[PMPG_CH01].ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "[PMPG_CH01].ipynb",
      "provenance": [],
      "collapsed_sections": [
        "P_HxX4dhdjvD"
      ]
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "3IlM53RiVtpw"
      },
      "source": [
        "***CH01. 파이썬 기반의 머신러닝과 생태계 이해***\r\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "oIFPMOGAijU9"
      },
      "source": [
        "# **01.머신러닝의 개념**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FHpX0PexV9u1"
      },
      "source": [
        "- 머신러닝의 개념 : 일반적으로는 애플리케이션을 수정하지 않고도 데이터를 기반으로 패턴을 학습하고 결과를 예측하는 알고리즘 기법을 통칭합니다.\r\n",
        "\r\n",
        "EX) 스팸메일분류 : 단순히 특정 단어가 메일 내용에 포함되어있다고 이를 스팸메일로 분류할 수는 없습니다. 언어란 문맥에 의해 판단해야 하므로 인간의 언어에서 이러한 패턴을 규정하기란 매우 어렵다\r\n",
        "\r\n",
        "위 문제를 해결 <- 머신러닝은 이러한 문제를 데이터 기반으로 숨겨진 패턴을 인지해 해결 (통계적인 신뢰도를 강화하고 예측 오류를 최소화하기 위해 다양한 수학적 기법을 적용)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "TyioVgyyXzVI"
      },
      "source": [
        "**머신러닝의 분류**\r\n",
        "1. 지도학습\r\n",
        "* *분류* \r\n",
        "* *회귀*\r\n",
        "* 추천 시스템 \r\n",
        "* 시각/음성 감지/인지\r\n",
        "* 텍스트 분석 NLP\r\n",
        "\r\n",
        "2. 비지도 학습\r\n",
        "* 클러스터링\r\n",
        "* 차원축소\r\n",
        "* 강화학습\r\n",
        "\r\n",
        "3. 강화학습\r\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LUHTtcTKaiHu"
      },
      "source": [
        "**머신러닝의 단점**\r\n",
        "- 데이터에 매우 의존적, 즉 가비지 인(Garbage In), 가비지 아웃(Garbage Out), 즉 좋은 품질의 데이터를 갖추지 못한다면 머신러닝의 수행 결과도 좋을 수 없습니다.\r\n",
        "- 머신러닝을 이용해 데이터만 집어넣으면 자동으로 최적화된 결과를 도출할 거라는 믿음은 환상 <- 이 말은, 즉 데이터가 기본 베이스!"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "P_HxX4dhdjvD"
      },
      "source": [
        "# ***02. 파이썬 머신러닝 생태계를 구성하는 주요 패키지***\r\n",
        "* 머신러닝 패키지 : 사이킷런 Scikit-Learn(머신러닝의 가장 대표적인 패키지), 그 외 딥러닝의 뛰어난 활약으로 텐서플로, 케라스 등\r\n",
        "\r\n",
        "\r\n",
        "```\r\n",
        "# from Scikit.learn_selection import train_test_split\r\n",
        "```\r\n",
        "\r\n",
        "\r\n",
        "\r\n",
        "* 행렬/선형대수/통계 패키지 : 넘파이 Numpy\r\n",
        "\r\n",
        "\r\n",
        "```\r\n",
        "# import numpy\r\n",
        "```\r\n",
        "\r\n",
        "\r\n",
        "\r\n",
        "* 데이터 핸들링 : 판다스 Pandas (일반적인 데이터 처리) > 넘파이 Numpy (행렬 기반의 데이터 처리 특화)\r\n",
        "\r\n",
        "```\r\n",
        "# import pandas\r\n",
        "```\r\n",
        "\r\n",
        "* 시각화 : 맷플롯립 Matplotlib (코드가 길어져서) 이를 보완 -> 시본 Seaborn\r\n",
        "\r\n",
        "```\r\n",
        "# import matplotlib.pyplot\r\n",
        "```\r\n",
        "```\r\n",
        "# import seaborn\r\n",
        "```"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8RcLFPUDfe4D"
      },
      "source": [
        "# ***03. 넘파이 Numpy***"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3RRYkuSsWUdd"
      },
      "source": [
        "import numpy as np"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "su0hvs8oi0Sf"
      },
      "source": [
        "- 넘파이의 기반 데이터 타입은 ndarray입니다.\r\n",
        "- ndarray를 이용해 넘파이에서 다차원(Multi-dimension) 배열을 쉽게 생성하고 다양한 연산을 수행할 수 있다."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RXpPd_CbkJPT"
      },
      "source": [
        "- np.array() 사용"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "n34JvrUzizbY",
        "outputId": "9b64f2ca-1f68-428a-a47a-68c34b82fa13"
      },
      "source": [
        "array1 = np.array([1,2,3])\r\n",
        "print('array1 type :',type(array1))\r\n",
        "print('array1 array 형태 :',array1.shape)\r\n",
        "print(array1)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "array1 type : <class 'numpy.ndarray'>\n",
            "array1 array 형태 : (3,)\n",
            "[1 2 3]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lpt4cHR2jUqG",
        "outputId": "3bdd9e26-88d2-47f5-d3eb-b6bad25e56cc"
      },
      "source": [
        "array2 = np.array([[1,2,3],[2,3,4]])\r\n",
        "print('array2 type :',type(array2))\r\n",
        "print('array2 array 형태 :',array2.shape)\r\n",
        "print(array2)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "array2 type : <class 'numpy.ndarray'>\n",
            "array2 array 형태 : (2, 3)\n",
            "[[1 2 3]\n",
            " [2 3 4]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YKmnJrR0j5BB",
        "outputId": "7c3763e0-b498-47eb-da8e-85c1b24a4eea"
      },
      "source": [
        "array3 = np.array([[1,2,3]])\r\n",
        "print('array3 type :',type(array3))\r\n",
        "print('array3 array 형태 :',array3.shape)\r\n",
        "print(array3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "array3 type : <class 'numpy.ndarray'>\n",
            "array3 array 형태 : (1, 3)\n",
            "[[1 2 3]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CYdbIoZZnTlX"
      },
      "source": [
        "차원(dimension)의 줄임말 dim"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ZcnSwLdkliWI"
      },
      "source": [
        "- 각 array의 차원을 ndarray.ndim을 이용해 차원 수 확인"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BsS8UOeskCTa",
        "outputId": "bc235eec-28a5-4a9d-8b01-ede0b29a07c0"
      },
      "source": [
        "print('array1 : {:0}차원, array2 : {:1}차원, array3 : {:2}차원'.format(array1.ndim,array2.ndim,array3.ndim))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "array1 : 1차원, array2 : 2차원, array3 :  2차원\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ra683tlUnAJM",
        "outputId": "05585efb-5947-429f-833f-8a66140174f4"
      },
      "source": [
        "list1 = [1, 2, 3]\r\n",
        "list1\r\n",
        "print(type(list1))\r\n",
        "array1 = np.array(list1)\r\n",
        "array1\r\n",
        "print(type(array1))\r\n",
        "print(array1, array1.dtype)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'list'>\n",
            "<class 'numpy.ndarray'>\n",
            "[1 2 3] int64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "j33OAeDqnuGV",
        "outputId": "01852bbf-27de-4aa6-f525-b372635c9cdf"
      },
      "source": [
        "list2 = [1,2,'test']\r\n",
        "list2\r\n",
        "array2 = np.array(list2)\r\n",
        "array2\r\n",
        "print(array2.dtype) # 데이터 타입이 더 큰 데이터 타입으로 변환 따라서 int형이 유니 코드 문자열 값으로 변환 <U21\r\n",
        "list3 = [1,2,3.0]\r\n",
        "array3 = np.array(list3)\r\n",
        "print(array3.dtype)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<U21\n",
            "float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zMyW9nhsowUX"
      },
      "source": [
        "- ndarray 내 데이터값의 타입 변경도 astype() 메서드를 통해 변경 가능\r\n",
        "- 왜 변경 하는지? : 머신러닝은 메모리 부족으로 수행이 느려지거나 오류 발생\r\n",
        "- 따라서 데이터 타입을 float -> int 형으로 변환하여 메모리를 절약"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "75c1tkNYoCar",
        "outputId": "db565463-65a7-4772-9616-20552f8cb673"
      },
      "source": [
        "array_int = np.array([1,2,3])\r\n",
        "print(array_int.dtype)\r\n",
        "array_float = array_int.astype('float')\r\n",
        "print(array_float.dtype)\r\n",
        "\r\n",
        "array_int1 = array_float.astype('int')\r\n",
        "print(array_int1.dtype)\r\n",
        "\r\n",
        "array_float1 = np.array([1.1,2.1,3.1])\r\n",
        "print(array_float1,array_float1.dtype)\r\n",
        "array_int2 = array_float1.astype('int')\r\n",
        "print(array_int2,array_int2.dtype)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "int64\n",
            "float64\n",
            "int64\n",
            "[1.1 2.1 3.1] float64\n",
            "[1 2 3] int64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "U10I06p6qZXI"
      },
      "source": [
        "- ndarray를 편리하게 생성하기 - arange, zeros, ones"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5MqaX22PpTyX",
        "outputId": "848e33f6-394b-4a4e-a073-fae1af6d55f1"
      },
      "source": [
        "# np.arange()\r\n",
        "sequence_array = np.arange(10)\r\n",
        "print(sequence_array)\r\n",
        "print(sequence_array.dtype,sequence_array.shape)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[0 1 2 3 4 5 6 7 8 9]\n",
            "int64 (10,)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "s6racblsrAvT",
        "outputId": "8c37eb04-a999-43b3-bce6-01233effd5b3"
      },
      "source": [
        "# np.zeros()\r\n",
        "zero_array = np.zeros((3,2),dtype ='int32') # 튜플 형태로 값을 입력 / dtype을 정해주지 않으면 default값으로 float64 형의 데이터로 채워짐\r\n",
        "print(zero_array)\r\n",
        "print(zero_array.dtype,zero_array.shape)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0 0]\n",
            " [0 0]\n",
            " [0 0]]\n",
            "int32 (3, 2)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0jFZ7SAsrgJo",
        "outputId": "ae30bf02-f26f-4f35-cee0-82db3f80d835"
      },
      "source": [
        "# np.ones()\r\n",
        "one_array = np.ones((3,2)) # np.zeros와 동일 dtype을 정해주지 않았기에 float형태로 채워졌다.\r\n",
        "print(one_array)\r\n",
        "print(one_array.dtype,one_array.shape)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[1. 1.]\n",
            " [1. 1.]\n",
            " [1. 1.]]\n",
            "float64 (3, 2)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "V0Y7h0nosXmG"
      },
      "source": [
        " - ndarray의 차원과 크기를 변경하는 reshape()"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dH5tzueOr_Dy",
        "outputId": "e94f8363-6252-4a20-8e79-d5ddd92003a2"
      },
      "source": [
        "array1 = np.arange(10)\r\n",
        "print('array1 :',array1)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "array1 : [0 1 2 3 4 5 6 7 8 9]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Di1wTU_Fsj1K",
        "outputId": "8febf6ca-f306-4cc3-ce96-0fc30628846f"
      },
      "source": [
        "array2 = array1.reshape(2,5)\r\n",
        "print('array2 :\\n',array2)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "array2 :\n",
            " [[0 1 2 3 4]\n",
            " [5 6 7 8 9]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZNM7jqLcs8av",
        "outputId": "1bc5be0d-14fd-425f-aae1-ce067291cc5f"
      },
      "source": [
        "array3 = array1.reshape(5,2)\r\n",
        "print('array3 :\\n',array3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "array3 :\n",
            " [[0 1]\n",
            " [2 3]\n",
            " [4 5]\n",
            " [6 7]\n",
            " [8 9]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "l_m2gb9rtefx"
      },
      "source": [
        "- reshape()에 -1값을 인자로 적용한 경우\r\n",
        "- -1을 적용하면 ndarray와 호환되는 새로운 shape로 변환"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mBIDCwmutHJM",
        "outputId": "9a826966-c334-4f21-b310-7443e3e02585"
      },
      "source": [
        "array1 = np.arange(10)\r\n",
        "array1\r\n",
        "array2 = array1.reshape(-1,5) # -1의 의미 : 고정된 5개의 컬럼에 맞게 로우를 자동 변환\r\n",
        "print(array2)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0 1 2 3 4]\n",
            " [5 6 7 8 9]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2ZOhd9enuT_M"
      },
      "source": [
        "- -1 인자는 reshape(-1,1)와 같은 형태로 자주 사용된다. 무조건 2차원이고, 여러개의 넘파이 ndarray는 stack이나 concatㅇ로 결합할때 각각의 ndarray형태를 통일해 유용하게 사용됩니다."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yV08Zm2Au0b5"
      },
      "source": [
        "- 다음 예제는 reshape(-1,1)을 이용해 3차원을 2차원으로, 1차원을 2차원으로 변경합니다. (adarray는 tolist() 메서드를 통해서 리스트 자료형으로 변환할 수 있다)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "as329AxYtxRQ",
        "outputId": "5bfa944c-fb60-4da3-e3a9-7426ff2888e0"
      },
      "source": [
        "array1 = np.arange(8)\r\n",
        "print(array1,array1.shape)\r\n",
        "array1_3d = array1.reshape((2,2,2)) # reshape()메서드를 통해 3차원으로 변경\r\n",
        "print(array1_3d)\r\n",
        "print(array1_3d.shape)\r\n",
        "array1_list = array1_3d.tolist() # 리스트 자료형으로 변환\r\n",
        "print(array1_list)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[0 1 2 3 4 5 6 7] (8,)\n",
            "[[[0 1]\n",
            "  [2 3]]\n",
            "\n",
            " [[4 5]\n",
            "  [6 7]]]\n",
            "(2, 2, 2)\n",
            "[[[0, 1], [2, 3]], [[4, 5], [6, 7]]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Jn2_z3r3vYe1",
        "outputId": "8b38f0db-2892-466e-d064-d6daba9742d2"
      },
      "source": [
        "array5 = array1_3d.reshape(-1,1)\r\n",
        "print(array5,array5.shape)\r\n",
        "array5_list = array5.tolist()\r\n",
        "print(array5_list)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0]\n",
            " [1]\n",
            " [2]\n",
            " [3]\n",
            " [4]\n",
            " [5]\n",
            " [6]\n",
            " [7]] (8, 1)\n",
            "[[0], [1], [2], [3], [4], [5], [6], [7]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nDQDX0hAv9v0",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "acc2e3f9-8789-4843-c74c-1378fbfb901f"
      },
      "source": [
        "array6 = array1.reshape(-1,1)\r\n",
        "print(array6,array6.shape)\r\n",
        "array6_list = array6.tolist()\r\n",
        "print(array6_list)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0]\n",
            " [1]\n",
            " [2]\n",
            " [3]\n",
            " [4]\n",
            " [5]\n",
            " [6]\n",
            " [7]] (8, 1)\n",
            "[[0], [1], [2], [3], [4], [5], [6], [7]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ojLFSx_Z3GjW"
      },
      "source": [
        "넘파이의 adarray의 데이터 세트 선택하기 - 인덱싱(indexing)\r\n",
        "1. 특정한 데이터만 추출\r\n",
        "2. 슬라이싱\r\n",
        "3. 팬시 인덱싱(Fancy Indexing)\r\n",
        "4. 불린 인덱싱(Bloolean Indexing)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "KjFyMTrH3oyX"
      },
      "source": [
        "**1. 특정한 데이터만 추출**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YUb8vtDLz96U",
        "outputId": "6d0e6b94-4f44-4002-d2c4-d7a7faf21be9"
      },
      "source": [
        "# 1부터 9까지의 1차원 ndarray 생성\r\n",
        "array1 = np.arange(start=1,stop=10)\r\n",
        "print(array1, array1.shape)\r\n",
        "# index는 0부터 시작하므로 array1[2]는 세번째 index 위치의 데이터값을 의미\r\n",
        "print('array1[2] 값:',array1[2])\r\n",
        "print(type(array1[2]))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[1 2 3 4 5 6 7 8 9] (9,)\n",
            "array1[2] 값: 3\n",
            "<class 'numpy.int64'>\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "m867bBlY5BoJ"
      },
      "source": [
        "- 인덱스를 이용해 수정도 가능하다."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Yol9jT3w4V7I",
        "outputId": "e85f35e4-a0a2-495c-80d4-6f234a3f0bf6"
      },
      "source": [
        "array1[0] = 9\r\n",
        "array1[8] = 0\r\n",
        "print(array1)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[9 2 3 4 5 6 7 8 0]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bRl9YHd85Kb3",
        "outputId": "01f5e82f-f65c-467d-f180-efcd4c8c5dc2"
      },
      "source": [
        "array1d = np.arange(start=1,stop=10)\r\n",
        "array1d\r\n",
        "array2d = array1d.reshape(-1,3)\r\n",
        "print(array2d)\r\n",
        "\r\n",
        "print('(row=0,col=0 index 가리키는 값 :',array2d[0][0])\r\n",
        "print('(row=0,col=1 index 가리키는 값 :',array2d[0][1])\r\n",
        "print('(row=1,col=0 index 가리키는 값 :',array2d[1,0])\r\n",
        "print('(row=2,col=2 index 가리키는 값 :',array2d[2,2])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[1 2 3]\n",
            " [4 5 6]\n",
            " [7 8 9]]\n",
            "(row=0,col=0 index 가리키는 값 : 1\n",
            "(row=0,col=1 index 가리키는 값 : 2\n",
            "(row=1,col=0 index 가리키는 값 : 4\n",
            "(row=2,col=2 index 가리키는 값 : 9\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tgje-myk-MoW"
      },
      "source": [
        "**2. 슬라이싱**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "U7A5_2Wc5UwH",
        "outputId": "34bb8930-c186-49e3-e80b-bfc37ab36f9c"
      },
      "source": [
        "array1 = np.arange(start=1, stop=10)\r\n",
        "array1\r\n",
        "array4 = array1[:3]\r\n",
        "print(array4)\r\n",
        "\r\n",
        "array5 = array1[3:]\r\n",
        "print(array5)\r\n",
        "\r\n",
        "array6 = array1[:]\r\n",
        "print(array6)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[1 2 3]\n",
            "[4 5 6 7 8 9]\n",
            "[1 2 3 4 5 6 7 8 9]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ERoyiZ8a-XQf",
        "outputId": "1a6ddd6f-b480-4a88-daa8-ac7d74f0c6b2"
      },
      "source": [
        "array1d = np.arange(start=1, stop=10)\r\n",
        "array2d = array1d.reshape(3,3)\r\n",
        "print(array2d)\r\n",
        "\r\n",
        "print('array2d[0:2][0:2] :\\n',array2d[0:2,0:2])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[1 2 3]\n",
            " [4 5 6]\n",
            " [7 8 9]]\n",
            "array2d[0:2][0:2] :\n",
            " [[1 2]\n",
            " [4 5]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ZTo3kWwLAPft"
      },
      "source": [
        "**3. 팬시 인덱싱**\r\n",
        "- 팬시 인덱싱은 리스트나 ndarray로 인덱스 집합을 지정하면 해당 위치의 인덱스에 해당하는 ndarray를 반환하는 인덱싱 방식"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2EElap5a_EFk",
        "outputId": "e7814c0d-667c-4d25-8cbf-e05079ebfa2e"
      },
      "source": [
        "array1d = np.arange(start=1, stop=10)\r\n",
        "array2d = array1d.reshape(3,3)\r\n",
        "print(array2d)\r\n",
        "\r\n",
        "# 팬시 인덱싱\r\n",
        "print(array2d[[0,1],2])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[1 2 3]\n",
            " [4 5 6]\n",
            " [7 8 9]]\n",
            "[3 6]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VUEhlveABS5n"
      },
      "source": [
        "**4. 불린 인덱싱**\r\n",
        "- 불린 인덱싱은 조건 필터링과 검색을 동시에 할 수 있기에 자주 사용됨\r\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eUEqEcUNA6xR",
        "outputId": "3cd0b320-af18-4cc6-fe5c-2e83830c4f70"
      },
      "source": [
        "array1d = np.arange(start=1, stop=10)\r\n",
        "array1d\r\n",
        "array3 = array1d[array1d>5] # array1d > 5 인 조건\r\n",
        "print(array3)\r\n",
        "print(array1d>5)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[6 7 8 9]\n",
            "[False False False False False  True  True  True  True]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AMU4s0ajBi2B",
        "outputId": "83c6dba4-bd42-4791-e119-a9cccdb43414"
      },
      "source": [
        "# 또 다른 예시\r\n",
        "boolean_indexes = np.array([False, False, False, False, False,  True,  True,  True,  True])\r\n",
        "boolean_indexes\r\n",
        "array3 = array1d[boolean_indexes]\r\n",
        "print(array3)\r\n",
        "\r\n",
        "indexes = np.array([5,6,7,8])\r\n",
        "# print(array1d)\r\n",
        "print(array1d[indexes])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[6 7 8 9]\n",
            "[6 7 8 9]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LR07U8TFC6d7"
      },
      "source": [
        "**- 행렬의 정렬 - sort()와 argsort()**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "y0i66iUUG-JN"
      },
      "source": [
        "sort"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wp8WGiOrF2cr"
      },
      "source": [
        "- 넘파이의 행렬 정렬은 np.sort()와 같이 넘파이에서 sort()를 호출하는 방식과 ndarray.sort()와 같이 행렬에서 sort()를 호출하는 방식이 있다.\r\n",
        "- 두 방식의 차이 : np.sort의 경우 원 행렬은 그대로 유지한 채 원 행렬의 정렬된 행렬을 반환하며, ndarray.sort()의 경우 원 행렬 자체를 정렬한 형태로 변환하며 반환 값은 None"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3OpNFQekCXvY",
        "outputId": "12d1e83b-9eb0-42e0-ff49-ec06a727197f"
      },
      "source": [
        "#np.array()\r\n",
        "org_array = np.array([3,1,9,5])\r\n",
        "sort_array1 = np.sort(org_array)\r\n",
        "print('원본 행렬 :',org_array) # 원본 행렬은 그대로\r\n",
        "print('정렬 행렬 :',sort_array1) # 정렬된 행렬 반환"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "원본 행렬 : [3 1 9 5]\n",
            "정렬 행렬 : [1 3 5 9]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6Y9jULzUHOze",
        "outputId": "d669857c-589e-4646-f44f-bd335968a619"
      },
      "source": [
        "# ndarray.sort()\r\n",
        "org_array = np.array([3,1,9,5])\r\n",
        "sort_array1 = org_array.sort()\r\n",
        "print('원본 행렬 :',org_array) # 원본 행렬이 정렬\r\n",
        "print('정렬 행렬 :',sort_array1) # None 값 반환"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "원본 행렬 : [1 3 5 9]\n",
            "정렬 행렬 : None\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "A7FNP3EQIK6p"
      },
      "source": [
        "- 내림차순으로 정렬하기\r\n",
        "- 기본 np.sort() , ndarray.sort() 는 오름차순 정렬"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AKA3wlwqHt4d",
        "outputId": "aca73fc7-abc5-40e1-de33-9533cd9c6772"
      },
      "source": [
        "sort_array_desc = np.sort(org_array)[::-1] # np.sort()[::-1] 형태\r\n",
        "print(sort_array_desc)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[9 5 3 1]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cFWlzrDoInGZ",
        "outputId": "ebbf6c22-9cb7-4ce7-f6d7-97bc629a7582"
      },
      "source": [
        "array2d = np.array([[8,12],[7,1]])\r\n",
        "print(array2d)\r\n",
        "print(\"\\n\")\r\n",
        "# 로우 방향으로 정렬\r\n",
        "sort_array2d_axis0 = np.sort(array2d,axis=0)\r\n",
        "print(sort_array2d_axis0)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[ 8 12]\n",
            " [ 7  1]]\n",
            "\n",
            "\n",
            "[[ 7  1]\n",
            " [ 8 12]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cFtm__RUI1LH",
        "outputId": "cfea2406-cbf4-4cdc-b115-5ef344ebe2e4"
      },
      "source": [
        "#컬럼 방향으로 정렬\r\n",
        "sort_array2d_axis1 = np.sort(array2d,axis=1)\r\n",
        "print(sort_array2d_axis1)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[ 8 12]\n",
            " [ 1  7]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "O6FaP5V9KKus"
      },
      "source": [
        "argsort"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "QiIg68hSKMpH"
      },
      "source": [
        "- 원본 행렬이 정렬되었을 때 기존 원본 행렬의 원소에 대한 인덱스를 필요로 할 때 사용\r\n",
        "- 즉 원소의 값이 아닌 인덱스 번호가 필요할 때(sort는 원소의 값/ argsort는 원소의 인덱스 번호)\r\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MKT8PK3hJMnd",
        "outputId": "92ed0b96-0fca-46db-b5c3-cac1951a64c0"
      },
      "source": [
        "org_array = np.array([3,1,9,5])\r\n",
        "\r\n",
        "sort_indices = np.argsort(org_array) #내림차순도 마찬가지 np.argsort(org_array)[::-1] -> [2,3,0,1]\r\n",
        "print(sort_indices)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[1 0 3 2]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "V1wxRDbIKtYe",
        "outputId": "14570a55-df53-4f45-b333-42aa1c4df6e3"
      },
      "source": [
        "# 예시 - 성적 오름차순으로 이름 출력\r\n",
        "import numpy as np\r\n",
        "name_array = np.array(['John','Mike','Sarch'])\r\n",
        "score_array = np.array([78,95,84])\r\n",
        "sort_indices = np.argsort(score_array)\r\n",
        "print(sort_indices)\r\n",
        "print(name_array[sort_indices])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[0 2 1]\n",
            "['John' 'Sarch' 'Mike']\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-2b542NQMQWb"
      },
      "source": [
        "**선형대수 연산 - 행렬 내적과 전치 행렬 구하기**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "x9yCs5W3NVTj"
      },
      "source": [
        "- 내적 행렬 : 두 행렬의 곱"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ayBbKdlTLRf-",
        "outputId": "71009a7b-76c5-4eb5-da0f-3af700c1aacc"
      },
      "source": [
        "# 행렬 내적 - np.dot() 메서드 사용\r\n",
        "A = np.array([[1,2,3],[4,5,6]])\r\n",
        "B = np.array([[7,8],[9,10],[11,12]])\r\n",
        "dot_product = np.dot(A,B)\r\n",
        "print(dot_product)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[ 58  64]\n",
            " [139 154]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wovW2Pw2NOhn"
      },
      "source": [
        "- 전치 행렬 : 행과 열 위치를 교환한 원소로 구성한 행렬 "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jX-7-N3RMwsR",
        "outputId": "5020c2d5-8f53-4176-945c-cbd180fd5cd9"
      },
      "source": [
        "# 전치 행렬 - np.transpose() 메서드 사용\r\n",
        "A\r\n",
        "transpose_product = np.transpose(A)\r\n",
        "print(transpose_product)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[1 4]\n",
            " [2 5]\n",
            " [3 6]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Pwd1_CRzOjVV"
      },
      "source": [
        "# ***04. 데이터 핸들링 - 판다스 Pandas***"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Opz1_jfKNGXI"
      },
      "source": [
        "import pandas as pd"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 434
        },
        "id": "ZnZPAuUpp8-6",
        "outputId": "aef45b6b-a398-4875-e16a-2a8439082c17"
      },
      "source": [
        "titanic_df = pd.read_csv('train.csv')\r\n",
        "print('titanic 변수 type :',type(titanic_df))\r\n",
        "titanic_df"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "titanic 변수 type : <class 'pandas.core.frame.DataFrame'>\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr....</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mr...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, ...</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 31...</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Futrelle, M...</td>\n",
              "      <td>female</td>\n",
              "      <td>35.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>113803</td>\n",
              "      <td>53.1000</td>\n",
              "      <td>C123</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Allen, Mr. ...</td>\n",
              "      <td>male</td>\n",
              "      <td>35.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>373450</td>\n",
              "      <td>8.0500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>886</th>\n",
              "      <td>887</td>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>Montvila, R...</td>\n",
              "      <td>male</td>\n",
              "      <td>27.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>211536</td>\n",
              "      <td>13.0000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>887</th>\n",
              "      <td>888</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Graham, Mis...</td>\n",
              "      <td>female</td>\n",
              "      <td>19.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>112053</td>\n",
              "      <td>30.0000</td>\n",
              "      <td>B42</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>888</th>\n",
              "      <td>889</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Johnston, M...</td>\n",
              "      <td>female</td>\n",
              "      <td>NaN</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>W./C. 6607</td>\n",
              "      <td>23.4500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>889</th>\n",
              "      <td>890</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Behr, Mr. K...</td>\n",
              "      <td>male</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>111369</td>\n",
              "      <td>30.0000</td>\n",
              "      <td>C148</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>890</th>\n",
              "      <td>891</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Dooley, Mr....</td>\n",
              "      <td>male</td>\n",
              "      <td>32.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>370376</td>\n",
              "      <td>7.7500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Q</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>891 rows × 12 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "     PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
              "0              1         0       3  ...   7.2500   NaN         S\n",
              "1              2         1       1  ...  71.2833   C85         C\n",
              "2              3         1       3  ...   7.9250   NaN         S\n",
              "3              4         1       1  ...  53.1000  C123         S\n",
              "4              5         0       3  ...   8.0500   NaN         S\n",
              "..           ...       ...     ...  ...      ...   ...       ...\n",
              "886          887         0       2  ...  13.0000   NaN         S\n",
              "887          888         1       1  ...  30.0000   B42         S\n",
              "888          889         0       3  ...  23.4500   NaN         S\n",
              "889          890         1       1  ...  30.0000  C148         C\n",
              "890          891         0       3  ...   7.7500   NaN         Q\n",
              "\n",
              "[891 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 203
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "UQm0j2TXqBZd",
        "outputId": "fb4f5cbe-7e5d-406d-dcc2-9bd0f27da85f"
      },
      "source": [
        "titanic_df.head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr. Owen Harris</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, Miss. Laina</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 3101282</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
              "0            1         0       3  ...   7.2500   NaN         S\n",
              "1            2         1       1  ...  71.2833   C85         C\n",
              "2            3         1       3  ...   7.9250   NaN         S\n",
              "\n",
              "[3 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 152
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cfH3FtjdqU7Y",
        "outputId": "5fde8743-6f9d-491a-a976-00f82cfe7c87"
      },
      "source": [
        "print('DataFrame 크기 :',titanic_df.shape)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "DataFrame 크기 : (891, 12)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hKv7pldYqeTm",
        "outputId": "2b056cc2-a3ee-4073-b89c-c0675a7a701f"
      },
      "source": [
        "titanic_df.info() # info() 메서드를 통해 데이터 건수와 데이터 타입, NULL 건수를 확인"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 891 entries, 0 to 890\n",
            "Data columns (total 12 columns):\n",
            " #   Column       Non-Null Count  Dtype  \n",
            "---  ------       --------------  -----  \n",
            " 0   PassengerId  891 non-null    int64  \n",
            " 1   Survived     891 non-null    int64  \n",
            " 2   Pclass       891 non-null    int64  \n",
            " 3   Name         891 non-null    object \n",
            " 4   Sex          891 non-null    object \n",
            " 5   Age          714 non-null    float64\n",
            " 6   SibSp        891 non-null    int64  \n",
            " 7   Parch        891 non-null    int64  \n",
            " 8   Ticket       891 non-null    object \n",
            " 9   Fare         891 non-null    float64\n",
            " 10  Cabin        204 non-null    object \n",
            " 11  Embarked     889 non-null    object \n",
            "dtypes: float64(2), int64(5), object(5)\n",
            "memory usage: 83.7+ KB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 294
        },
        "id": "_S-US4vmqh-m",
        "outputId": "a5f82e36-b382-4504-d099-52d903a11ca3"
      },
      "source": [
        "titanic_df.describe() # describe() 메서드를 통해 n-percentile 분포도, 평균값, 최대값, 최솟값을 확인(int,float 자료형만 확인 object 자료형은 자동 제거)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Fare</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>891.000000</td>\n",
              "      <td>891.000000</td>\n",
              "      <td>891.000000</td>\n",
              "      <td>714.000000</td>\n",
              "      <td>891.000000</td>\n",
              "      <td>891.000000</td>\n",
              "      <td>891.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>446.000000</td>\n",
              "      <td>0.383838</td>\n",
              "      <td>2.308642</td>\n",
              "      <td>29.699118</td>\n",
              "      <td>0.523008</td>\n",
              "      <td>0.381594</td>\n",
              "      <td>32.204208</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>257.353842</td>\n",
              "      <td>0.486592</td>\n",
              "      <td>0.836071</td>\n",
              "      <td>14.526497</td>\n",
              "      <td>1.102743</td>\n",
              "      <td>0.806057</td>\n",
              "      <td>49.693429</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.420000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>223.500000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>2.000000</td>\n",
              "      <td>20.125000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>7.910400</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>446.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>28.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>14.454200</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>668.500000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>38.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>31.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>891.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>80.000000</td>\n",
              "      <td>8.000000</td>\n",
              "      <td>6.000000</td>\n",
              "      <td>512.329200</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "       PassengerId    Survived      Pclass  ...       SibSp       Parch        Fare\n",
              "count   891.000000  891.000000  891.000000  ...  891.000000  891.000000  891.000000\n",
              "mean    446.000000    0.383838    2.308642  ...    0.523008    0.381594   32.204208\n",
              "std     257.353842    0.486592    0.836071  ...    1.102743    0.806057   49.693429\n",
              "min       1.000000    0.000000    1.000000  ...    0.000000    0.000000    0.000000\n",
              "25%     223.500000    0.000000    2.000000  ...    0.000000    0.000000    7.910400\n",
              "50%     446.000000    0.000000    3.000000  ...    0.000000    0.000000   14.454200\n",
              "75%     668.500000    1.000000    3.000000  ...    1.000000    0.000000   31.000000\n",
              "max     891.000000    1.000000    3.000000  ...    8.000000    6.000000  512.329200\n",
              "\n",
              "[8 rows x 7 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 156
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "muPpzmurq6ad",
        "outputId": "c9332df1-98ab-42d7-b700-288d1c116548"
      },
      "source": [
        "value_counts = titanic_df['Pclass'].value_counts()\r\n",
        "value_counts"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "3    491\n",
              "1    216\n",
              "2    184\n",
              "Name: Pclass, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 158
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OFJEzx8vr5p7",
        "outputId": "80088c7b-8fb5-4ecc-fc53-b18ff321e9ad"
      },
      "source": [
        "titanic_pclass = titanic_df['Pclass'] # 이 처럼 DataFrame의 []연산자 내부에 컬럼명을 입력하면 Series 형태로 반환\r\n",
        "print(type(titanic_pclass))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.series.Series'>\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dlcMJZlKsO-u",
        "outputId": "fc9c1308-c09f-4b92-9018-07c90c77447c"
      },
      "source": [
        "titanic_pclass.head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    3\n",
              "1    1\n",
              "2    3\n",
              "3    1\n",
              "4    3\n",
              "Name: Pclass, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 161
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "j7kCwG88t3kz"
      },
      "source": [
        "* 넘파이 ndarray, 리스트 list, 딕셔너리 dict을 \r\n",
        "DataFrame으로 변환하기\r\n",
        "* DataFrame은 기본적으로 행과 열을 가지는 2차원 데이터\r\n",
        "* 따라서 2차원 이하의 데이터들만 DataFrame으로 변환 가능"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RnQl4kvSwDpN"
      },
      "source": [
        "리스트,ndarray -> 데이터 프레임"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7BTrmd0Vsfq-",
        "outputId": "8bbf6bd5-1c35-4981-f211-8770b8118ef8"
      },
      "source": [
        "import numpy as np\r\n",
        "\r\n",
        "col_name = ['col1']\r\n",
        "list1 = [1,2,3]\r\n",
        "array1 = np.array(list1)\r\n",
        "print('array1 shape :',array1.shape)\r\n",
        "# 리스트를 이용해 DataFrame 생성\r\n",
        "df_list1 = pd.DataFrame(list1,columns=col_name)\r\n",
        "print(df_list1,'\\n')\r\n",
        "# 넘파이 ndarray를 이용해 DataFrame 생성\r\n",
        "df_array1 = pd.DataFrame(array1,columns=col_name)\r\n",
        "print(df_array1)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "array1 shape : (3,)\n",
            "   col1\n",
            "0     1\n",
            "1     2\n",
            "2     3 \n",
            "\n",
            "   col1\n",
            "0     1\n",
            "1     2\n",
            "2     3\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8_SueJgfuRtI",
        "outputId": "b6959be9-318b-41c8-f3d9-1ff2c33af343"
      },
      "source": [
        "import numpy as np\r\n",
        "\r\n",
        "col_name = ['col','col2','col3']\r\n",
        "list2 = [[1,2,3],[11,12,13]]\r\n",
        "array2 = np.array(list2)\r\n",
        "print('array2 shape :',array2.shape)\r\n",
        "# list -> DataFrame\r\n",
        "df_list2 = pd.DataFrame(list2,columns=col_name)\r\n",
        "print(df_list2)\r\n",
        "# ndarray -> DataFrame\r\n",
        "df_array2 = pd.DataFrame(array2,columns=col_name)\r\n",
        "print('\\n',df_array2)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "array2 shape : (2, 3)\n",
            "   col  col2  col3\n",
            "0    1     2     3\n",
            "1   11    12    13\n",
            "\n",
            "    col  col2  col3\n",
            "0    1     2     3\n",
            "1   11    12    13\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OB0sZfpDwAPS"
      },
      "source": [
        "딕셔너리 -> 데이터프레임"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Mt9CD__wv7qq",
        "outputId": "66232d15-8bb5-437d-8d75-daacb9c70734"
      },
      "source": [
        "dict = {'col':[1,11],'col2':[2,12],'col3':[3,13]}\r\n",
        "df_dict = pd.DataFrame(dict)\r\n",
        "print(df_dict)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "   col  col2  col3\n",
            "0    1     2     3\n",
            "1   11    12    13\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JqPrFz61wqIv"
      },
      "source": [
        "- DataFrame을 넘파이 ndarray, 리스트, 딕셔너리로 변환하기"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Bg_Lp68IxUXn"
      },
      "source": [
        "데이터프레임 객체의 values를 이용하여 변환 가능"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZpwOoqUUwf6Y",
        "outputId": "470e130d-401b-4ad7-9696-9871355ca961"
      },
      "source": [
        "# DataFrame -> ndarray\r\n",
        "array3 = df_dict.values\r\n",
        "print('df_dict.values 타입 :',type(array3),'df_dict shape :',array3.shape)\r\n",
        "print(array3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "df_dict.values 타입 : <class 'numpy.ndarray'> df_dict shape : (2, 3)\n",
            "[[ 1  2  3]\n",
            " [11 12 13]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "j7Yjgc38xEOM",
        "outputId": "2d578d79-fbe7-40ba-d328-67490b5791f1"
      },
      "source": [
        "# DataFrame -> list\r\n",
        "list3 = df_dict.values.tolist()\r\n",
        "print('df_dict.values.tolist 타입 :',type(list3))\r\n",
        "print(list3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "df_dict.values.tolist 타입 : <class 'list'>\n",
            "[[1, 2, 3], [11, 12, 13]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0qBa8yi7xx__",
        "outputId": "5f1339e7-47b0-40cb-c9e4-302804b1cd19"
      },
      "source": [
        "# DataFrame -> list\r\n",
        "dict3 = df_dict.to_dict()\r\n",
        "print('df_dict.to_dict 타입 :',type(dict3))\r\n",
        "print(dict3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "df_dict.to_dict 타입 : <class 'dict'>\n",
            "{'col': {0: 1, 1: 11}, 'col2': {0: 2, 1: 12}, 'col3': {0: 3, 1: 13}}\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "qYAFoVETyTim"
      },
      "source": [
        "- to_list() # DataFrame -> list로 변환\r\n",
        "\r\n",
        "- to_dict() # DataFrame -> 딕셔너리로 변환"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6VPUW9N_y8QL"
      },
      "source": [
        "**DataFrame의 컬럼 데이터 생성 또는 수정**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 193
        },
        "id": "0xMqnedayMyE",
        "outputId": "fb32d306-0f10-45d2-e0fe-258932d476ed"
      },
      "source": [
        "titanic_df['Age_0']=0\r\n",
        "titanic_df.head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "      <th>Age_by_10</th>\n",
              "      <th>Family_No</th>\n",
              "      <th>Age_0</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr. Owen Harris</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>320.0</td>\n",
              "      <td>2</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "      <td>480.0</td>\n",
              "      <td>2</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, Miss. Laina</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 3101282</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>360.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ... Age_by_10 Family_No  Age_0\n",
              "0            1         0       3  ...     320.0         2      0\n",
              "1            2         1       1  ...     480.0         2      0\n",
              "2            3         1       3  ...     360.0         1      0\n",
              "\n",
              "[3 rows x 15 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 190
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 193
        },
        "id": "y--6nNnozJe_",
        "outputId": "f9037b3f-361b-4a62-a024-4a3be7e3cf37"
      },
      "source": [
        "titanic_df['Age_by_10'] = titanic_df['Age']*10\r\n",
        "titanic_df['Family_No'] = titanic_df['SibSp']+titanic_df['Parch']+1\r\n",
        "titanic_df.head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "      <th>Age_0</th>\n",
              "      <th>Age_by_10</th>\n",
              "      <th>Family_No</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr. Owen Harris</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>0</td>\n",
              "      <td>220.0</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "      <td>0</td>\n",
              "      <td>380.0</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, Miss. Laina</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 3101282</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>0</td>\n",
              "      <td>260.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ... Age_0 Age_by_10  Family_No\n",
              "0            1         0       3  ...     0     220.0          2\n",
              "1            2         1       1  ...     0     380.0          2\n",
              "2            3         1       3  ...     0     260.0          1\n",
              "\n",
              "[3 rows x 15 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 183
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jYOvyBbLzn_D"
      },
      "source": [
        "titanic_df['Age_by_10'] = titanic_df['Age_by_10']+100"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 193
        },
        "id": "K8ooiLPdz2dv",
        "outputId": "b7d1f5be-fe99-46c0-d0a3-c1fbb5264563"
      },
      "source": [
        "titanic_df.head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "      <th>Age_0</th>\n",
              "      <th>Age_by_10</th>\n",
              "      <th>Family_No</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr. Owen Harris</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>0</td>\n",
              "      <td>320.0</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "      <td>0</td>\n",
              "      <td>480.0</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, Miss. Laina</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 3101282</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>0</td>\n",
              "      <td>360.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ... Age_0 Age_by_10  Family_No\n",
              "0            1         0       3  ...     0     320.0          2\n",
              "1            2         1       1  ...     0     480.0          2\n",
              "2            3         1       3  ...     0     360.0          1\n",
              "\n",
              "[3 rows x 15 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 185
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "YolvqRUh1DzN"
      },
      "source": [
        "** DataFrame 데이터 삭제**\r\n",
        "- drop() 메서드 사용\r\n",
        "- drop(labels = None, axis = 0, inplace = False)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 175
        },
        "id": "iJ8IlEULz4ip",
        "outputId": "a01d4dbd-bfe3-40df-c45f-98dd0eda6e5a"
      },
      "source": [
        "titanic_drop_df = titanic_df.drop(labels='Age_0',axis=1,inplace=False)\r\n",
        "titanic_drop_df.head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "      <th>Age_by_10</th>\n",
              "      <th>Family_No</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr. Owen Harris</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>320.0</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "      <td>480.0</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, Miss. Laina</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 3101282</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>360.0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ... Embarked Age_by_10  Family_No\n",
              "0            1         0       3  ...        S     320.0          2\n",
              "1            2         1       1  ...        C     480.0          2\n",
              "2            3         1       3  ...        S     360.0          1\n",
              "\n",
              "[3 rows x 14 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 191
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 193
        },
        "id": "q_fEaDHt1W9K",
        "outputId": "2dac99e1-022e-4e57-8d8b-e6e93e3d1a19"
      },
      "source": [
        "titanic_df.head(3) # Age_0이 존재 문재해결 -> inplace = True 사용"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "      <th>Age_by_10</th>\n",
              "      <th>Family_No</th>\n",
              "      <th>Age_0</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr. Owen Harris</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>320.0</td>\n",
              "      <td>2</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "      <td>480.0</td>\n",
              "      <td>2</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, Miss. Laina</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 3101282</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "      <td>360.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ... Age_by_10 Family_No  Age_0\n",
              "0            1         0       3  ...     320.0         2      0\n",
              "1            2         1       1  ...     480.0         2      0\n",
              "2            3         1       3  ...     360.0         1      0\n",
              "\n",
              "[3 rows x 15 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 193
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "3gVmHEoN2Lvd"
      },
      "source": [
        "- inplace 파라미터를 기재하지 않거나 False로 설정하면 자기 자신의 데이터는 삭제하지 않는다. 반면에 True로 설정하면 자기 자신의 데이터도 삭제"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "mjtoAbOv132i"
      },
      "source": [
        "drop_result = titanic_df.drop(['Age_0','Age_by_10','Family_No'],axis=1,inplace=True)\r\n",
        "drop_result"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "9P6tNDGm2vUV",
        "outputId": "af21bf56-f4b9-49cc-95b2-7c79544301c6"
      },
      "source": [
        "titanic_df.head(3) # inplace = True 파라미터를 설정할 시 Age_0, Age_by_10, Family_No 컬럼이 삭제된 것을 알 수 있다."
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr. Owen Harris</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, Miss. Laina</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 3101282</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
              "0            1         0       3  ...   7.2500   NaN         S\n",
              "1            2         1       1  ...  71.2833   C85         C\n",
              "2            3         1       3  ...   7.9250   NaN         S\n",
              "\n",
              "[3 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 195
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cz5ToZuC2wxi",
        "outputId": "8ebb9cea-eb9c-4404-b62b-b4a499c6e12b"
      },
      "source": [
        "pd.set_option('display.width',1000)\r\n",
        "pd.set_option('display.max_colwidth',15)\r\n",
        "print('#### before axis 0 drop ####')\r\n",
        "print(titanic_df.head(3))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "#### before axis 0 drop ####\n",
            "   PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
            "0            1         0       3  ...   7.2500   NaN         S\n",
            "1            2         1       1  ...  71.2833   C85         C\n",
            "2            3         1       3  ...   7.9250   NaN         S\n",
            "\n",
            "[3 rows x 12 columns]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SuCCTssA4eS4"
      },
      "source": [
        "- axis=0 으로 설정해 index 1,2,3 (맨 첫번째 두번째 세번째) 로우를 삭제"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nHCByyr33gLU",
        "outputId": "8bf65090-325d-4871-fc3d-6b99c5a6990a"
      },
      "source": [
        "titanic_df.drop([1,2,3],axis=0,inplace=True)\r\n",
        "\r\n",
        "print('### after axis 0 drop ####')\r\n",
        "print(titanic_df.head(3))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "### after axis 0 drop ####\n",
            "   PassengerId  Survived  Pclass  ...    Fare Cabin  Embarked\n",
            "0            1         0       3  ...  7.2500   NaN         S\n",
            "4            5         0       3  ...  8.0500   NaN         S\n",
            "5            6         0       3  ...  8.4583   NaN         Q\n",
            "\n",
            "[3 rows x 12 columns]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ACs86zOq4vUm"
      },
      "source": [
        "[정리]\r\n",
        "- axis = 0 이면 로우 삭제/axis = 1 이면 컬럼 삭제\r\n",
        "- inplace = True 이면 데이터 원본 삭제/ inplace = False이면 데이터 원본 유지\r\n",
        "- titanic_df = titanic_df.drop('Age_0',axis=1, inplace=True) 즉 다시 워논 데이터프레임을 변수로 할당하면 원본 데이터프레임에서 드롭된 결과를 적용할 경우와 같음 "
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NVf1iO2f6bsn"
      },
      "source": [
        "**index 객체**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "V4d88siA63NK"
      },
      "source": [
        "titanic_df = pd.read_csv('train.csv')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MbHj4y8d4IfE",
        "outputId": "9fc18161-f58c-4490-eca3-a0d1b4e0cdc1"
      },
      "source": [
        "indexes = titanic_df.index\r\n",
        "print(indexes)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "RangeIndex(start=0, stop=891, step=1)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kTium8Cb6jhQ",
        "outputId": "f4292df1-aee6-417e-8d88-6b9e3ac345fe"
      },
      "source": [
        "print(indexes.values)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17\n",
            "  18  19  20  21  22  23  24  25  26  27  28  29  30  31  32  33  34  35\n",
            "  36  37  38  39  40  41  42  43  44  45  46  47  48  49  50  51  52  53\n",
            "  54  55  56  57  58  59  60  61  62  63  64  65  66  67  68  69  70  71\n",
            "  72  73  74  75  76  77  78  79  80  81  82  83  84  85  86  87  88  89\n",
            "  90  91  92  93  94  95  96  97  98  99 100 101 102 103 104 105 106 107\n",
            " 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125\n",
            " 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143\n",
            " 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161\n",
            " 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179\n",
            " 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197\n",
            " 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215\n",
            " 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233\n",
            " 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251\n",
            " 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269\n",
            " 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287\n",
            " 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305\n",
            " 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323\n",
            " 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341\n",
            " 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359\n",
            " 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377\n",
            " 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395\n",
            " 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413\n",
            " 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431\n",
            " 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449\n",
            " 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467\n",
            " 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485\n",
            " 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503\n",
            " 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521\n",
            " 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539\n",
            " 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557\n",
            " 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575\n",
            " 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593\n",
            " 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611\n",
            " 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629\n",
            " 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647\n",
            " 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665\n",
            " 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683\n",
            " 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701\n",
            " 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719\n",
            " 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737\n",
            " 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755\n",
            " 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773\n",
            " 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791\n",
            " 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809\n",
            " 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827\n",
            " 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845\n",
            " 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863\n",
            " 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881\n",
            " 882 883 884 885 886 887 888 889 890]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "H3MAALoh6sOj",
        "outputId": "d95fae99-3623-4dfb-bdf1-870ad5a09631"
      },
      "source": [
        "print(type(indexes.values))\r\n",
        "print(indexes.values.shape)\r\n",
        "print(indexes[:5].values)\r\n",
        "print(indexes.values[:5])\r\n",
        "print(indexes[6])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'numpy.ndarray'>\n",
            "(891,)\n",
            "[0 1 2 3 4]\n",
            "[0 1 2 3 4]\n",
            "6\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 307
        },
        "id": "XcWt8XHt7K-g",
        "outputId": "ad7199e3-0b22-4c99-a55f-b4bd795ad0d4"
      },
      "source": [
        "indexes[0] = 5 # index 객체는 함부로 변경할 수 없다"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "error",
          "ename": "TypeError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-218-0586941eae38>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mindexes\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m5\u001b[0m \u001b[0;31m# index 객체는 함부로 변경할 수 없다\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36m__setitem__\u001b[0;34m(self, key, value)\u001b[0m\n\u001b[1;32m   4082\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4083\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__setitem__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 4084\u001b[0;31m         \u001b[0;32mraise\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Index does not support mutable operations\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   4085\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4086\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__getitem__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mTypeError\u001b[0m: Index does not support mutable operations"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cIgTkWhw7j0j",
        "outputId": "0a157371-aa18-4f1e-b8d8-64a507c92819"
      },
      "source": [
        "series_fair = titanic_df['Fare']\r\n",
        "print('Fair Series max 값 :',series_fair.max())\r\n",
        "print('Fair Series sum 값 :',series_fair.sum())\r\n",
        "print('sum() Fair Series 값 :',sum(series_fair))\r\n",
        "print('Fair Series + 3 :\\n',(series_fair + 3).head(3))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Fair Series max 값 : 512.3292\n",
            "Fair Series sum 값 : 28693.9493\n",
            "sum() Fair Series 값 : 28693.949299999967\n",
            "Fair Series + 3 :\n",
            " 0    10.2500\n",
            "1    74.2833\n",
            "2    10.9250\n",
            "Name: Fare, dtype: float64\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7gwy41F_9mJ6"
      },
      "source": [
        "- reset_index() 메서드를 수행하면 새롭게 인덱스를 연속 숫자 형으로 할당 하며 기존 인덱스는 index라는 새로운 컬럼 명으로 추가됨"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "u0tdeOE08WsL",
        "outputId": "f4b4ea19-37c1-4c4e-85d8-b518640ced23"
      },
      "source": [
        "titanic_reset_df = titanic_df.reset_index(inplace=False)\r\n",
        "titanic_reset_df.head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>index</th>\n",
              "      <th>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr....</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mr...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, ...</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 31...</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   index  PassengerId  Survived  Pclass  ...          Ticket     Fare  Cabin  Embarked\n",
              "0      0            1         0       3  ...       A/5 21171   7.2500    NaN         S\n",
              "1      1            2         1       1  ...        PC 17599  71.2833    C85         C\n",
              "2      2            3         1       3  ...  STON/O2. 31...   7.9250    NaN         S\n",
              "\n",
              "[3 rows x 13 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 223
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BBOYbGBa9w3W",
        "outputId": "b2861662-771c-4d10-d0bc-2a41eda5d220"
      },
      "source": [
        "print('### before reset_index ###')\r\n",
        "value_counts = titanic_df['Pclass'].value_counts()\r\n",
        "print(value_counts)\r\n",
        "print(type(value_counts))\r\n",
        "new_value_counts = value_counts.reset_index()\r\n",
        "print('### before reset_index ###') # Series -> DataFrame 으로 변환 (reset_index 사용 후)\r\n",
        "print(new_value_counts)\r\n",
        "print(type(new_value_counts))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "### before reset_index ###\n",
            "3    491\n",
            "1    216\n",
            "2    184\n",
            "Name: Pclass, dtype: int64\n",
            "<class 'pandas.core.series.Series'>\n",
            "### before reset_index ###\n",
            "   index  Pclass\n",
            "0      3     491\n",
            "1      1     216\n",
            "2      2     184\n",
            "<class 'pandas.core.frame.DataFrame'>\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nsQRtpZ_Cllu"
      },
      "source": [
        "**데이터 셀렉션 및 필터링**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zcEj3HioCwxu"
      },
      "source": [
        "- 넘파이의 경우 [ ] 연산자 내 단일 값 추출, 슬라이싱, 팬시 인덱싱, 불린 인덱싱을 통해 데이터를 추출\r\n",
        "\r\n",
        "- 판다스의 경우 ix[ ], iloc[ ], loc[ ] 연산자를 통해 동일한 작업을 수행"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 611
        },
        "id": "667m_88L_NAp",
        "outputId": "c48953aa-7711-4e5a-c2bc-d6a46147255d"
      },
      "source": [
        "titanic_df[0] # 숫자를 입력할 경우 오류발생"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "error",
          "ename": "KeyError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   2897\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2898\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcasted_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2899\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
            "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
            "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
            "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
            "\u001b[0;31mKeyError\u001b[0m: 0",
            "\nThe above exception was the direct cause of the following exception:\n",
            "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-229-95c93d0fdf67>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mtitanic_df\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;31m# 숫자를 입력할 경우 오류발생\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/pandas/core/frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   2904\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnlevels\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2905\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2906\u001b[0;31m             \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2907\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mis_integer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2908\u001b[0m                 \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mindexer\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   2898\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcasted_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2899\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2900\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2901\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2902\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mtolerance\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mKeyError\u001b[0m: 0"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 110
        },
        "id": "2fO6w84XEJbC",
        "outputId": "64d5cdd4-75ce-4b56-ef65-aae4b6e0d0cf"
      },
      "source": [
        "titanic_df[0:2] # 슬라이싱은 정확히 원하는 결과를 반환"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr....</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mr...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
              "0            1         0       3  ...   7.2500   NaN         S\n",
              "1            2         1       1  ...  71.2833   C85         C\n",
              "\n",
              "[2 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 228
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "GZRJkIvfEMKK",
        "outputId": "1dee5fc4-d81d-421b-a519-df28095fb8d9"
      },
      "source": [
        "titanic_df[titanic_df['Pclass']==3].head(3) # Pclass 가 3인 데이터 3개만 추출"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr....</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, ...</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 31...</td>\n",
              "      <td>7.925</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Allen, Mr. ...</td>\n",
              "      <td>male</td>\n",
              "      <td>35.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>373450</td>\n",
              "      <td>8.050</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ...   Fare Cabin  Embarked\n",
              "0            1         0       3  ...  7.250   NaN         S\n",
              "2            3         1       3  ...  7.925   NaN         S\n",
              "4            5         0       3  ...  8.050   NaN         S\n",
              "\n",
              "[3 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 230
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "T1MAjMjSEtCP"
      },
      "source": [
        "- ix [ ] 연산자는 넘파이의 [ ] 연산자와 유사한 기능 제공\r\n",
        "- ix [행위치 , 열위치 또는 컬럼이름]"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 171
        },
        "id": "m9SXky7HEc8U",
        "outputId": "c5f3cf9d-6251-48fb-b3af-f9fdd6fa6eaa"
      },
      "source": [
        "# ix [ ]\r\n",
        "\r\n",
        "data = {'Name':['Chulmin','Eunkyung','Jinwoong','Soobeom'],'Year':[2011,2016,2015,2015],'Gender':['M','F','M','M']}\r\n",
        "data_df = pd.DataFrame(data, index=['one','two','three','four'])\r\n",
        "data_df"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Name</th>\n",
              "      <th>Year</th>\n",
              "      <th>Gender</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>one</th>\n",
              "      <td>Chulmin</td>\n",
              "      <td>2011</td>\n",
              "      <td>M</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>two</th>\n",
              "      <td>Eunkyung</td>\n",
              "      <td>2016</td>\n",
              "      <td>F</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>three</th>\n",
              "      <td>Jinwoong</td>\n",
              "      <td>2015</td>\n",
              "      <td>M</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>four</th>\n",
              "      <td>Soobeom</td>\n",
              "      <td>2015</td>\n",
              "      <td>M</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "           Name  Year Gender\n",
              "one     Chulmin  2011      M\n",
              "two    Eunkyung  2016      F\n",
              "three  Jinwoong  2015      M\n",
              "four    Soobeom  2015      M"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 235
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 171
        },
        "id": "ezs9_Zb4GBPV",
        "outputId": "3e977a1a-e1cb-4e3c-ce81-1ed725ce2d28"
      },
      "source": [
        "data_df_reset = data_df.reset_index()\r\n",
        "data_df_reset = data_df_reset.rename(columns = {'index':'old_index'})\r\n",
        "data_df_reset.index = data_df_reset.index+1\r\n",
        "data_df_reset"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>old_index</th>\n",
              "      <th>Name</th>\n",
              "      <th>Year</th>\n",
              "      <th>Gender</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>one</td>\n",
              "      <td>Chulmin</td>\n",
              "      <td>2011</td>\n",
              "      <td>M</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>two</td>\n",
              "      <td>Eunkyung</td>\n",
              "      <td>2016</td>\n",
              "      <td>F</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>three</td>\n",
              "      <td>Jinwoong</td>\n",
              "      <td>2015</td>\n",
              "      <td>M</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>four</td>\n",
              "      <td>Soobeom</td>\n",
              "      <td>2015</td>\n",
              "      <td>M</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "  old_index      Name  Year Gender\n",
              "1       one   Chulmin  2011      M\n",
              "2       two  Eunkyung  2016      F\n",
              "3     three  Jinwoong  2015      M\n",
              "4      four   Soobeom  2015      M"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 238
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 307
        },
        "id": "qpBZXCH3HLlN",
        "outputId": "1890c74b-8b66-4be1-895c-aca2518e5bc8"
      },
      "source": [
        "data_df_reset.ix[1,1] # 최근에 ix 기능이 삭제되서 오류 뜨는거"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "error",
          "ename": "AttributeError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-244-735cd9f8bb40>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdata_df_reset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mix\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m   5139\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5140\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 5141\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   5142\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5143\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__setattr__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mAttributeError\u001b[0m: 'DataFrame' object has no attribute 'ix'"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "UcYV9Us7HlNZ"
      },
      "source": [
        "**iloc[ ]**\r\n",
        "- 위치 기반\r\n",
        "- 위치 인덱싱 값만 입력 가능\r\n",
        "- 0 부터 시작\r\n",
        "- 명칭 입력 불가능"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 36
        },
        "id": "zHSdLqVzGt1k",
        "outputId": "54e65550-6ed0-4bab-cca7-ba32f95be29f"
      },
      "source": [
        "data_df_reset.iloc[0,1]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "'Chulmin'"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 243
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-Y0qujZNHxd4"
      },
      "source": [
        "**loc[ ]**\r\n",
        "- 명칭 기반\r\n",
        "- 1 부터 시작"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 36
        },
        "id": "QjYvPSk8GyUq",
        "outputId": "5ea7bfe4-d6b1-4817-ca3e-9a25edd9df6a"
      },
      "source": [
        "data_df_reset.loc[1,'Name'] # 명칭 기반이라고 무조건 명칭만 되는건 아님 (1 부터 시작)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            },
            "text/plain": [
              "'Chulmin'"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 254
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Yo6yrp2IKuir"
      },
      "source": [
        "**불린 인덱싱**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 159
        },
        "id": "rXMYi7fDJQk3",
        "outputId": "d32419d3-8a5d-4f06-d1f7-ca277a21dc4d"
      },
      "source": [
        "titanic_df = pd.read_csv('train.csv')\r\n",
        "titanic_boolean = titanic_df[titanic_df['Age']>60]\r\n",
        "print(type(titanic_boolean))\r\n",
        "titanic_boolean.head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>33</th>\n",
              "      <td>34</td>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>Wheadon, Mr...</td>\n",
              "      <td>male</td>\n",
              "      <td>66.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>C.A. 24579</td>\n",
              "      <td>10.5000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>54</th>\n",
              "      <td>55</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>Ostby, Mr. ...</td>\n",
              "      <td>male</td>\n",
              "      <td>65.0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>113509</td>\n",
              "      <td>61.9792</td>\n",
              "      <td>B30</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96</th>\n",
              "      <td>97</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>Goldschmidt...</td>\n",
              "      <td>male</td>\n",
              "      <td>71.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17754</td>\n",
              "      <td>34.6542</td>\n",
              "      <td>A5</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "    PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
              "33           34         0       2  ...  10.5000   NaN         S\n",
              "54           55         0       1  ...  61.9792   B30         C\n",
              "96           97         0       1  ...  34.6542    A5         C\n",
              "\n",
              "[3 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 270
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "yOZ5_RpHKr0V",
        "outputId": "7cb31530-1e42-46bf-c2dc-ee1d7b4147bb"
      },
      "source": [
        "titanic_df[titanic_df['Age']>60][['Name','Age']].head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Name</th>\n",
              "      <th>Age</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>33</th>\n",
              "      <td>Wheadon, Mr...</td>\n",
              "      <td>66.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>54</th>\n",
              "      <td>Ostby, Mr. ...</td>\n",
              "      <td>65.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96</th>\n",
              "      <td>Goldschmidt...</td>\n",
              "      <td>71.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "              Name   Age\n",
              "33  Wheadon, Mr...  66.0\n",
              "54  Ostby, Mr. ...  65.0\n",
              "96  Goldschmidt...  71.0"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 271
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "IZA8_mG3LhPx",
        "outputId": "7d553142-f533-4535-ef25-16b24f6977a5"
      },
      "source": [
        "titanic_df.loc[titanic_df['Age']>60,['Name','Age']].head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Name</th>\n",
              "      <th>Age</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>33</th>\n",
              "      <td>Wheadon, Mr...</td>\n",
              "      <td>66.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>54</th>\n",
              "      <td>Ostby, Mr. ...</td>\n",
              "      <td>65.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96</th>\n",
              "      <td>Goldschmidt...</td>\n",
              "      <td>71.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "              Name   Age\n",
              "33  Wheadon, Mr...  66.0\n",
              "54  Ostby, Mr. ...  65.0\n",
              "96  Goldschmidt...  71.0"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 279
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "kR8swrS6Oyry"
      },
      "source": [
        "- 복합 조건 연산자 사용해서도 가능"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 110
        },
        "id": "hF-aEHJhNnsu",
        "outputId": "262c8561-9bae-4066-8cf4-53701baf71ac"
      },
      "source": [
        "titanic_df[(titanic_df['Age']>60)&(titanic_df['Pclass']==1)&(titanic_df['Sex']=='female')]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>275</th>\n",
              "      <td>276</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Andrews, Mi...</td>\n",
              "      <td>female</td>\n",
              "      <td>63.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>13502</td>\n",
              "      <td>77.9583</td>\n",
              "      <td>D7</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>829</th>\n",
              "      <td>830</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Stone, Mrs....</td>\n",
              "      <td>female</td>\n",
              "      <td>62.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>113572</td>\n",
              "      <td>80.0000</td>\n",
              "      <td>B28</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "     PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
              "275          276         1       1  ...  77.9583    D7         S\n",
              "829          830         1       1  ...  80.0000   B28       NaN\n",
              "\n",
              "[2 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 280
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xR7mkJHrPNdt"
      },
      "source": [
        "- 불린 인덱싱 + 복합 조건 연산자"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 110
        },
        "id": "qzpOrDzLPDxT",
        "outputId": "083e1e62-aaa9-4889-a5ff-fbeed3cae54e"
      },
      "source": [
        "cond1 = titanic_df['Age']>60\r\n",
        "cond2 = titanic_df['Pclass']==1\r\n",
        "cond3 = titanic_df['Sex'] == 'female'\r\n",
        "titanic_df[cond1&cond2&cond3]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>275</th>\n",
              "      <td>276</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Andrews, Mi...</td>\n",
              "      <td>female</td>\n",
              "      <td>63.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>13502</td>\n",
              "      <td>77.9583</td>\n",
              "      <td>D7</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>829</th>\n",
              "      <td>830</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Stone, Mrs....</td>\n",
              "      <td>female</td>\n",
              "      <td>62.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>113572</td>\n",
              "      <td>80.0000</td>\n",
              "      <td>B28</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "     PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
              "275          276         1       1  ...  77.9583    D7         S\n",
              "829          830         1       1  ...  80.0000   B28       NaN\n",
              "\n",
              "[2 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 281
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "W2cLOAcBPjFp"
      },
      "source": [
        "**sort_values 정렬, Aggregation 함수, GroupBy 적용**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "33SxWkEuPpPY"
      },
      "source": [
        "- DataFrame, Series의 정렬 - sort_values()\r\n",
        "- 데이터프레임 시리즈를 정렬하기위해서는 sort_values() 메서드를 이용\r\n",
        "- by 파라미터는 기준이 될 컬럼이름\r\n",
        "- ascending = False로 하면 내림차순 ascending = True로 하면 오름차순\r\n",
        "- drop 때 사용한 inplace 파라미터와 마찬가지"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 415
        },
        "id": "FWia9IusPdfH",
        "outputId": "89bf6b35-d07a-4fe2-aea8-e75a9f25af24"
      },
      "source": [
        "titanic_sorted = titanic_df.sort_values(by=['Name']) # ascending 파라미터는 디폴트값이 오름차순 따라서 Name 컬럼으로 오름차순 정렬\r\n",
        "titanic_sorted"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>845</th>\n",
              "      <td>846</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Abbing, Mr....</td>\n",
              "      <td>male</td>\n",
              "      <td>42.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>C.A. 5547</td>\n",
              "      <td>7.5500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>746</th>\n",
              "      <td>747</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Abbott, Mr....</td>\n",
              "      <td>male</td>\n",
              "      <td>16.0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>C.A. 2673</td>\n",
              "      <td>20.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>279</th>\n",
              "      <td>280</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Abbott, Mrs...</td>\n",
              "      <td>female</td>\n",
              "      <td>35.0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>C.A. 2673</td>\n",
              "      <td>20.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>308</th>\n",
              "      <td>309</td>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>Abelson, Mr...</td>\n",
              "      <td>male</td>\n",
              "      <td>30.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>P/PP 3381</td>\n",
              "      <td>24.0000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>874</th>\n",
              "      <td>875</td>\n",
              "      <td>1</td>\n",
              "      <td>2</td>\n",
              "      <td>Abelson, Mr...</td>\n",
              "      <td>female</td>\n",
              "      <td>28.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>P/PP 3381</td>\n",
              "      <td>24.0000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>286</th>\n",
              "      <td>287</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>de Mulder, ...</td>\n",
              "      <td>male</td>\n",
              "      <td>30.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>345774</td>\n",
              "      <td>9.5000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>282</th>\n",
              "      <td>283</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>de Pelsmaek...</td>\n",
              "      <td>male</td>\n",
              "      <td>16.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>345778</td>\n",
              "      <td>9.5000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>361</th>\n",
              "      <td>362</td>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>del Carlo, ...</td>\n",
              "      <td>male</td>\n",
              "      <td>29.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>SC/PARIS 2167</td>\n",
              "      <td>27.7208</td>\n",
              "      <td>NaN</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>153</th>\n",
              "      <td>154</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>van Billiar...</td>\n",
              "      <td>male</td>\n",
              "      <td>40.5</td>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>A/5. 851</td>\n",
              "      <td>14.5000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>868</th>\n",
              "      <td>869</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>van Melkebe...</td>\n",
              "      <td>male</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>345777</td>\n",
              "      <td>9.5000</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>891 rows × 12 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "     PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
              "845          846         0       3  ...   7.5500   NaN         S\n",
              "746          747         0       3  ...  20.2500   NaN         S\n",
              "279          280         1       3  ...  20.2500   NaN         S\n",
              "308          309         0       2  ...  24.0000   NaN         C\n",
              "874          875         1       2  ...  24.0000   NaN         C\n",
              "..           ...       ...     ...  ...      ...   ...       ...\n",
              "286          287         1       3  ...   9.5000   NaN         S\n",
              "282          283         0       3  ...   9.5000   NaN         S\n",
              "361          362         0       2  ...  27.7208   NaN         C\n",
              "153          154         0       3  ...  14.5000   NaN         S\n",
              "868          869         0       3  ...   9.5000   NaN         S\n",
              "\n",
              "[891 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 283
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "q0SkaIFuRj6M",
        "outputId": "63a468ba-4328-4414-e7df-43d80bbe6c5a"
      },
      "source": [
        "titanic_sorted = titanic_df.sort_values(by=['Pclass','Name'],ascending=False) # ascending = False 내림차순\r\n",
        "titanic_sorted.head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>868</th>\n",
              "      <td>869</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>van Melkebe...</td>\n",
              "      <td>male</td>\n",
              "      <td>NaN</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>345777</td>\n",
              "      <td>9.5</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>153</th>\n",
              "      <td>154</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>van Billiar...</td>\n",
              "      <td>male</td>\n",
              "      <td>40.5</td>\n",
              "      <td>0</td>\n",
              "      <td>2</td>\n",
              "      <td>A/5. 851</td>\n",
              "      <td>14.5</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>282</th>\n",
              "      <td>283</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>de Pelsmaek...</td>\n",
              "      <td>male</td>\n",
              "      <td>16.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>345778</td>\n",
              "      <td>9.5</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "     PassengerId  Survived  Pclass  ...  Fare Cabin  Embarked\n",
              "868          869         0       3  ...   9.5   NaN         S\n",
              "153          154         0       3  ...  14.5   NaN         S\n",
              "282          283         0       3  ...   9.5   NaN         S\n",
              "\n",
              "[3 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 284
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jOr3dcY1SZ9O"
      },
      "source": [
        "**Aggregation 함수 적용**\r\n",
        "- aggregation 함수의 적용은 RDBMS SQL의 aggregation 함수 적용과 유사\r\n",
        "- 차이점은 데이터프레임에서 바로 aggregation을 호출할 경우 모든 칼럼에 해당하는 agrregation을 적용\r\n",
        "- min(), max(), sum(), count(), mean()"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sqGrX8sSSMqm",
        "outputId": "9c2170ad-5752-415a-e04f-183eaaaf5aaf"
      },
      "source": [
        "titanic_df.count()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "PassengerId    891\n",
              "Survived       891\n",
              "Pclass         891\n",
              "Name           891\n",
              "Sex            891\n",
              "Age            714\n",
              "SibSp          891\n",
              "Parch          891\n",
              "Ticket         891\n",
              "Fare           891\n",
              "Cabin          204\n",
              "Embarked       889\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 285
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0SIakYggS0fp",
        "outputId": "c9aef9bd-6877-4a41-a310-a0ab1dc0b76a"
      },
      "source": [
        "titanic_df[['Age','Fare']].mean() # 대상 컬럼들만 추출"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Age     29.699118\n",
              "Fare    32.204208\n",
              "dtype: float64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 287
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EqWo67yrTM0J"
      },
      "source": [
        "**groupby() 적용**\r\n",
        "- RDBMS SQL의 groupby 키워드와 유사 대신 다른 면도 존재 (조심)\r\n",
        "- by = 대상 컬럼 입력하게 되면 해당 컬럼 기준으로 groupby가 된 데이터프레임 반환"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "iY9nCl0HTGCG",
        "outputId": "a86fdc56-a277-4a9d-d8a6-f26c7765b9e5"
      },
      "source": [
        "titanic_groupby = titanic_df.groupby(by='Pclass')\r\n",
        "print(titanic_groupby)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "<pandas.core.groupby.generic.DataFrameGroupBy object at 0x7f221cae5940>\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 171
        },
        "id": "r36nq9xhTs63",
        "outputId": "503ddc33-37ee-42ea-db48-4f123d422432"
      },
      "source": [
        "titanic_groupby = titanic_df.groupby(by='Pclass').count() # groupby를 하고 aggregation 함수 (count함수) 적용 : 해당 컬럼 기준으로 각 컬럼의 개수를 반환\r\n",
        "titanic_groupby"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Pclass</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>216</td>\n",
              "      <td>216</td>\n",
              "      <td>216</td>\n",
              "      <td>216</td>\n",
              "      <td>186</td>\n",
              "      <td>216</td>\n",
              "      <td>216</td>\n",
              "      <td>216</td>\n",
              "      <td>216</td>\n",
              "      <td>176</td>\n",
              "      <td>214</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>184</td>\n",
              "      <td>184</td>\n",
              "      <td>184</td>\n",
              "      <td>184</td>\n",
              "      <td>173</td>\n",
              "      <td>184</td>\n",
              "      <td>184</td>\n",
              "      <td>184</td>\n",
              "      <td>184</td>\n",
              "      <td>16</td>\n",
              "      <td>184</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>491</td>\n",
              "      <td>491</td>\n",
              "      <td>491</td>\n",
              "      <td>491</td>\n",
              "      <td>355</td>\n",
              "      <td>491</td>\n",
              "      <td>491</td>\n",
              "      <td>491</td>\n",
              "      <td>491</td>\n",
              "      <td>12</td>\n",
              "      <td>491</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "        PassengerId  Survived  Name  Sex  ...  Ticket  Fare  Cabin  Embarked\n",
              "Pclass                                    ...                               \n",
              "1               216       216   216  216  ...     216   216    176       214\n",
              "2               184       184   184  184  ...     184   184     16       184\n",
              "3               491       491   491  491  ...     491   491     12       491\n",
              "\n",
              "[3 rows x 11 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 295
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 171
        },
        "id": "oSio6hjjT-Us",
        "outputId": "57266781-a6a1-4867-aca6-18d557d9f965"
      },
      "source": [
        "titanic_groupby = titanic_df.groupby('Pclass')[['PassengerId','Survived']].count() # 대상컬럼만 count를 수행\r\n",
        "titanic_groupby"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Pclass</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>216</td>\n",
              "      <td>216</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>184</td>\n",
              "      <td>184</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>491</td>\n",
              "      <td>491</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "        PassengerId  Survived\n",
              "Pclass                       \n",
              "1               216       216\n",
              "2               184       184\n",
              "3               491       491"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 299
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hEDxTBa2VIBs"
      },
      "source": [
        "- aggregation 의 약자인 agg()함수를 통해 최댓값과 최솟값을 반환"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 171
        },
        "id": "E4ZzAGCXUn0v",
        "outputId": "5ef07486-b60a-4989-e68f-573cd7fdf484"
      },
      "source": [
        "titanic_df.groupby('Pclass')['Age'].agg(['max','min'])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>max</th>\n",
              "      <th>min</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Pclass</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>80.0</td>\n",
              "      <td>0.92</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>70.0</td>\n",
              "      <td>0.67</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>74.0</td>\n",
              "      <td>0.42</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "         max   min\n",
              "Pclass            \n",
              "1       80.0  0.92\n",
              "2       70.0  0.67\n",
              "3       74.0  0.42"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 301
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 171
        },
        "id": "xDey59_9VEpe",
        "outputId": "aef33013-2e73-4acb-e744-d635eba4bb3a"
      },
      "source": [
        "agg_format = {'Age':'max','SibSp':'sum','Fare':'mean'} # Age 컬럼은 최댓값, SibSp컬럼은 합계, 등 이런식으로도 활용 가능\r\n",
        "titanic_df.groupby('Pclass').agg(agg_format)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Fare</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Pclass</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>80.0</td>\n",
              "      <td>90</td>\n",
              "      <td>84.154687</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>70.0</td>\n",
              "      <td>74</td>\n",
              "      <td>20.662183</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>74.0</td>\n",
              "      <td>302</td>\n",
              "      <td>13.675550</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "         Age  SibSp       Fare\n",
              "Pclass                        \n",
              "1       80.0     90  84.154687\n",
              "2       70.0     74  20.662183\n",
              "3       74.0    302  13.675550"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 304
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NVwhwj6MV5Ft"
      },
      "source": [
        "**결손 데이터 처리하기**\r\n",
        "- 결측치 NULL인 경우를 의미 넘파이의 NaN으로 표시\r\n",
        "- isna() 를 통해 NaN 여부를 확인\r\n",
        "- NaN 값을 다른 값으로 대체하는 fillna() 도 있음"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LOQLaLDVVei8",
        "outputId": "1218906e-6fd5-4062-a0f4-91ae0744f00f"
      },
      "source": [
        "# isna()로 결손 데이터 여부 확인\r\n",
        "# 내가 알고 있는 방법 titanic_df.isnull().sum()\r\n",
        "titanic_df.isna().sum()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "PassengerId      0\n",
              "Survived         0\n",
              "Pclass           0\n",
              "Name             0\n",
              "Sex              0\n",
              "Age            177\n",
              "SibSp            0\n",
              "Parch            0\n",
              "Ticket           0\n",
              "Fare             0\n",
              "Cabin          687\n",
              "Embarked         2\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 307
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "LNyKTDvAXREW",
        "outputId": "875078b8-56bd-4002-ef64-3c99e8cd63f7"
      },
      "source": [
        "# fillna()로 결손 데이터 대체하기\r\n",
        "titanic_df['Cabin'] = titanic_df['Cabin'].fillna('C000')\r\n",
        "titanic_df.head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr....</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>C000</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mr...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, ...</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 31...</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>C000</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   PassengerId  Survived  Pclass  ...     Fare Cabin  Embarked\n",
              "0            1         0       3  ...   7.2500  C000         S\n",
              "1            2         1       1  ...  71.2833   C85         C\n",
              "2            3         1       3  ...   7.9250  C000         S\n",
              "\n",
              "[3 rows x 12 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 308
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "24yDWKVFYJDz"
      },
      "source": [
        "- fillna(결측치를 반환할 값, inplace = False)\r\n",
        "- drop() 참조 - inplace = True 설정하면 실제 데이터 세트 값이 변경"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pahFvY1zXnm4",
        "outputId": "bfe48eea-4921-4fe9-c9e3-f6d2fbdc8888"
      },
      "source": [
        "titanic_df['Age'] = titanic_df['Age'].fillna(titanic_df['Age'].mean()) # Age의 결측치는 -> 평균\r\n",
        "titanic_df['Embarked'] = titanic_df['Embarked'].fillna('S') # Embarked의 결측치는 -> S\r\n",
        "titanic_df.isna().sum()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "PassengerId    0\n",
              "Survived       0\n",
              "Pclass         0\n",
              "Name           0\n",
              "Sex            0\n",
              "Age            0\n",
              "SibSp          0\n",
              "Parch          0\n",
              "Ticket         0\n",
              "Fare           0\n",
              "Cabin          0\n",
              "Embarked       0\n",
              "dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 309
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "E3Z4imMKYkFb"
      },
      "source": [
        "**apply lambda 식으로 데이터 가공**\r\n",
        "- 복잡한 데이터를 가공할때 사용"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "l77GO_h9X5Ik",
        "outputId": "99b07d3b-78fa-45ef-b249-7eac6e33ddc0"
      },
      "source": [
        "# 예제\r\n",
        "def get_square(a):\r\n",
        "  return a**2\r\n",
        "\r\n",
        "print('3의 제곱은 :',get_square(3))\r\n",
        "# lambda를 사용해 이것을 한줄로 쉽게 변환 "
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "3의 제곱은 : 9\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TqFsvS7hY932",
        "outputId": "abd2fccf-8fb1-4699-e2e1-eebb5ee6dbbe"
      },
      "source": [
        "lambda_square = lambda x:x**2\r\n",
        "print('3의 제곱 :',lambda_square(3))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "3의 제곱 : 9\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MexOYuasZYp8"
      },
      "source": [
        "- lambda x:x**2에서 : 로 입력 인자와 반환될 입력 인자의 계산식을 분리\r\n",
        "- : 왼쪽에 있는 인자를 입력 인자 오른쪽을 반환 값(계산식)을 의미\r\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QbEKJwcBZUZL",
        "outputId": "86e09cfe-5003-4c15-9985-fb21dc5f7e66"
      },
      "source": [
        "a = [1,2,3]\r\n",
        "sqaures = map(lambda x:x**2,a) # 보통 여러 개의 값을 입력 인자로 사용해야 할 경우 map() 함수를 결합해서 사용\r\n",
        "list(sqaures)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[1, 4, 9]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 315
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141
        },
        "id": "ZchhdYA4Z1hf",
        "outputId": "045562a6-c74d-4f36-e680-4f12b6a0f32b"
      },
      "source": [
        "titanic_df['Name_len'] = titanic_df['Name'].apply(lambda x:len(x))\r\n",
        "titanic_df[['Name','Name_len']].head(3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Name</th>\n",
              "      <th>Name_len</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Braund, Mr....</td>\n",
              "      <td>23</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Cumings, Mr...</td>\n",
              "      <td>51</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Heikkinen, ...</td>\n",
              "      <td>22</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "             Name  Name_len\n",
              "0  Braund, Mr....        23\n",
              "1  Cumings, Mr...        51\n",
              "2  Heikkinen, ...        22"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 316
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 294
        },
        "id": "f9Q1EzcyaQjD",
        "outputId": "d365626c-17ce-4d30-fb42-680c4eacb75d"
      },
      "source": [
        "# lambda 식에서 if else 절을 사용해 조금 더 복잡한 가공 예제\r\n",
        "# 나이가 15세 미만이면 'chile', 아니면 'Adult' 구분하는 새로운 칼럼 'Child_Adult'를 apply,lambda를 이용해 만들기\r\n",
        "titanic_df['Child_Adult'] = titanic_df['Age'].apply(lambda x:'Child' if x < 15 else 'Adult')\r\n",
        "titanic_df[['Age','Child_Adult']].head(8)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Age</th>\n",
              "      <th>Child_Adult</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>22.000000</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>38.000000</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>26.000000</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>35.000000</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>35.000000</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>29.699118</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>54.000000</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>2.000000</td>\n",
              "      <td>Child</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "         Age Child_Adult\n",
              "0  22.000000       Adult\n",
              "1  38.000000       Adult\n",
              "2  26.000000       Adult\n",
              "3  35.000000       Adult\n",
              "4  35.000000       Adult\n",
              "5  29.699118       Adult\n",
              "6  54.000000       Adult\n",
              "7   2.000000       Child"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 318
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "X1oj9L5QbhIy"
      },
      "source": [
        "- lambda x : 'Child' if x < 15 else 'Adult'"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "guSlOsWXbMEG",
        "outputId": "ec1688d1-924b-4024-8bdf-cf3ff5111317"
      },
      "source": [
        "titanic_df['Age_cat'] = titanic_df['Age'].apply(lambda x:'Child' if x<15 else ('Adult' if x<=60 else 'Elderly'))\r\n",
        "titanic_df['Age_cat'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Adult      791\n",
              "Child       78\n",
              "Elderly     22\n",
              "Name: Age_cat, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 320
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 202
        },
        "id": "u5VIzmoOcEff",
        "outputId": "14dfe8bd-49df-47e5-8955-50d58804c1ff"
      },
      "source": [
        "# apply lamda  def 함수 생성 3가지 응용\r\n",
        "def get_category(age):\r\n",
        "  cat = ''\r\n",
        "  if age <= 5: cat = 'Baby'\r\n",
        "  elif age <=12: cat = 'Teenager'\r\n",
        "  elif age <= 18: cat = 'Student'\r\n",
        "  elif age <= 25: cat = 'Young Adult'\r\n",
        "  elif age <= 35: cat = 'Adult'\r\n",
        "  else: cat = 'Elderly'\r\n",
        "\r\n",
        "  return cat\r\n",
        "\r\n",
        "titanic_df['Age_cat'] = titanic_df['Age'].apply(lambda x:get_category(x))\r\n",
        "titanic_df[['Age','Age_cat']].head()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<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>Age</th>\n",
              "      <th>Age_cat</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>22.0</td>\n",
              "      <td>Young Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>38.0</td>\n",
              "      <td>Elderly</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>26.0</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>35.0</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>35.0</td>\n",
              "      <td>Adult</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "    Age      Age_cat\n",
              "0  22.0  Young Adult\n",
              "1  38.0      Elderly\n",
              "2  26.0        Adult\n",
              "3  35.0        Adult\n",
              "4  35.0        Adult"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 321
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "TmJKjbD_dHpC"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}