LangChain_with_iris_dataset.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyMaKexPpsZxIVKqenXPFTj+",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/tolgakurtuluss/LangChain_chatwithcsv_irisdataset/blob/main/LangChain_with_iris_dataset.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "RRYSu48huSUW",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "33c66368-9d29-4fb4-dd04-0741bf3a95c2"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m477.2/477.2 KB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m70.3/70.3 KB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m27.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m264.6/264.6 KB\u001b[0m \u001b[31m22.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m158.8/158.8 KB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.2/114.2 KB\u001b[0m \u001b[31m12.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.1/49.1 KB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h"
          ]
        }
      ],
      "source": [
        "!pip -q install langchain openai\n",
        "!pip show langchain"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "\n",
        "os.environ[\"OPENAI_API_KEY\"] = \"sk-PLACEYOUROWNAPI\""
      ],
      "metadata": {
        "id": "H6WcxTXzQfG4"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "df = pd.read_csv('/content/iris.csv')"
      ],
      "metadata": {
        "id": "s0DT4CfVQfJX"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "Dyk1mJ3LQfMY",
        "outputId": "0fdfc425-4966-41f0-ba9f-bba714270b52"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   sepal.length  sepal.width  petal.length  petal.width variety\n",
              "0           5.1          3.5           1.4          0.2  Setosa\n",
              "1           4.9          3.0           1.4          0.2  Setosa\n",
              "2           4.7          3.2           1.3          0.2  Setosa\n",
              "3           4.6          3.1           1.5          0.2  Setosa\n",
              "4           5.0          3.6           1.4          0.2  Setosa"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-20b76e92-2d89-41e9-9a0c-38206d7e8ba6\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>sepal.length</th>\n",
              "      <th>sepal.width</th>\n",
              "      <th>petal.length</th>\n",
              "      <th>petal.width</th>\n",
              "      <th>variety</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>5.1</td>\n",
              "      <td>3.5</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Setosa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>4.9</td>\n",
              "      <td>3.0</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Setosa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>4.7</td>\n",
              "      <td>3.2</td>\n",
              "      <td>1.3</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Setosa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4.6</td>\n",
              "      <td>3.1</td>\n",
              "      <td>1.5</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Setosa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5.0</td>\n",
              "      <td>3.6</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "      <td>Setosa</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-20b76e92-2d89-41e9-9a0c-38206d7e8ba6')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-20b76e92-2d89-41e9-9a0c-38206d7e8ba6 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-20b76e92-2d89-41e9-9a0c-38206d7e8ba6');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from langchain.agents import create_csv_agent\n",
        "from langchain.llms import OpenAI"
      ],
      "metadata": {
        "id": "Xo4L6dRMQfOa"
      },
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "agent = create_csv_agent(OpenAI(temperature=0), \n",
        "                         '/content/iris.csv', \n",
        "                         verbose=True)"
      ],
      "metadata": {
        "id": "bjR5amWlQo7a"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "agent"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "iZY-gRExQo5f",
        "outputId": "b86ecde8-fd26-4519-beb9-d1eeb213a302"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "AgentExecutor(memory=None, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x7f94e0cc9610>, verbose=True, agent=ZeroShotAgent(llm_chain=LLMChain(memory=None, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x7f94e0cc9610>, verbose=False, prompt=PromptTemplate(input_variables=['input', 'agent_scratchpad'], output_parser=None, partial_variables={'df': '   sepal.length  sepal.width  petal.length  petal.width variety\\n0           5.1          3.5           1.4          0.2  Setosa\\n1           4.9          3.0           1.4          0.2  Setosa\\n2           4.7          3.2           1.3          0.2  Setosa\\n3           4.6          3.1           1.5          0.2  Setosa\\n4           5.0          3.6           1.4          0.2  Setosa'}, template='\\nYou are working with a pandas dataframe in Python. The name of the dataframe is `df`.\\nYou should use the tools below to answer the question posed of you:\\n\\npython_repl_ast: A Python shell. Use this to execute python commands. Input should be a valid python command. When using this tool, sometimes output is abbreviated - make sure it does not look abbreviated before using it in your answer.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [python_repl_ast]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\n\\nThis is the result of `print(df.head())`:\\n{df}\\n\\nBegin!\\nQuestion: {input}\\n{agent_scratchpad}', template_format='f-string', validate_template=True), llm=OpenAI(cache=None, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x7f94e0cc9610>, client=<class 'openai.api_resources.completion.Completion'>, model_name='text-davinci-003', temperature=0.0, max_tokens=256, top_p=1, frequency_penalty=0, presence_penalty=0, n=1, best_of=1, model_kwargs={}, openai_api_key=None, batch_size=20, request_timeout=None, logit_bias={}, max_retries=6, streaming=False), output_key='text'), allowed_tools=['python_repl_ast']), tools=[PythonAstREPLTool(name='python_repl_ast', description='A Python shell. Use this to execute python commands. Input should be a valid python command. When using this tool, sometimes output is abbreviated - make sure it does not look abbreviated before using it in your answer.', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x7f94e0cc9610>, globals={}, locals={'df':      sepal.length  sepal.width  petal.length  petal.width    variety\n",
              "0             5.1          3.5           1.4          0.2     Setosa\n",
              "1             4.9          3.0           1.4          0.2     Setosa\n",
              "2             4.7          3.2           1.3          0.2     Setosa\n",
              "3             4.6          3.1           1.5          0.2     Setosa\n",
              "4             5.0          3.6           1.4          0.2     Setosa\n",
              "..            ...          ...           ...          ...        ...\n",
              "145           6.7          3.0           5.2          2.3  Virginica\n",
              "146           6.3          2.5           5.0          1.9  Virginica\n",
              "147           6.5          3.0           5.2          2.0  Virginica\n",
              "148           6.2          3.4           5.4          2.3  Virginica\n",
              "149           5.9          3.0           5.1          1.8  Virginica\n",
              "\n",
              "[150 rows x 5 columns]})], return_intermediate_steps=False, max_iterations=15, early_stopping_method='force')"
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.agent.llm_chain.prompt.template"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 70
        },
        "id": "zZfdJETYQo3f",
        "outputId": "9aa556cc-1877-4595-d7cc-7d45dd464b43"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'\\nYou are working with a pandas dataframe in Python. The name of the dataframe is `df`.\\nYou should use the tools below to answer the question posed of you:\\n\\npython_repl_ast: A Python shell. Use this to execute python commands. Input should be a valid python command. When using this tool, sometimes output is abbreviated - make sure it does not look abbreviated before using it in your answer.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [python_repl_ast]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\n\\nThis is the result of `print(df.head())`:\\n{df}\\n\\nBegin!\\nQuestion: {input}\\n{agent_scratchpad}'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.run(\"Explain this dataset statistically with mentioning outliers, mean and unique features of values.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "fbswp0LkQo1g",
        "outputId": "0dedabe6-1012-498c-814b-adf3e9439749"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mThought: I should look at the data to get an understanding of the values.\n",
            "Action: python_repl_ast\n",
            "Action Input: df.describe()\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m       sepal.length  sepal.width  petal.length  petal.width\n",
            "count    150.000000   150.000000    150.000000   150.000000\n",
            "mean       5.843333     3.057333      3.758000     1.199333\n",
            "std        0.828066     0.435866      1.765298     0.762238\n",
            "min        4.300000     2.000000      1.000000     0.100000\n",
            "25%        5.100000     2.800000      1.600000     0.300000\n",
            "50%        5.800000     3.000000      4.350000     1.300000\n",
            "75%        6.400000     3.300000      5.100000     1.800000\n",
            "max        7.900000     4.400000      6.900000     2.500000\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I now have an understanding of the data.\n",
            "Final Answer: This dataset contains 150 observations of 4 features (sepal.length, sepal.width, petal.length, petal.width). The mean values for each feature are 5.84 for sepal.length, 3.06 for sepal.width, 3.76 for petal.length, and 1.20 for petal.width. The minimum and maximum values for each feature are 4.30 and 7.90 for sepal.length, 2.00 and 4.40 for sepal.width, 1.00 and 6.90 for petal.length, and 0.10 and 2.50 for petal.width, respectively. There may be outliers in the dataset, as the maximum values for each feature are significantly higher than the 75th percentile values.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'This dataset contains 150 observations of 4 features (sepal.length, sepal.width, petal.length, petal.width). The mean values for each feature are 5.84 for sepal.length, 3.06 for sepal.width, 3.76 for petal.length, and 1.20 for petal.width. The minimum and maximum values for each feature are 4.30 and 7.90 for sepal.length, 2.00 and 4.40 for sepal.width, 1.00 and 6.90 for petal.length, and 0.10 and 2.50 for petal.width, respectively. There may be outliers in the dataset, as the maximum values for each feature are significantly higher than the 75th percentile values.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.run(\"Do a detailed analysis for explaining the key points of 4 features in this dataset.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 524
        },
        "id": "24Xve46XQozo",
        "outputId": "a0329e22-e974-45a9-e876-dcd5fd58e97a"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mThought: I should look at the data and see what I can find.\n",
            "Action: python_repl_ast\n",
            "Action Input: df.describe()\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m       sepal.length  sepal.width  petal.length  petal.width\n",
            "count    150.000000   150.000000    150.000000   150.000000\n",
            "mean       5.843333     3.057333      3.758000     1.199333\n",
            "std        0.828066     0.435866      1.765298     0.762238\n",
            "min        4.300000     2.000000      1.000000     0.100000\n",
            "25%        5.100000     2.800000      1.600000     0.300000\n",
            "50%        5.800000     3.000000      4.350000     1.300000\n",
            "75%        6.400000     3.300000      5.100000     1.800000\n",
            "max        7.900000     4.400000      6.900000     2.500000\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I can see the mean, min, max, and quartiles for each feature.\n",
            "Action: python_repl_ast\n",
            "Action Input: df.variety.value_counts()\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3mSetosa        50\n",
            "Versicolor    50\n",
            "Virginica     50\n",
            "Name: variety, dtype: int64\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I can also see the number of each variety.\n",
            "Final Answer: The sepal length has a mean of 5.84, a min of 4.3, and a max of 7.9. The sepal width has a mean of 3.06, a min of 2, and a max of 4.4. The petal length has a mean of 3.76, a min of 1, and a max of 6.9. The petal width has a mean of 1.2, a min of 0.1, and a max of 2.5. There are 50 of each variety in the dataset.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'The sepal length has a mean of 5.84, a min of 4.3, and a max of 7.9. The sepal width has a mean of 3.06, a min of 2, and a max of 4.4. The petal length has a mean of 3.76, a min of 1, and a max of 6.9. The petal width has a mean of 1.2, a min of 0.1, and a max of 2.5. There are 50 of each variety in the dataset.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "agent.run(\"Do a correlation test for 4 features and explain their significance.\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 315
        },
        "id": "sSnWB0-uQoxn",
        "outputId": "68de3421-9d34-4de4-9694-7edc4f47c0e4"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "\n",
            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
            "\u001b[32;1m\u001b[1;3mThought: I need to calculate the correlation between the 4 features.\n",
            "Action: python_repl_ast\n",
            "Action Input: df.corr()\u001b[0m\n",
            "Observation: \u001b[36;1m\u001b[1;3m              sepal.length  sepal.width  petal.length  petal.width\n",
            "sepal.length      1.000000    -0.117570      0.871754     0.817941\n",
            "sepal.width      -0.117570     1.000000     -0.428440    -0.366126\n",
            "petal.length      0.871754    -0.428440      1.000000     0.962865\n",
            "petal.width       0.817941    -0.366126      0.962865     1.000000\u001b[0m\n",
            "Thought:\u001b[32;1m\u001b[1;3m I can interpret the correlation values.\n",
            "Final Answer: The correlation test shows that sepal length and petal length have a strong positive correlation (0.871754), while sepal width and petal width have a moderate negative correlation (-0.366126). This suggests that sepal length and petal length are related, while sepal width and petal width are inversely related.\u001b[0m\n",
            "\n",
            "\u001b[1m> Finished chain.\u001b[0m\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'The correlation test shows that sepal length and petal length have a strong positive correlation (0.871754), while sepal width and petal width have a moderate negative correlation (-0.366126). This suggests that sepal length and petal length are related, while sepal width and petal width are inversely related.'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "Ua2xcQtMQou_"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "f8pgW-ylQosA"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "7htsWJ-UQopo"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}