(f\"\\n最终回答：{msg.content}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "083faa70",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ 数据加载完成\n",
      "   员工表：5 行 × 5 列\n",
      "   产品表：4 行 × 5 列\n",
      "   订单表：5 行 × 5 列\n",
      "\n",
      "📋 员工表示例：\n",
      " id name department  salary  hire_date\n",
      "  1   张三        技术部 20000.0 2023-01-15\n",
      "  2   李四        销售部 11000.0 2023-02-20\n",
      "  3   王五        技术部 16000.0 2022-11-10\n"
     ]
    }
   ],
   "source": [
    "import matplotlib\n",
    "import matplotlib.font_manager as fm\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import numpy as np\n",
    "# 1. 删除旧的字体缓存\n",
    "cache_dir = matplotlib.get_cachedir()\n",
    "for f in os.listdir(cache_dir):\n",
    "    if f.startswith('fontlist'):\n",
    "        os.remove(os.path.join(cache_dir, f))\n",
    "\n",
    "# 2. 强制重新扫描系统字体\n",
    "fm._load_fontmanager(try_read_cache=False)\n",
    "# ============================================================\n",
    "# 配置 matplotlib 中文显示\n",
    "# ============================================================\n",
    "# Windows 用 SimHei（黑体），macOS 用 PingFang SC\n",
    "# 如果还是乱码，试试安装 fonts-noto-cjk 并清除缓存\n",
    "plt.rcParams[\"font.sans-serif\"] = [\"SimHei\", \"PingFang SC\", \"DejaVu Sans\"]\n",
    "plt.rcParams[\"axes.unicode_minus\"] = False  # 解决负号显示为方块的问题\n",
    "\n",
    "# ============================================================\n",
    "# 从数据库加载数据到 Pandas DataFrame\n",
    "# ============================================================\n",
    "# 用 SQLAlchemy engine 复用连接，避免重复创建连接池\n",
    "from sqlalchemy import create_engine\n",
    "\n",
    "engine = create_engine(db_uri)\n",
    "\n",
    "employees_df = pd.read_sql(\"SELECT * FROM employees\", engine)\n",
    "products_df  = pd.read_sql(\"SELECT * FROM products\", engine)\n",
    "orders_df    = pd.read_sql(\"SELECT * FROM orders\", engine)\n",
    "\n",
    "print(\"✅ 数据加载完成\")\n",
    "print(f\"   员工表：{len(employees_df)} 行 × {len(employees_df.columns)} 列\")\n",
    "print(f\"   产品表：{len(products_df)} 行 × {len(products_df.columns)} 列\")\n",
    "print(f\"   订单表：{len(orders_df)} 行 × {len(orders_df.columns)} 列\")\n",
    "print(f\"\\n📋 员工表示例：\")\n",
    "print(employees_df.head(3).to_string(index=False))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "9bf4a205",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "✅ Python 代码执行沙箱创建成功\n"
     ]
    }
   ],
   "source": [
    "import traceback\n",
    "from io import StringIO\n",
    "from contextlib import redirect_stdout\n",
    "from langchain.tools import tool\n",
    "\n",
    "# ============================================================\n",
    "# 定义沙箱的\"白名单\"——只有这些库和数据可以被代码访问\n",
    "# ============================================================\n",
    "# 这是一种简单的安全策略：不在白名单里的东西，代码碰不到\n",
    "SANDBOX_GLOBALS = {\n",
    "    # 数据：Agent 可以分析这三张表\n",
    "    \"employees_df\": employees_df,\n",
    "    \"products_df\":  products_df,\n",
    "    \"orders_df\":    orders_df,\n",
    "    # 工具库：Agent 可以用这些库做分析和画图\n",
    "    \"pd\":  pd,       # pandas — 数据处理\n",
    "    \"plt\": plt,      # matplotlib — 基础绑图\n",
    "    \"sns\": sns,      # seaborn — 统计可视化\n",
    "    \"np\":  np,       # numpy — 数值计算\n",
    "}\n",
    "\n",
    "\n",
    "@tool\n",
    "def execute_python_code(code: str) -> str:\n",
    "    \"\"\"\n",
    "    执行 Python 代码进行数据分析和可视化。\n",
    "\n",
    "    可用变量：\n",
    "      - employees_df: 员工表 DataFrame（字段：id, name, department, salary, hire_date）\n",
    "      - products_df:  产品表 DataFrame（字段：id, product_name, category, price, stock）\n",
    "      - orders_df:    订单表 DataFrame（字段：id, employee_id, product_id, quantity, order_date）\n",
    "      - pd:   pandas 库\n",
    "      - plt:  matplotlib.pyplot\n",
    "      - sns:  seaborn\n",
    "      - np:   numpy\n",
    "\n",
    "    使用示例：\n",
    "      # 统计各部门平均薪资\n",
    "      result = employees_df.groupby('department')['salary'].mean()\n",
    "      print(result)\n",
    "\n",
    "      # 画柱状图\n",
    "      plt.figure(figsize=(10, 6))\n",
    "      employees_df.groupby('department')['salary'].mean().plot(kind='bar')\n",
    "      plt.title('各部门平均薪资')\n",
    "      plt.show()\n",
    "    \"\"\"\n",
    "    # 准备隔离的执行环境\n",
    "    # globals_dict 提供白名单变量，locals_dict 收集执行过程中产生的新变量\n",
    "    exec_globals = dict(SANDBOX_GLOBALS)\n",
    "    exec_locals = {}\n",
    "\n",
    "    # 用 StringIO 捕获 print() 的输出\n",
    "    # 这样 Agent 生成的代码里所有的 print 语句都会被收集\n",
    "    output_buffer = StringIO()\n",
    "\n",
    "    try:\n",
    "        # redirect_stdout 会把标准输出重定向到我们的 buffer\n",
    "        with redirect_stdout(output_buffer):\n",
    "            exec(code, exec_globals, exec_locals)\n",
    "\n",
    "        result = output_buffer.getvalue()\n",
    "\n",
    "        # 如果代码没有 print 任何东西，给个默认提示\n",
    "        if not result.strip():\n",
    "            result = \"✅ 代码执行成功（无文本输出，可能已生成图表）\"\n",
    "\n",
    "        return f\"执行成功：\\n{result}\"\n",
    "\n",
    "    except Exception as e:\n",
    "        # 出错时返回完整的错误堆栈，方便 Agent 自我修正\n",
    "        error_detail = traceback.format_exc()\n",
    "        return f\"❌ 执行出错：{e}\\n\\n{error_detail}\"\n",
    "\n",
    "\n",
    "print(\"✅ Python 代码执行沙箱创建成功\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "bc6db1c3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "数据可视化 Agent 创建完成\n"
     ]
    }
   ],
   "source": [
    "from langchain.agents import create_agent\n",
    "\n",
    "# ============================================================\n",
    "# 定义可视化 Agent 的 System Prompt\n",
    "# ============================================================\n",
    "VISUALIZATION_PROMPT = \"\"\"你是一名资深数据分析师，精通 Python、Pandas 和 Matplotlib 数据可视化。\n",
    "\n",
    "## 可用数据\n",
    "1. employees_df — 员工表（字段：id, name, department, salary, hire_date）\n",
    "2. products_df  — 产品表（字段：id, product_name, category, price, stock）\n",
    "3. orders_df    — 订单表（字段：id, employee_id, product_id, quantity, order_date）\n",
    "\n",
    "## 工作流程\n",
    "1. 理解用户的分析需求\n",
    "2. 用 execute_python_code 工具编写并执行 Python 代码\n",
    "3. 先做数据探索（head、describe、info），再做深入分析\n",
    "4. 用中文解释分析结果，给出业务洞察\n",
    "\n",
    "## 代码规范\n",
    "- 绑图前设置中文字体：plt.rcParams['font.sans-serif'] = ['SimHei', 'PingFang SC', 'DejaVu Sans']\n",
    "- 设置 plt.rcParams['axes.unicode_minus'] = False\n",
    "- 图表尺寸统一用 plt.figure(figsize=(10, 6))\n",
    "- 必须添加标题、坐标轴标签，让图表自解释\n",
    "- 用 print() 输出关键统计量，不要只画图不说话\n",
    "- 图表标题用英文（避免渲染问题），但用中文向用户解释结果\n",
    "\n",
    "## 注意事项\n",
    "- 每次只执行一段完整的代码，不要拆成多段\n",
    "- 先探索数据结构，再做分析——不要上来就画图\n",
    "- 结果要有业务洞察，不只是\"最大值是 XXX\"\n",
    "\"\"\"\n",
    "\n",
    "# ============================================================\n",
    "# 组装可视化 Agent（langchain 1.3.1 写法）\n",
    "# ============================================================\n",
    "viz_tools = [execute_python_code]\n",
    "\n",
    "# 同样用 create_agent 一行搞定，和 SQL Agent 的创建方式完全一致\n",
    "visualization_agent = create_agent(\n",
    "    model=llm,\n",
    "    tools=viz_tools,\n",
    "    system_prompt=VISUALIZATION_PROMPT,\n",
    ")\n",
    "\n",
    "print(\"数据可视化 Agent 创建完成\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "75e5e5c3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<Figure size 1200x600 with 0 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "分析结果：\n",
      "好的，分析完成！以下是完整的 **员工薪资分布分析报告**：\n",
      "\n",
      "---\n",
      "\n",
      "## 📊 员工薪资分布分析报告\n",
      "\n",
      "### 一、数据概览\n",
      "数据集中共有 **5 名员工**，分布在 **3 个部门**（技术部、销售部、人力资源），薪资字段无缺失值。\n",
      "\n",
      "---\n",
      "\n",
      "### 二、关键统计指标\n",
      "\n",
      "| 指标 | 数值 |\n",
      "|------|------|\n",
      "| **平均薪资** | **13,800 元** |\n",
      "| **中位数薪资** | **16,000 元** |\n",
      "| **最低薪资** | **5,000 元** |\n",
      "| **最高薪资** | **20,000 元** |\n",
      "| **薪资范围** | **15,000 元** |\n",
      "| **标准差** | **5,890 元** |\n",
      "| **Q1（第一四分位）** | **11,000 元** |\n",
      "| **Q3（第三四分位）** | **17,000 元** |\n",
      "| **四分位距 (IQR)** | **6,000 元** |\n",
      "| **偏度** | **-0.86（左偏）** |\n",
      "\n",
      "---\n",
      "\n",
      "### 三、业务洞察\n",
      "\n",
      "**1️⃣ 薪资整体分布特征**\n",
      "- **均值（13,800）< 中位数（16,000）**，说明薪资分布呈现 **左偏（负偏）** 形态——即薪资较低端有极端值（人力资源的 5,000 元）拖低了均值，大部分人的薪资其实集中在 11,000~17,000 元区间。\n",
      "- 薪资范围宽达 **15,000 元**，最高薪资（20,000）是最低薪资（5,000）的 **4 倍**，反映出部门间薪资差距较大。\n",
      "\n",
      "**2️⃣ 部门薪资差异显著**\n",
      "| 部门 | 平均薪资 | 员工数 |\n",
      "|------|---------|-------|\n",
      "| 🔧 **技术部** | **18,000 元** | 2 人 |\n",
      "| 💼 **销售部** | **14,000 元** | 2 人 |\n",
      "| 👥 **人力资源** | **5,000 元** | 1 人 |\n",
      "\n",
      "- **技术部薪资最高**（平均 18,000 元），两名员工薪资分别为 16,000 和 20,000，内部差距 4,000 元。\n",
      "- **销售部居中**（平均 14,000 元），两人薪资为 11,000 和 17,000，内部差距达 6,000 元，销售岗位的业绩导向特征明显。\n",
      "- **人力资源最低**（仅 5,000 元），这个薪资明显低于其他部门，可能存在 **岗位价值评估偏低** 或 **数据不完整** 的情况，建议关注。\n",
      "\n",
      "**3️⃣ 箱线图分析**\n",
      "- 从箱线图看，数据中没有明显的异常值（所有点都在 1.5 倍 IQR 范围内）。\n",
      "- 但人力资源的 5,000 元薪资已接近下须边缘，属于 **合理范围内的最低值**，但仍需结合行业薪酬水平判断是否合理。\n",
      "\n",
      "---\n",
      "\n",
      "### 四、建议\n",
      "\n",
      "1. **人力资源薪资偏低**：5,000 元的薪资显著低于其他部门，建议对照市场薪酬水平进行复核，避免因薪资不公导致人才流失。\n",
      "2. **销售部薪资差距大**（11,000~17,000），建议明确绩效薪资结构，确保内部公平性。\n",
      "3. **数据量较少**（仅 5 条），以上结论受数据规模限制，建议收集更多员工数据以获得更可靠的薪资分布洞察。\n"
     ]
    }
   ],
   "source": [
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")  # 抑制 matplotlib 的字体警告\n",
    "\n",
    "response = visualization_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"分析一下员工薪资的分布情况，包括均值、中位数、最大最小值等统计量\"}]\n",
    "})\n",
    "final_msg = response[\"messages\"][-1]\n",
    "print(f\"\\n分析结果：\\n{final_msg.content}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "515bfde9",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"=== 薪资统计概览 ===\")\n",
    "print(employees_df['salary'].describe())\n",
    "\n",
    "# 计算额外统计量\n",
    "median_salary = employees_df['salary'].median()\n",
    "print(f\"\\n中位数薪资：{median_salary:,.0f} 元\")\n",
    "print(f\"薪资范围：{employees_df['salary'].min():,.0f} ~ {employees_df['salary'].max():,.0f} 元\")\n",
    "print(f\"薪资标准差：{employees_df['salary'].std():,.0f} 元\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "58b8aca8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 定制化图表内容\n",
    "plt.rcParams['font.sans-serif'] = ['SimHei', 'PingFang SC', 'DejaVu Sans']\n",
    "plt.rcParams['axes.unicode_minus'] = False\n",
    "\n",
    "# 按部门计算平均薪资\n",
    "dept_salary = employees_df.groupby('department')['salary'].mean().sort_values(ascending=False)\n",
    "\n",
    "# 画柱状图\n",
    "plt.figure(figsize=(10, 6))\n",
    "bars = plt.bar(dept_salary.index, dept_salary.values, color=['#4C78A8', '#F58518', '#E45756'])\n",
    "plt.title('Average Salary by Department', fontsize=16)\n",
    "plt.xlabel('Department', fontsize=12)\n",
    "plt.ylabel('Average Salary (CNY)', fontsize=12)\n",
    "\n",
    "# 在柱子上方标注具体数值\n",
    "for bar in bars:\n",
    "    height = bar.get_height()\n",
    "    plt.text(bar.get_x() + bar.get_width()/2., height,\n",
    "             f'{height:,.0f}', ha='center', va='bottom', fontsize=11)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eff33063",
   "metadata": {},
   "outputs": [],
   "source": [
    "response = visualization_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"计算每个产品类别的库存总量，用水平条形图展示，并标注具体数值\"}]\n",
    "})\n",
    "final_msg = response[\"messages\"][-1]\n",
    "print(f\"\\n分析结果：\\n{final_msg.content}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1c4d1ca1",
   "metadata": {},
   "outputs": [],
   "source": [
    "response = visualization_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"分析各产品类别的平均价格，画一个饼图\"}]\n",
    "})\n",
    "\n",
    "for i, msg in enumerate(response[\"messages\"]):\n",
    "    msg_type = msg.__class__.__name__\n",
    "\n",
    "    # AIMessage 中的 tool_calls 包含 Agent 生成的代码\n",
    "    if msg_type == \"AIMessage\" and hasattr(msg, \"tool_calls\") and msg.tool_calls:\n",
    "        print(f\"\\n{'='*60}\")\n",
    "        for tc in msg.tool_calls:\n",
    "            if tc[\"name\"] == \"execute_python_code\":\n",
    "                print(f\"Agent 生成的第 {i+1} 段代码：\")\n",
    "                print(f\"{'='*60}\")\n",
    "                print(tc[\"args\"].get(\"code\", \"\"))\n",
    "\n",
    "    # ToolMessage 是代码执行的结果\n",
    "    elif msg_type == \"ToolMessage\":\n",
    "        print(f\"\\n--- 执行结果 ---\")\n",
    "        print(msg.content[:500])\n",
    "\n",
    "# 最终回答\n",
    "final_msg = response[\"messages\"][-1]\n",
    "print(f\"\\n{'='*60}\")\n",
    "print(f\"最终回答：\\n{final_msg.content}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "df23159e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 编排器：根据用户意图路由到合适的 Agent\n",
    "def run_data_analysis(user_query: str) -> str:\n",
    "    \"\"\"\n",
    "    统一入口：自动判断用户意图，路由到对应的 Agent。\n",
    "    \"\"\"\n",
    "    # 用 LLM 做意图分类（也可以用规则匹配，看场景复杂度）\n",
    "    classification_prompt = f\"\"\"判断以下用户问题属于哪种类型：\n",
    "    - \"query\"：需要查询数据库获取数据\n",
    "    - \"visualize\"：需要画图或做统计分析\n",
    "    - \"both\"：需要先查数据，再画图分析\n",
    "\n",
    "    用户问题：{user_query}\n",
    "\n",
    "    只回复一个词：query / visualize / both\"\"\"\n",
    "\n",
    "    intent = llm.invoke(classification_prompt).content.strip().lower()\n",
    "\n",
    "    if intent == \"query\":\n",
    "        # create_agent 返回的消息格式：取最后一条消息\n",
    "        result = sql_agent.invoke({\"messages\": [{\"role\": \"user\", \"content\": user_query}]})\n",
    "        return result[\"messages\"][-1].content\n",
    "    elif intent == \"visualize\":\n",
    "        result = visualization_agent.invoke({\"messages\": [{\"role\": \"user\", \"content\": user_query}]})\n",
    "        return result[\"messages\"][-1].content\n",
    "    else:  # both\n",
    "        # 先查数据\n",
    "        data_result = sql_agent.invoke({\"messages\": [{\"role\": \"user\", \"content\": user_query}]})\n",
    "        data_content = data_result[\"messages\"][-1].content\n",
    "        # 把查询结果传给可视化 Agent\n",
    "        viz_input = f\"基于以下数据进行可视化分析：\\n{data_content}\\n\\n原始问题：{user_query}\"\n",
    "        viz_result = visualization_agent.invoke({\"messages\": [{\"role\": \"user\", \"content\": viz_input}]})\n",
    "        return viz_result[\"messages\"][-1].content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "66564354",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "双Agent准备完成\n"
     ]
    }
   ],
   "source": [
    "# 把 SQL 工具和 Python 代码执行工具都挂到同一个 Agent 上，\n",
    "# 让 LLM 自己决定调用哪些工具。优点是简单，缺点是工具太多时 LLM 容易\"选择困难\"。\n",
    "both_tools = tools + viz_tools\n",
    "\n",
    "BOTH_PROMPT = \"\"\"你是一命资深数据分析师，精通SQL查询数据以及Python、Pandas 和 Matplotlib 制作数据可视化图表。\n",
    "\n",
    "## 可用数据\n",
    "1. employees_df — 员工表（字段：id, name, department, salary, hire_date）\n",
    "2. products_df  — 产品表（字段：id, product_name, category, price, stock）\n",
    "3. orders_df    — 订单表（字段：id, employee_id, product_id, quantity, order_date）\n",
    "\n",
    "## 工作流程\n",
    "1. 优先判断用户需求是关于“SQL”查询还是“生出可视化图表”，确定好合适的需求后调用工具帮助用户解决问题\n",
    "2. 如果需求是是SQL查询，例如想要查询数据库数据，工作流程如下:\n",
    "    (1) 先用 sql_db_list_tables 查看数据库中有哪些表\n",
    "    (2) 用 sql_db_schema 获取相关表的字段结构和类型\n",
    "    (3) 生成 SQL 之前，用 sql_db_query_checker 检查语法\n",
    "    (4) 确认无误后，用 sql_db_query 执行查询\n",
    "    (5) 用中文总结查询结果，给出简洁的业务洞察\n",
    "3. 如果需求是生成图表或做统计分析，工作流程如下：\n",
    "    (1) 理解用户的分析需求\n",
    "    (2) 用 execute_python_code 工具编写并执行 Python 代码\n",
    "    (3) 先做数据探索（head、describe、info），再做深入分析\n",
    "    (4) 用中文解释分析结果，给出业务洞察\n",
    "4. 如果需要同时执行SQL查询和统计分析，按照先查询SQL(回到步骤2),再生成统计图表(回到步骤3的顺序执行)\n",
    "5. 如果用户的提问和SQL查询、统计数据、图表生成等问题无关，或者询问的内容不属于员工表、产品表、订单表的信息，请用户再次明确问题，并告知无法查询到相关信息\n",
    "\n",
    "## 约束\n",
    "如果执行SQL查询，约束如下：\n",
    "- 只使用数据库中实际存在的表和字段，不要凭空编造\n",
    "- 单次查询结果限制在 50 条以内\n",
    "- 如果查询出错，分析错误原因后重新生成 SQL\n",
    "- 回答要简洁专业，不要啰嗦\n",
    "如果执行生成图表，约束如下：\n",
    "- 每次只执行一段完整的代码，不要拆成多段\n",
    "- 先探索数据结构，再做分析——不要上来就画图\n",
    "- 结果要有业务洞察，不只是\"最大值是 XXX\"\n",
    "\n",
    "## 代码规范\n",
    "- 绑图前设置中文字体：plt.rcParams['font.sans-serif'] = ['SimHei', 'PingFang SC', 'DejaVu Sans']\n",
    "- 设置 plt.rcParams['axes.unicode_minus'] = False\n",
    "- 图表尺寸统一用 plt.figure(figsize=(10, 6))\n",
    "- 必须添加标题、坐标轴标签，让图表自解释\n",
    "- 用 print() 输出关键统计量，不要只画图不说话\n",
    "- 图表标题用英文（避免渲染问题），但用中文向用户解释结果\n",
    "\n",
    "## 注意事项\n",
    "\"\"\"\n",
    "both_agent = create_agent(\n",
    "    model=llm,\n",
    "    tools=both_tools,\n",
    "    system_prompt=BOTH_PROMPT,\n",
    ")\n",
    "\n",
    "print(\"双Agent准备完成\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "99a92ac2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "回答：查询完成！以下是 **技术部** 所有员工的姓名和薪资（按薪资从高到低排序）：\n",
      "\n",
      "| 姓名 | 薪资 |\n",
      "|------|------|\n",
      "| 张三 | ¥20,000.00 |\n",
      "| 王五 | ¥16,000.00 |\n",
      "\n",
      "**业务洞察：**\n",
      "- 技术部共有 **2 名员工**，平均薪资为 **¥18,000.00**。\n",
      "- 薪资最高的是 **张三（¥20,000）**，比第二名王五高出 **¥4,000（25%）**，说明技术部内部薪资存在一定差距。\n"
     ]
    }
   ],
   "source": [
    "response = both_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"列出技术部所有员工的姓名和薪资，按薪资从高到低排序\"}]\n",
    "})\n",
    "final_msg = response[\"messages\"][-1]\n",
    "print(f\"回答：{final_msg.content}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "197be8a6",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "findfont: Failed to find font weight bold, now using 400.\n",
      "findfont: Failed to find font weight bold, now using 400.\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "分析结果：\n",
      "## 分析结果与业务洞察\n",
      "\n",
      "### 📊 各产品类别库存总量\n",
      "\n",
      "| 产品类别 | 库存总量 |\n",
      "|---------|:--------:|\n",
      "| 🖥️ **电子产品** | **1,900 件** |\n",
      "| 🪑 **办公用品** | **300 件** |\n",
      "| **合计** | **2,200 件** |\n",
      "\n",
      "### 💡 业务洞察\n",
      "\n",
      "1. **电子产品占据绝对主导**——库存占比高达 **86.4%**（1,900/2,200），是办公用品的 **6 倍多**，说明该公司核心业务聚焦在电子产品线。\n",
      "\n",
      "2. **办公用品库存偏少**——仅 300 件，可能因为该类目产品较少（只有 1 款办公椅），建议关注是否有扩展办公用品品类的空间。\n",
      "\n",
      "3. **库存结构不均衡**——两个类别的库存量差距悬殊，建议进一步分析销售周转率，判断电子产品是否存在**库存积压**风险，而办公用品是否存在**断货隐患**。\n",
      "\n",
      "4. **整体库存水位**——总库存 2,200 件，结合订单表数据可以进一步评估库存周转效率，判断是否需要优化采购策略。\n",
      "\n",
      "> 📌 如需深入分析，可以进一步查看各产品类别的销量情况，计算**库存周转天数**，更精准地评估健康度。\n"
     ]
    }
   ],
   "source": [
    "response = visualization_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"计算每个产品类别的库存总量，用水平条形图展示，并标注具体数值\"}]\n",
    "})\n",
    "final_msg = response[\"messages\"][-1]\n",
    "print(f\"\\n分析结果：\\n{final_msg.content}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "8da88f92",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "回答：抱歉，当前数据库中只有以下三张表：\n",
      "\n",
      "1. **employees** — 员工表\n",
      "2. **products** — 产品表\n",
      "3. **orders** — 订单表\n",
      "\n",
      "**没有「学生表」**，因此无法查询学生的姓名、学号和分数信息。\n",
      "\n",
      "请您重新明确需求，例如：\n",
      "- 想查询**员工**的姓名和相关信息？\n",
      "- 想查询**产品**或**订单**的数据？\n",
      "- 或者有其他分析需求？\n",
      "\n",
      "确认后我来帮您处理！\n"
     ]
    }
   ],
   "source": [
    "response = both_agent.invoke({\n",
    "    \"messages\": [{\"role\": \"user\", \"content\": \"列出所有学生的姓名和学号，按分数从高到低排序\"}]\n",
    "})\n",
    "final_msg = response[\"messages\"][-1]\n",
    "print(f\"回答：{final_msg.content}\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "02_DATA_Analysis",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}