autogen/website/docs/topics/code-execution/custom-executor.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Custom Code Executor\n",
    "\n",
    "In this guide we will show you how to create a custom code executor that runs\n",
    "code inside the same Jupyter notebook as this one.\n",
    "\n",
    "First, let's install the required dependencies:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "! pip -qqq install pyautogen matplotlib yfinance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from typing import List\n",
    "\n",
    "from IPython import get_ipython\n",
    "\n",
    "from autogen import ConversableAgent\n",
    "from autogen.coding import CodeBlock, CodeExecutor, CodeExtractor, CodeResult, MarkdownCodeExtractor"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we can create the custom code executor class by subclassing the\n",
    "`CodeExecutor` protocol and implementing the `execute_code_blocks` method."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "class NotebookExecutor(CodeExecutor):\n",
    "\n",
    "    @property\n",
    "    def code_extractor(self) -> CodeExtractor:\n",
    "        # Extact code from markdown blocks.\n",
    "        return MarkdownCodeExtractor()\n",
    "\n",
    "    def __init__(self) -> None:\n",
    "        # Get the current IPython instance running in this notebook.\n",
    "        self._ipython = get_ipython()\n",
    "\n",
    "    def execute_code_blocks(self, code_blocks: List[CodeBlock]) -> CodeResult:\n",
    "        log = \"\"\n",
    "        for code_block in code_blocks:\n",
    "            result = self._ipython.run_cell(\"%%capture --no-display cap\\n\" + code_block.code)\n",
    "            log += self._ipython.ev(\"cap.stdout\")\n",
    "            log += self._ipython.ev(\"cap.stderr\")\n",
    "            if result.result is not None:\n",
    "                log += str(result.result)\n",
    "            exitcode = 0 if result.success else 1\n",
    "            if result.error_before_exec is not None:\n",
    "                log += f\"\\n{result.error_before_exec}\"\n",
    "                exitcode = 1\n",
    "            if result.error_in_exec is not None:\n",
    "                log += f\"\\n{result.error_in_exec}\"\n",
    "                exitcode = 1\n",
    "            if exitcode != 0:\n",
    "                break\n",
    "        return CodeResult(exit_code=exitcode, output=log)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we can use the new custom code executor in our agents."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "code_writer_agent = ConversableAgent(\n",
    "    name=\"CodeWriter\",\n",
    "    system_message=\"You are a helpful AI assistant.\\n\"\n",
    "    \"You use your coding skill to solve problems.\\n\"\n",
    "    \"You have access to a IPython kernel to execute Python code.\\n\"\n",
    "    \"You can suggest Python code in Markdown blocks, each block is a cell.\\n\"\n",
    "    \"The code blocks will be executed in the IPython kernel in the order you suggest them.\\n\"\n",
    "    \"All necessary libraries have already been installed.\\n\"\n",
    "    \"Once the task is done, returns 'TERMINATE'.\",\n",
    "    llm_config={\"config_list\": [{\"model\": \"gpt-4\", \"api_key\": os.getenv(\"OPENAI_API_KEY\")}]},\n",
    ")\n",
    "\n",
    "code_executor_agent = ConversableAgent(\n",
    "    name=\"CodeExecutor\",\n",
    "    llm_config=False,\n",
    "    code_execution_config={\"executor\": NotebookExecutor()},\n",
    "    is_termination_msg=lambda msg: \"TERMINATE\" in msg.get(\"content\", \"\").strip().upper(),\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's use the agents to complete a simple task of drawing a plot showing\n",
    "the market caps of the top 7 publicly listed companies."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mCodeExecutor\u001b[0m (to CodeWriter):\n",
      "\n",
      "Create a plot showing the market caps of the top 7 publicly listed companies using data from Yahoo Finance.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeWriter\u001b[0m (to CodeExecutor):\n",
      "\n",
      "To accomplish this task, we would use the `yfinance` library to fetch data from Yahoo Finance, `pandas` library for data manipulation, and `matplotlib` for data visualization.\n",
      "\n",
      "Steps:\n",
      "1. Identify the tickers for the top 7 largest publicly listed companies. Currently, these companies are: Apple (AAPL), Microsoft (MSFT), Google (GOOGL), Amazon (AMZN), Facebook (FB), Tesla (TSLA), and Berkshire Hathaway (BRK-A).\n",
      "2. Fetch market cap information for these companies using yfinance.\n",
      "3. Clean and process the fetched data into a usable format (a pandas DataFrame).\n",
      "4. Plot the market caps for these companies.\n",
      "\n",
      "Let's start by fetching data for these companies.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeExecutor\u001b[0m (to CodeWriter):\n",
      "\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeWriter\u001b[0m (to CodeExecutor):\n",
      "\n",
      "Great! Before I continue, I need to know if the necessary libraries are installed.\n",
      "\n",
      "The libraries needed for this task are:\n",
      "1. `yfinance`\n",
      "2. `pandas`\n",
      "3. `matplotlib`\n",
      "\n",
      "If these libraries are not installed, you can install them using pip:\n",
      "\n",
      "```python\n",
      "!pip install yfinance pandas matplotlib\n",
      "```\n",
      "\n",
      "Assuming these libraries are installed, we would import them and proceed with fetching the market cap data:\n",
      "\n",
      "```python\n",
      "import yfinance as yf\n",
      "import pandas as pd\n",
      "import matplotlib.pyplot as plt\n",
      "\n",
      "# Define tickers \n",
      "tickers = [\"AAPL\", \"MSFT\", \"GOOGL\", \"AMZN\", \"FB\", \"TSLA\", \"BRK-A\"]\n",
      "\n",
      "# Fetch data\n",
      "data = yf.download(tickers, start=\"2022-02-01\", end=\"2022-02-28\")\n",
      "\n",
      "# Extract only 'Close' values for each ticker\n",
      "data = data['Close']\n",
      "\n",
      "# Create empty dictionary to hold market cap data\n",
      "market_caps = {}\n",
      "\n",
      "# Calculate market caps\n",
      "for ticker in tickers:\n",
      "    info = yf.Ticker(ticker).info\n",
      "    market_caps[ticker] = info[\"marketCap\"]\n",
      "\n",
      "# Convert market_caps dictionary to pandas DataFrame\n",
      "df = pd.DataFrame(list(market_caps.items()), columns=['Company', 'Market_Cap'])\n",
      "\n",
      "# Sort DataFrame by Market_Cap in descending order\n",
      "df = df.sort_values('Market_Cap', ascending=False)\n",
      "\n",
      "# Plot data\n",
      "plt.figure(figsize=(10,6))\n",
      "plt.barh(df['Company'], df['Market_Cap'], color='skyblue')\n",
      "plt.xlabel('Market Cap (in trillions)')\n",
      "plt.title('Market Caps of Top 7 Publicly Listed Companies')\n",
      "plt.gca().invert_yaxis()\n",
      "plt.show()\n",
      "```\n",
      "\n",
      "Please note that the start and end dates used while fetching data specifies the time period we are interested in. Feel free to modify these as needed. The 'marketCap' obtained from the 'info' property of the Ticker object represents the market cap as of the end date.\n",
      "\n",
      "Also note that the final plot shows the companies in descending order of market cap, with the company with the highest market cap at the top of the chart.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> EXECUTING 2 CODE BLOCKS (inferred languages are [python, python])...\u001b[0m\n"
     ]
    },
    {
     "ename": "KeyError",
     "evalue": "'marketCap'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[24], line 20\u001b[0m\n\u001b[1;32m     18\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m ticker \u001b[38;5;129;01min\u001b[39;00m tickers:\n\u001b[1;32m     19\u001b[0m     info \u001b[38;5;241m=\u001b[39m yf\u001b[38;5;241m.\u001b[39mTicker(ticker)\u001b[38;5;241m.\u001b[39minfo\n\u001b[0;32m---> 20\u001b[0m     market_caps[ticker] \u001b[38;5;241m=\u001b[39m \u001b[43minfo\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmarketCap\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m]\u001b[49m\n\u001b[1;32m     22\u001b[0m \u001b[38;5;66;03m# Convert market_caps dictionary to pandas DataFrame\u001b[39;00m\n\u001b[1;32m     23\u001b[0m df \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mDataFrame(\u001b[38;5;28mlist\u001b[39m(market_caps\u001b[38;5;241m.\u001b[39mitems()), columns\u001b[38;5;241m=\u001b[39m[\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mCompany\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mMarket_Cap\u001b[39m\u001b[38;5;124m'\u001b[39m])\n",
      "\u001b[0;31mKeyError\u001b[0m: 'marketCap'"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mCodeExecutor\u001b[0m (to CodeWriter):\n",
      "\n",
      "exitcode: 0 (execution succeeded)\n",
      "Code output: Requirement already satisfied: yfinance in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (0.2.36)\n",
      "Requirement already satisfied: pandas in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (2.2.1)\n",
      "Requirement already satisfied: matplotlib in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (3.8.3)\n",
      "Requirement already satisfied: numpy>=1.16.5 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (1.26.4)\n",
      "Requirement already satisfied: requests>=2.31 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (2.31.0)\n",
      "Requirement already satisfied: multitasking>=0.0.7 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (0.0.11)\n",
      "Requirement already satisfied: lxml>=4.9.1 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (5.0.1)\n",
      "Requirement already satisfied: appdirs>=1.4.4 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (1.4.4)\n",
      "Requirement already satisfied: pytz>=2022.5 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (2023.3.post1)\n",
      "Requirement already satisfied: frozendict>=2.3.4 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (2.4.0)\n",
      "Requirement already satisfied: peewee>=3.16.2 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (3.17.0)\n",
      "Requirement already satisfied: beautifulsoup4>=4.11.1 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (4.12.2)\n",
      "Requirement already satisfied: html5lib>=1.1 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from yfinance) (1.1)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from pandas) (2.8.2)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from pandas) (2023.4)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from matplotlib) (1.2.0)\n",
      "Requirement already satisfied: cycler>=0.10 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from matplotlib) (0.12.1)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from matplotlib) (4.47.2)\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from matplotlib) (1.4.5)\n",
      "Requirement already satisfied: packaging>=20.0 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from matplotlib) (23.2)\n",
      "Requirement already satisfied: pillow>=8 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from matplotlib) (10.2.0)\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from matplotlib) (3.1.1)\n",
      "Requirement already satisfied: soupsieve>1.2 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from beautifulsoup4>=4.11.1->yfinance) (2.5)\n",
      "Requirement already satisfied: six>=1.9 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from html5lib>=1.1->yfinance) (1.16.0)\n",
      "Requirement already satisfied: webencodings in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from html5lib>=1.1->yfinance) (0.5.1)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from requests>=2.31->yfinance) (3.3.2)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from requests>=2.31->yfinance) (3.6)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from requests>=2.31->yfinance) (1.26.18)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages (from requests>=2.31->yfinance) (2024.2.2)\n",
      "/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[**************        29%%                      ]  2 of 7 completed/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[********************* 43%%                      ]  3 of 7 completed/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[**********************57%%*                     ]  4 of 7 completed/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[**********************71%%********              ]  5 of 7 completed/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[*********************100%%**********************]  7 of 7 completed\n",
      "\n",
      "1 Failed download:\n",
      "['FB']: Exception('%ticker%: No timezone found, symbol may be delisted')\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeWriter\u001b[0m (to CodeExecutor):\n",
      "\n",
      "From the error message, it seems that the 'FB' ticker (Facebook) failed to download because it might have been delisted. This is likely due to Facebook's corporate rebranding to Meta Platforms Inc. in late 2021, which resulted in a ticker change from 'FB' to 'META'.\n",
      "\n",
      "To resolve this, we'll replace 'FB' in our tickers list with 'META' and then retrieve the data again. Here is the modified code:\n",
      "\n",
      "```python\n",
      "# Define tickers \n",
      "tickers = [\"AAPL\", \"MSFT\", \"GOOGL\", \"AMZN\", \"META\", \"TSLA\", \"BRK-A\"]\n",
      "\n",
      "# Fetch data\n",
      "data = yf.download(tickers, start=\"2022-02-01\", end=\"2022-02-28\")\n",
      "\n",
      "# Extract only 'Close' values for each ticker\n",
      "data = data['Close']\n",
      "\n",
      "# Create empty dictionary to hold market cap data\n",
      "market_caps = {}\n",
      "\n",
      "# Calculate market caps\n",
      "for ticker in tickers:\n",
      "    info = yf.Ticker(ticker).info\n",
      "    market_caps[ticker] = info[\"marketCap\"]\n",
      "\n",
      "# Convert market_caps dictionary to pandas DataFrame\n",
      "df = pd.DataFrame(list(market_caps.items()), columns=['Company', 'Market_Cap'])\n",
      "\n",
      "# Sort DataFrame by Market_Cap in descending order\n",
      "df = df.sort_values('Market_Cap', ascending=False)\n",
      "\n",
      "# Plot data\n",
      "plt.figure(figsize=(10,6))\n",
      "plt.barh(df['Company'], df['Market_Cap'], color='skyblue')\n",
      "plt.xlabel('Market Cap (in trillions)')\n",
      "plt.title('Market Caps of Top 7 Publicly Listed Companies')\n",
      "plt.gca().invert_yaxis()\n",
      "plt.show()\n",
      "```\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> EXECUTING CODE BLOCK (inferred language is python)...\u001b[0m\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": [
      "\u001b[33mCodeExecutor\u001b[0m (to CodeWriter):\n",
      "\n",
      "exitcode: 0 (execution succeeded)\n",
      "Code output: /Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[                       0%%                      ]/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[********************* 43%%                      ]  3 of 7 completed/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[**********************57%%*                     ]  4 of 7 completed/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[**********************71%%********              ]  5 of 7 completed/Users/ekzhu/miniconda3/envs/autogen/lib/python3.11/site-packages/yfinance/utils.py:775: FutureWarning: The 'unit' keyword in TimedeltaIndex construction is deprecated and will be removed in a future version. Use pd.to_timedelta instead.\n",
      "  df.index += _pd.TimedeltaIndex(dst_error_hours, 'h')\n",
      "[*********************100%%**********************]  7 of 7 completed\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeWriter\u001b[0m (to CodeExecutor):\n",
      "\n",
      "I see that the fetched data was successfully retrieved and processed. However, it looks like the result of the plot isn't visible, so we don't know whether the plot was generated successfully. Please run the code again and provide the output of the plot.\n",
      "\n",
      "If there are any issues or any other points you would like me to help with, let me know!\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeExecutor\u001b[0m (to CodeWriter):\n",
      "\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeWriter\u001b[0m (to CodeExecutor):\n",
      "\n",
      "I'm glad we were able to retrieve and process the data successfully. Please try running the last part of the code again to generate and display the plot:\n",
      "\n",
      "```python\n",
      "# Plot data\n",
      "plt.figure(figsize=(10,6))\n",
      "plt.barh(df['Company'], df['Market_Cap'], color='skyblue')\n",
      "plt.xlabel('Market Cap (in trillions)')\n",
      "plt.title('Market Caps of Top 7 Publicly Listed Companies')\n",
      "plt.gca().invert_yaxis()\n",
      "plt.show()\n",
      "```\n",
      "\n",
      "This section of the code creates a horizontal bar plot of the market capitalizations of the companies. The `plt.gca().invert_yaxis()` line is included to invert the y-axis, so the company with the highest market cap is at the top of the chart.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> EXECUTING CODE BLOCK (inferred language is python)...\u001b[0m\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": [
      "\u001b[33mCodeExecutor\u001b[0m (to CodeWriter):\n",
      "\n",
      "exitcode: 0 (execution succeeded)\n",
      "Code output: \n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeWriter\u001b[0m (to CodeExecutor):\n",
      "\n",
      "I see that the code has executed successfully, but unfortunately, the generated plot is not visible here. However, given that there are no errors, it's likely that the plot has been created as expected when you executed the code on your end.\n",
      "\n",
      "If you have any other questions related to this code or need further assistance with Python coding or data visualization, please let me know! I'm here to help.\n",
      "\n",
      "Otherwise, if this completes your initial request, I will end this task. Just let me know your decision.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeExecutor\u001b[0m (to CodeWriter):\n",
      "\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mCodeWriter\u001b[0m (to CodeExecutor):\n",
      "\n",
      "Alright. If you have any more questions regarding this task, or if you need help with other tasks in the future, don't hesitate to ask. Have a great day!\n",
      "\n",
      "'---TERMINATE---'\n",
      "\n",
      "--------------------------------------------------------------------------------\n"
     ]
    }
   ],
   "source": [
    "chat_result = code_executor_agent.initiate_chat(\n",
    "    code_writer_agent,\n",
    "    message=\"Create a plot showing the market caps of the top 7 publicly listed companies using data from Yahoo Finance.\",\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can see the plots are now displayed in the current notebook."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "autogen",
   "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": 2
}