{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "c81da886",
   "metadata": {},
   "source": [
    "# Pandas Dataframe\n",
    "\n",
    "This notebook shows how to use agents to interact with a `Pandas DataFrame`. It is mostly optimized for question answering.\n",
    "\n",
    "**NOTE: this agent calls the `Python` agent under the hood, which executes LLM generated Python code - this can be bad if the LLM generated Python code is harmful. Use cautiously.**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "0cdd9bf5",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.agents import create_pandas_dataframe_agent\n",
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.agents.agent_types import AgentType"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "051ebe84",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import OpenAI\n",
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv(\"titanic.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a62858e2",
   "metadata": {},
   "source": [
    "## Using `ZERO_SHOT_REACT_DESCRIPTION`\n",
    "\n",
    "This shows how to initialize the agent using the `ZERO_SHOT_REACT_DESCRIPTION` agent type. Note that this is an alternative to the above."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4185ff46",
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = create_pandas_dataframe_agent(OpenAI(temperature=0), df, verbose=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7233ab56",
   "metadata": {},
   "source": [
    "## Using OpenAI Functions\n",
    "\n",
    "This shows how to initialize the agent using the OPENAI_FUNCTIONS agent type. Note that this is an alternative to the above."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a8ea710e",
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = create_pandas_dataframe_agent(\n",
    "    ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-0613\"),\n",
    "    df,\n",
    "    verbose=True,\n",
    "    agent_type=AgentType.OPENAI_FUNCTIONS,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a9207a2e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new  chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m\n",
      "Invoking: `python_repl_ast` with `df.shape[0]`\n",
      "\n",
      "\n",
      "\u001b[0m\u001b[36;1m\u001b[1;3m891\u001b[0m\u001b[32;1m\u001b[1;3mThere are 891 rows in the dataframe.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'There are 891 rows in the dataframe.'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"how many rows are there?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "bd43617c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to count the number of people with more than 3 siblings\n",
      "Action: python_repl_ast\n",
      "Action Input: df[df['SibSp'] > 3].shape[0]\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m30\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: 30 people have more than 3 siblings.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'30 people have more than 3 siblings.'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"how many people have more than 3 siblings\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "94e64b58",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to calculate the average age first\n",
      "Action: python_repl_ast\n",
      "Action Input: df['Age'].mean()\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m29.69911764705882\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now need to calculate the square root of the average age\n",
      "Action: python_repl_ast\n",
      "Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3mNameError(\"name 'math' is not defined\")\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I need to import the math library\n",
      "Action: python_repl_ast\n",
      "Action Input: import math\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now need to calculate the square root of the average age\n",
      "Action: python_repl_ast\n",
      "Action Input: math.sqrt(df['Age'].mean())\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m5.449689683556195\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: The square root of the average age is 5.449689683556195.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'The square root of the average age is 5.449689683556195.'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent.run(\"whats the square root of the average age?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4bc0584",
   "metadata": {},
   "source": [
    "## Multi DataFrame Example\n",
    "\n",
    "This next part shows how the agent can interact with multiple dataframes passed in as a list."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "42a15bd9",
   "metadata": {},
   "outputs": [],
   "source": [
    "df1 = df.copy()\n",
    "df1[\"Age\"] = df1[\"Age\"].fillna(df1[\"Age\"].mean())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "eba13b4d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mThought: I need to compare the age columns in both dataframes\n",
      "Action: python_repl_ast\n",
      "Action Input: len(df1[df1['Age'] != df2['Age']])\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m177\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
      "Final Answer: 177 rows in the age column are different.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'177 rows in the age column are different.'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent = create_pandas_dataframe_agent(OpenAI(temperature=0), [df, df1], verbose=True)\n",
    "agent.run(\"how many rows in the age column are different?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "60d08a56",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}