rapids-23-10-cudf-pandas-accelerator-mode-notebook.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "[**Bhavesh Bhatt - Link to my YouTube Channel**](https://www.youtube.com/BhaveshBhatt8791?sub_confirmation=1)"
      ],
      "metadata": {
        "id": "gIWKwPZ9oykZ"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Download the Dataset"
      ],
      "metadata": {
        "id": "uvIr81mtpWVK"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import locale\n",
        "locale.getpreferredencoding = lambda: \"UTF-8\""
      ],
      "metadata": {
        "id": "aDSrmBu8pFsY"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!wget \"http://eforexcel.com/wp/wp-content/uploads/2020/09/5m-Sales-Records.zip\""
      ],
      "metadata": {
        "id": "ytYYnX6_pFut",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "720b64c7-954e-472a-c50f-04a2e6d2ed46"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "--2023-10-31 04:38:16--  http://eforexcel.com/wp/wp-content/uploads/2020/09/5m-Sales-Records.zip\n",
            "Resolving eforexcel.com (eforexcel.com)... 162.214.80.24\n",
            "Connecting to eforexcel.com (eforexcel.com)|162.214.80.24|:80... connected.\n",
            "HTTP request sent, awaiting response... 301 Moved Permanently\n",
            "Location: https://eforexcel.com/wp/wp-content/uploads/2020/09/5m-Sales-Records.zip [following]\n",
            "--2023-10-31 04:38:16--  https://eforexcel.com/wp/wp-content/uploads/2020/09/5m-Sales-Records.zip\n",
            "Connecting to eforexcel.com (eforexcel.com)|162.214.80.24|:443... connected.\n",
            "HTTP request sent, awaiting response... 200 OK\n",
            "Length: 201708941 (192M) [application/zip]\n",
            "Saving to: ‘5m-Sales-Records.zip’\n",
            "\n",
            "5m-Sales-Records.zi 100%[===================>] 192.36M   109MB/s    in 1.8s    \n",
            "\n",
            "2023-10-31 04:38:18 (109 MB/s) - ‘5m-Sales-Records.zip’ saved [201708941/201708941]\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "import zipfile\n",
        "with zipfile.ZipFile(\"/content/5m-Sales-Records.zip\", 'r') as zip_ref:\n",
        "    zip_ref.extractall()"
      ],
      "metadata": {
        "id": "HHC-LGkmpJJz"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print (\"Size of file is {} MB\".format(os.path.getsize(\"/content/5m Sales Records.csv\") >> 20))"
      ],
      "metadata": {
        "id": "jrpv8OIUpJMl",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "2debbd2d-416b-4784-be62-8b4f4b2c1bb6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Size of file is 595 MB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Reading the Data"
      ],
      "metadata": {
        "id": "jj2fmr01qcxe"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd"
      ],
      "metadata": {
        "id": "mB3Msg_2b1Fw"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "%%time\n",
        "\n",
        "df = pd.read_csv(\"/content/5m Sales Records.csv\")\n",
        "print(df.head(3))"
      ],
      "metadata": {
        "id": "FiJ87QOciuf3",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "e4e9b7d9-ad2b-41fa-e202-a6664584d5e2"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "                  Region Country        Item Type Sales Channel  \\\n",
            "0  Australia and Oceania   Palau  Office Supplies        Online   \n",
            "1                 Europe  Poland        Beverages        Online   \n",
            "2          North America  Canada           Cereal        Online   \n",
            "\n",
            "  Order Priority Order Date   Order ID  Ship Date  Units Sold  Unit Price  \\\n",
            "0              H   3/6/2016  517073523  3/26/2016        2401      651.21   \n",
            "1              L  4/18/2010  380507028  5/26/2010        9340       47.45   \n",
            "2              M   1/8/2015  504055583  1/31/2015         103      205.70   \n",
            "\n",
            "   Unit Cost  Total Revenue  Total Cost  Total Profit  \n",
            "0     524.96     1563555.21  1260428.96     303126.25  \n",
            "1      31.79      443183.00   296918.60     146264.40  \n",
            "2     117.11       21187.10    12062.33       9124.77  \n",
            "CPU times: user 454 ms, sys: 73.1 ms, total: 527 ms\n",
            "Wall time: 522 ms\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Count across axis 0 and 1"
      ],
      "metadata": {
        "id": "uu_oVTx3qsIc"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%%cudf.pandas.line_profile\n",
        "\n",
        "print(df.count(axis = 0))"
      ],
      "metadata": {
        "id": "T_TfIVzAnE2r",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 856
        },
        "outputId": "011a059c-9ace-4342-8f66-ddd6bc0e8d17"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\n",
            "PYDEV DEBUGGER WARNING:\n",
            "sys.settrace() should not be used when the debugger is being used.\n",
            "This may cause the debugger to stop working correctly.\n",
            "If this is needed, please check: \n",
            "http://pydev.blogspot.com/2007/06/why-cant-pydev-debugger-work-with.html\n",
            "to see how to restore the debug tracing back correctly.\n",
            "Call Location:\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/cudf/pandas/profiler.py\", line 86, in __enter__\n",
            "    sys.settrace(self._tracefunc)\n",
            "\n",
            "\n",
            "PYDEV DEBUGGER WARNING:\n",
            "sys.settrace() should not be used when the debugger is being used.\n",
            "This may cause the debugger to stop working correctly.\n",
            "If this is needed, please check: \n",
            "http://pydev.blogspot.com/2007/06/why-cant-pydev-debugger-work-with.html\n",
            "to see how to restore the debug tracing back correctly.\n",
            "Call Location:\n",
            "  File \"/usr/local/lib/python3.10/dist-packages/cudf/pandas/profiler.py\", line 105, in __exit__\n",
            "    sys.settrace(self._oldtrace)\n",
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Region            5000000\n",
            "Country           5000000\n",
            "Item Type         5000000\n",
            "Sales Channel     5000000\n",
            "Order Priority    5000000\n",
            "Order Date        5000000\n",
            "Order ID          5000000\n",
            "Ship Date         5000000\n",
            "Units Sold        5000000\n",
            "Unit Price        5000000\n",
            "Unit Cost         5000000\n",
            "Total Revenue     5000000\n",
            "Total Cost        5000000\n",
            "Total Profit      5000000\n",
            "issue_weekday     5000000\n",
            "dtype: int64\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[3m                                                                        \u001b[0m\n",
              "\u001b[3m                       Total time elapsed: 0.302 seconds                \u001b[0m\n",
              "\u001b[3m                                                                        \u001b[0m\n",
              "\u001b[3m                                     Stats                              \u001b[0m\n",
              "\u001b[3m                                                                        \u001b[0m\n",
              "┏━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLine no.\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mLine                         \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mGPU TIME(s)\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mCPU TIME(s)\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩\n",
              "│ 2        │ \u001b[38;2;248;248;242;48;2;39;40;34m    \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mprint\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mdf\u001b[0m\u001b[38;2;255;70;137;48;2;39;40;34m.\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mcount\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34maxis\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;255;70;137;48;2;39;40;34m=\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;174;129;255;48;2;39;40;34m0\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m)\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m)\u001b[0m │ 0.012429260 │             │\n",
              "│          │ \u001b[48;2;39;40;34m                             \u001b[0m │             │             │\n",
              "└──────────┴───────────────────────────────┴─────────────┴─────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-style: italic\">                                                                        </span>\n",
              "<span style=\"font-style: italic\">                       Total time elapsed: 0.302 seconds                </span>\n",
              "<span style=\"font-style: italic\">                                                                        </span>\n",
              "<span style=\"font-style: italic\">                                     Stats                              </span>\n",
              "<span style=\"font-style: italic\">                                                                        </span>\n",
              "┏━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Line no. </span>┃<span style=\"font-weight: bold\"> Line                          </span>┃<span style=\"font-weight: bold\"> GPU TIME(s) </span>┃<span style=\"font-weight: bold\"> CPU TIME(s) </span>┃\n",
              "┡━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩\n",
              "│ 2        │ <span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">    print(df</span><span style=\"color: #ff4689; text-decoration-color: #ff4689; background-color: #272822\">.</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">count(axis </span><span style=\"color: #ff4689; text-decoration-color: #ff4689; background-color: #272822\">=</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\"> </span><span style=\"color: #ae81ff; text-decoration-color: #ae81ff; background-color: #272822\">0</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">))</span> │ 0.012429260 │             │\n",
              "│          │ <span style=\"background-color: #272822\">                             </span> │             │             │\n",
              "└──────────┴───────────────────────────────┴─────────────┴─────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "%%cudf.pandas.line_profile\n",
        "\n",
        "print(df.count(axis = 1))"
      ],
      "metadata": {
        "id": "0ofN-6qgqrbN",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 405
        },
        "outputId": "4b8f0347-a0f1-4ad3-de2a-b58b26fc5029"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0          15\n",
            "1          15\n",
            "2          15\n",
            "3          15\n",
            "4          15\n",
            "           ..\n",
            "4999995    15\n",
            "4999996    15\n",
            "4999997    15\n",
            "4999998    15\n",
            "4999999    15\n",
            "Length: 5000000, dtype: int64\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[3m                                                                         \u001b[0m\n",
              "\u001b[3m                       Total time elapsed: 11.502 seconds                \u001b[0m\n",
              "\u001b[3m                                                                         \u001b[0m\n",
              "\u001b[3m                                      Stats                              \u001b[0m\n",
              "\u001b[3m                                                                         \u001b[0m\n",
              "┏━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLine no.\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mLine                         \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mGPU TIME(s)\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mCPU TIME(s) \u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━┩\n",
              "│ 2        │ \u001b[38;2;248;248;242;48;2;39;40;34m    \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mprint\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mdf\u001b[0m\u001b[38;2;255;70;137;48;2;39;40;34m.\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mcount\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34maxis\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;255;70;137;48;2;39;40;34m=\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;174;129;255;48;2;39;40;34m1\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m)\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m)\u001b[0m │ 0.275502605 │ 11.097853014 │\n",
              "│          │ \u001b[48;2;39;40;34m                             \u001b[0m │             │              │\n",
              "└──────────┴───────────────────────────────┴─────────────┴──────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-style: italic\">                                                                         </span>\n",
              "<span style=\"font-style: italic\">                       Total time elapsed: 11.502 seconds                </span>\n",
              "<span style=\"font-style: italic\">                                                                         </span>\n",
              "<span style=\"font-style: italic\">                                      Stats                              </span>\n",
              "<span style=\"font-style: italic\">                                                                         </span>\n",
              "┏━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Line no. </span>┃<span style=\"font-weight: bold\"> Line                          </span>┃<span style=\"font-weight: bold\"> GPU TIME(s) </span>┃<span style=\"font-weight: bold\"> CPU TIME(s)  </span>┃\n",
              "┡━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━┩\n",
              "│ 2        │ <span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">    print(df</span><span style=\"color: #ff4689; text-decoration-color: #ff4689; background-color: #272822\">.</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">count(axis </span><span style=\"color: #ff4689; text-decoration-color: #ff4689; background-color: #272822\">=</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\"> </span><span style=\"color: #ae81ff; text-decoration-color: #ae81ff; background-color: #272822\">1</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">))</span> │ 0.275502605 │ 11.097853014 │\n",
              "│          │ <span style=\"background-color: #272822\">                             </span> │             │              │\n",
              "└──────────┴───────────────────────────────┴─────────────┴──────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.head(3)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 233
        },
        "id": "jjHRd8O9EO5D",
        "outputId": "02dd84be-4d75-4e8d-c5b0-db8f7796fc1c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                  Region Country        Item Type Sales Channel  \\\n",
              "0  Australia and Oceania   Palau  Office Supplies        Online   \n",
              "1                 Europe  Poland        Beverages        Online   \n",
              "2          North America  Canada           Cereal        Online   \n",
              "\n",
              "  Order Priority Order Date   Order ID  Ship Date  Units Sold  Unit Price  \\\n",
              "0              H   3/6/2016  517073523  3/26/2016        2401      651.21   \n",
              "1              L  4/18/2010  380507028  5/26/2010        9340       47.45   \n",
              "2              M   1/8/2015  504055583  1/31/2015         103      205.70   \n",
              "\n",
              "   Unit Cost  Total Revenue  Total Cost  Total Profit  \n",
              "0     524.96     1563555.21  1260428.96     303126.25  \n",
              "1      31.79      443183.00   296918.60     146264.40  \n",
              "2     117.11       21187.10    12062.33       9124.77  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-2d03f1ec-d29d-46bb-941c-d7348fe40bd1\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Region</th>\n",
              "      <th>Country</th>\n",
              "      <th>Item Type</th>\n",
              "      <th>Sales Channel</th>\n",
              "      <th>Order Priority</th>\n",
              "      <th>Order Date</th>\n",
              "      <th>Order ID</th>\n",
              "      <th>Ship Date</th>\n",
              "      <th>Units Sold</th>\n",
              "      <th>Unit Price</th>\n",
              "      <th>Unit Cost</th>\n",
              "      <th>Total Revenue</th>\n",
              "      <th>Total Cost</th>\n",
              "      <th>Total Profit</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Australia and Oceania</td>\n",
              "      <td>Palau</td>\n",
              "      <td>Office Supplies</td>\n",
              "      <td>Online</td>\n",
              "      <td>H</td>\n",
              "      <td>3/6/2016</td>\n",
              "      <td>517073523</td>\n",
              "      <td>3/26/2016</td>\n",
              "      <td>2401</td>\n",
              "      <td>651.21</td>\n",
              "      <td>524.96</td>\n",
              "      <td>1563555.21</td>\n",
              "      <td>1260428.96</td>\n",
              "      <td>303126.25</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Europe</td>\n",
              "      <td>Poland</td>\n",
              "      <td>Beverages</td>\n",
              "      <td>Online</td>\n",
              "      <td>L</td>\n",
              "      <td>4/18/2010</td>\n",
              "      <td>380507028</td>\n",
              "      <td>5/26/2010</td>\n",
              "      <td>9340</td>\n",
              "      <td>47.45</td>\n",
              "      <td>31.79</td>\n",
              "      <td>443183.00</td>\n",
              "      <td>296918.60</td>\n",
              "      <td>146264.40</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>North America</td>\n",
              "      <td>Canada</td>\n",
              "      <td>Cereal</td>\n",
              "      <td>Online</td>\n",
              "      <td>M</td>\n",
              "      <td>1/8/2015</td>\n",
              "      <td>504055583</td>\n",
              "      <td>1/31/2015</td>\n",
              "      <td>103</td>\n",
              "      <td>205.70</td>\n",
              "      <td>117.11</td>\n",
              "      <td>21187.10</td>\n",
              "      <td>12062.33</td>\n",
              "      <td>9124.77</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-2d03f1ec-d29d-46bb-941c-d7348fe40bd1')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-2d03f1ec-d29d-46bb-941c-d7348fe40bd1 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-2d03f1ec-d29d-46bb-941c-d7348fe40bd1');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-8c5d9891-d505-4560-96ea-f32f86ba7249\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-8c5d9891-d505-4560-96ea-f32f86ba7249')\"\n",
              "            title=\"Suggest charts.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-8c5d9891-d505-4560-96ea-f32f86ba7249 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# How many item types are there across different countries and regions?"
      ],
      "metadata": {
        "id": "jz8h2E9qsmje"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%%cudf.pandas.line_profile\n",
        "\n",
        "(df[[\"Region\", \"Country\", \"Item Type\"]]\n",
        " .value_counts() # Calculate the frequency (count) of unique combinations of \"Region,\" \"Country,\" and \"Item Type\"\n",
        " .groupby([\"Region\", \"Country\"]) # Group the data based on the columns \"Region\" and \"Country\"\n",
        " .head(1) # Select the first row within each group, which represents the most common combination\n",
        " .sort_index() # Sort the resulting DataFrame based on its index, which likely includes \"Region\" and \"Country\"\n",
        " .reset_index() # Reset the index to default sequential integer indices\n",
        ")"
      ],
      "metadata": {
        "id": "WVeZi-2BjQqS",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 360
        },
        "outputId": "b9d932d1-0a4b-4b60-8b47-94d0de0810fc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[3m                                                                                                                   \u001b[0m\n",
              "\u001b[3m                                             Total time elapsed: 0.648 seconds                                     \u001b[0m\n",
              "\u001b[3m                                                                                                                   \u001b[0m\n",
              "\u001b[3m                                                           Stats                                                   \u001b[0m\n",
              "\u001b[3m                                                                                                                   \u001b[0m\n",
              "┏━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLine no.\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mLine                                                                    \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mGPU TIME(s)\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mCPU TIME(s)\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩\n",
              "│ 2        │ \u001b[38;2;248;248;242;48;2;39;40;34m    \u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mdf\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m[\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m[\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34mRegion\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m,\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34mCountry\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m,\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34mItem Type\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m]\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m]\u001b[0m\u001b[48;2;39;40;34m                             \u001b[0m │ 0.005705814 │             │\n",
              "│          │ \u001b[48;2;39;40;34m                                                                        \u001b[0m │             │             │\n",
              "│ 3        │ \u001b[38;2;248;248;242;48;2;39;40;34m     \u001b[0m\u001b[38;2;255;70;137;48;2;39;40;34m.\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mvalue_counts\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m)\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;149;144;119;48;2;39;40;34m# Calculate the frequency (count) of unique combin…\u001b[0m │ 0.123669495 │             │\n",
              "│          │ \u001b[48;2;39;40;34m                                                                        \u001b[0m │             │             │\n",
              "│ 4        │ \u001b[38;2;248;248;242;48;2;39;40;34m     \u001b[0m\u001b[38;2;255;70;137;48;2;39;40;34m.\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mgroupby\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m[\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34mRegion\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m,\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34mCountry\u001b[0m\u001b[38;2;230;219;116;48;2;39;40;34m\"\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m]\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m)\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;149;144;119;48;2;39;40;34m# Group the data based on the colu…\u001b[0m │ 0.000957324 │             │\n",
              "│          │ \u001b[48;2;39;40;34m                                                                        \u001b[0m │             │             │\n",
              "│ 5        │ \u001b[38;2;248;248;242;48;2;39;40;34m     \u001b[0m\u001b[38;2;255;70;137;48;2;39;40;34m.\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mhead\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;174;129;255;48;2;39;40;34m1\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m)\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;149;144;119;48;2;39;40;34m# Select the first row within each group, which represent…\u001b[0m │ 0.077215984 │             │\n",
              "│          │ \u001b[48;2;39;40;34m                                                                        \u001b[0m │             │             │\n",
              "│ 6        │ \u001b[38;2;248;248;242;48;2;39;40;34m     \u001b[0m\u001b[38;2;255;70;137;48;2;39;40;34m.\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34msort_index\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m)\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;149;144;119;48;2;39;40;34m# Sort the resulting DataFrame based on its index, w…\u001b[0m │ 0.012782164 │             │\n",
              "│          │ \u001b[48;2;39;40;34m                                                                        \u001b[0m │             │             │\n",
              "│ 7        │ \u001b[38;2;248;248;242;48;2;39;40;34m     \u001b[0m\u001b[38;2;255;70;137;48;2;39;40;34m.\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34mreset_index\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m(\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m)\u001b[0m\u001b[38;2;248;248;242;48;2;39;40;34m \u001b[0m\u001b[38;2;149;144;119;48;2;39;40;34m# Reset the index to default sequential integer ind…\u001b[0m │ 0.000991515 │             │\n",
              "│          │ \u001b[48;2;39;40;34m                                                                        \u001b[0m │             │             │\n",
              "└──────────┴──────────────────────────────────────────────────────────────────────────┴─────────────┴─────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-style: italic\">                                                                                                                   </span>\n",
              "<span style=\"font-style: italic\">                                             Total time elapsed: 0.648 seconds                                     </span>\n",
              "<span style=\"font-style: italic\">                                                                                                                   </span>\n",
              "<span style=\"font-style: italic\">                                                           Stats                                                   </span>\n",
              "<span style=\"font-style: italic\">                                                                                                                   </span>\n",
              "┏━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Line no. </span>┃<span style=\"font-weight: bold\"> Line                                                                     </span>┃<span style=\"font-weight: bold\"> GPU TIME(s) </span>┃<span style=\"font-weight: bold\"> CPU TIME(s) </span>┃\n",
              "┡━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩\n",
              "│ 2        │ <span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">    (df[[</span><span style=\"color: #e6db74; text-decoration-color: #e6db74; background-color: #272822\">\"Region\"</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">, </span><span style=\"color: #e6db74; text-decoration-color: #e6db74; background-color: #272822\">\"Country\"</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">, </span><span style=\"color: #e6db74; text-decoration-color: #e6db74; background-color: #272822\">\"Item Type\"</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">]]</span><span style=\"background-color: #272822\">                             </span> │ 0.005705814 │             │\n",
              "│          │ <span style=\"background-color: #272822\">                                                                        </span> │             │             │\n",
              "│ 3        │ <span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">     </span><span style=\"color: #ff4689; text-decoration-color: #ff4689; background-color: #272822\">.</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">value_counts() </span><span style=\"color: #959077; text-decoration-color: #959077; background-color: #272822\"># Calculate the frequency (count) of unique combin…</span> │ 0.123669495 │             │\n",
              "│          │ <span style=\"background-color: #272822\">                                                                        </span> │             │             │\n",
              "│ 4        │ <span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">     </span><span style=\"color: #ff4689; text-decoration-color: #ff4689; background-color: #272822\">.</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">groupby([</span><span style=\"color: #e6db74; text-decoration-color: #e6db74; background-color: #272822\">\"Region\"</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">, </span><span style=\"color: #e6db74; text-decoration-color: #e6db74; background-color: #272822\">\"Country\"</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">]) </span><span style=\"color: #959077; text-decoration-color: #959077; background-color: #272822\"># Group the data based on the colu…</span> │ 0.000957324 │             │\n",
              "│          │ <span style=\"background-color: #272822\">                                                                        </span> │             │             │\n",
              "│ 5        │ <span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">     </span><span style=\"color: #ff4689; text-decoration-color: #ff4689; background-color: #272822\">.</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">head(</span><span style=\"color: #ae81ff; text-decoration-color: #ae81ff; background-color: #272822\">1</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">) </span><span style=\"color: #959077; text-decoration-color: #959077; background-color: #272822\"># Select the first row within each group, which represent…</span> │ 0.077215984 │             │\n",
              "│          │ <span style=\"background-color: #272822\">                                                                        </span> │             │             │\n",
              "│ 6        │ <span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">     </span><span style=\"color: #ff4689; text-decoration-color: #ff4689; background-color: #272822\">.</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">sort_index() </span><span style=\"color: #959077; text-decoration-color: #959077; background-color: #272822\"># Sort the resulting DataFrame based on its index, w…</span> │ 0.012782164 │             │\n",
              "│          │ <span style=\"background-color: #272822\">                                                                        </span> │             │             │\n",
              "│ 7        │ <span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">     </span><span style=\"color: #ff4689; text-decoration-color: #ff4689; background-color: #272822\">.</span><span style=\"color: #f8f8f2; text-decoration-color: #f8f8f2; background-color: #272822\">reset_index() </span><span style=\"color: #959077; text-decoration-color: #959077; background-color: #272822\"># Reset the index to default sequential integer ind…</span> │ 0.000991515 │             │\n",
              "│          │ <span style=\"background-color: #272822\">                                                                        </span> │             │             │\n",
              "└──────────┴──────────────────────────────────────────────────────────────────────────┴─────────────┴─────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "C9TtGpmOENfP"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# What is the cumulative units sold across all countries?"
      ],
      "metadata": {
        "id": "fUQi8IELs3im"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%%time\n",
        "\n",
        "# Group the DataFrame df by the \"Country\" column\n",
        "(df\n",
        " .groupby([\"Country\"])\n",
        " .agg({\"Units Sold\": \"sum\"}) # Aggregate the grouped data by summing the \"Units Sold\" values for each country\n",
        " .rename(columns={\"Units Sold\": \"sum of units sold\"}) # Rename the \"Units Sold\" column to \"sum of units sold\" in the resulting DataFrame\n",
        " .sort_values([\"sum of units sold\"], ascending=False) # Sort the resulting DataFrame based on the \"sum of units sold\" column in descending order\n",
        ")"
      ],
      "metadata": {
        "id": "Araiy6GNjQsr",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 490
        },
        "outputId": "dbf5f937-0d26-407c-dd25-e74733d39208"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "CPU times: user 15.2 ms, sys: 4.89 ms, total: 20.1 ms\n",
            "Wall time: 23.3 ms\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                sum of units sold\n",
              "Country                                          \n",
              "Liberia                                 136188169\n",
              "Afghanistan                             135941343\n",
              "Federated States of Micronesia          135898227\n",
              "Cote d'Ivoire                           135885228\n",
              "Laos                                    135839983\n",
              "...                                           ...\n",
              "Vatican City                            134515340\n",
              "Lithuania                               134493249\n",
              "Qatar                                   134483291\n",
              "Nicaragua                               134474776\n",
              "Belarus                                 134313188\n",
              "\n",
              "[185 rows x 1 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-64f13ea3-ad0f-4551-8a0c-18b6f27ea615\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>sum of units sold</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Country</th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>Liberia</th>\n",
              "      <td>136188169</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Afghanistan</th>\n",
              "      <td>135941343</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Federated States of Micronesia</th>\n",
              "      <td>135898227</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Cote d'Ivoire</th>\n",
              "      <td>135885228</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Laos</th>\n",
              "      <td>135839983</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Vatican City</th>\n",
              "      <td>134515340</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Lithuania</th>\n",
              "      <td>134493249</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Qatar</th>\n",
              "      <td>134483291</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Nicaragua</th>\n",
              "      <td>134474776</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Belarus</th>\n",
              "      <td>134313188</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>185 rows × 1 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-64f13ea3-ad0f-4551-8a0c-18b6f27ea615')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-64f13ea3-ad0f-4551-8a0c-18b6f27ea615 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-64f13ea3-ad0f-4551-8a0c-18b6f27ea615');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-bc4c6ebc-d475-4702-9fbb-98e526effe09\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-bc4c6ebc-d475-4702-9fbb-98e526effe09')\"\n",
              "            title=\"Suggest charts.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-bc4c6ebc-d475-4702-9fbb-98e526effe09 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# How do units sold vary across days of the week?"
      ],
      "metadata": {
        "id": "OCKTpyIEtW-E"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "%%time\n",
        "\n",
        "weekday_names = {\n",
        "    0: \"Monday\",\n",
        "    1: \"Tuesday\",\n",
        "    2: \"Wednesday\",\n",
        "    3: \"Thursday\",\n",
        "    4: \"Friday\",\n",
        "    5: \"Saturday\",\n",
        "    6: \"Sunday\",\n",
        "}\n",
        "\n",
        "df[\"Ship Date\"] = df[\"Ship Date\"].astype(\"datetime64[ms]\")\n",
        "df[\"issue_weekday\"] = df[\"Ship Date\"].dt.weekday.map(weekday_names)\n",
        "\n",
        "df.groupby([\"Country\", \"issue_weekday\"])[\"Units Sold\"].sum()"
      ],
      "metadata": {
        "id": "vgAXKzEbjQvg",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "09baa7ba-e27c-40e2-ce03-2576b0d0ddd9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "CPU times: user 66.6 ms, sys: 25 ms, total: 91.6 ms\n",
            "Wall time: 92.4 ms\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Country      issue_weekday\n",
              "Afghanistan  Friday           19216920\n",
              "             Monday           19430838\n",
              "             Saturday         19736117\n",
              "             Sunday           19828726\n",
              "             Thursday         19520373\n",
              "                                ...   \n",
              "Zimbabwe     Saturday         19366713\n",
              "             Sunday           19821497\n",
              "             Thursday         18869024\n",
              "             Tuesday          19120642\n",
              "             Wednesday        19149278\n",
              "Name: Units Sold, Length: 1295, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "7AsZPnaojQyE"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "kcF9ZWvjSybR"
      },
      "source": [
        "# RAPIDS cuDF's pandas accelerator mode\n",
        "\n",
        "cuDF is a Python GPU DataFrame library (built on the Apache Arrow columnar memory format) for loading, joining, aggregating, filtering, and otherwise manipulating tabular data using a DataFrame style API in the style of pandas.\n",
        "\n",
        "cuDF now provides a pandas accelerator mode allowing you to bring accelerated computing to your pandas workflows without requiring any code change."
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Installing cuDF"
      ],
      "metadata": {
        "id": "y8x-KvrUqM1M"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "metadata": {
        "id": "TGEQqaqjaOhy",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ea9bed98-d80a-4b5d-bfae-f41247edc95d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install cudf-cu11 --extra-index-url=https://pypi.nvidia.com"
      ],
      "metadata": {
        "id": "IUi6nNHgba5J",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "9910c56c-cd48-4f0b-8c00-1ff4a264bd97"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://pypi.nvidia.com\n",
            "Collecting cudf-cu11\n",
            "  Downloading https://pypi.nvidia.com/cudf-cu11/cudf_cu11-23.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (502.5 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m502.5/502.5 MB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: cachetools in /usr/local/lib/python3.10/dist-packages (from cudf-cu11) (5.3.2)\n",
            "Collecting cubinlinker-cu11 (from cudf-cu11)\n",
            "  Downloading https://pypi.nvidia.com/cubinlinker-cu11/cubinlinker_cu11-0.3.0.post1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.8/8.8 MB\u001b[0m \u001b[31m78.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting cuda-python<12.0a0,>=11.7.1 (from cudf-cu11)\n",
            "  Downloading cuda_python-11.8.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.7 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.7/18.7 MB\u001b[0m \u001b[31m84.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting cupy-cuda11x>=12.0.0 (from cudf-cu11)\n",
            "  Downloading cupy_cuda11x-12.2.0-cp310-cp310-manylinux2014_x86_64.whl (89.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m89.6/89.6 MB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: fsspec>=0.6.0 in /usr/local/lib/python3.10/dist-packages (from cudf-cu11) (2023.6.0)\n",
            "Collecting numba<0.58,>=0.57 (from cudf-cu11)\n",
            "  Downloading numba-0.57.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (3.6 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m85.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: numpy<1.25,>=1.21 in /usr/local/lib/python3.10/dist-packages (from cudf-cu11) (1.23.5)\n",
            "Collecting nvtx>=0.2.1 (from cudf-cu11)\n",
            "  Downloading nvtx-0.2.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (582 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m582.4/582.4 kB\u001b[0m \u001b[31m54.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from cudf-cu11) (23.2)\n",
            "Requirement already satisfied: pandas<1.6.0dev0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from cudf-cu11) (1.5.3)\n",
            "Collecting protobuf<5,>=4.21 (from cudf-cu11)\n",
            "  Downloading protobuf-4.24.4-cp37-abi3-manylinux2014_x86_64.whl (311 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m311.6/311.6 kB\u001b[0m \u001b[31m35.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting ptxcompiler-cu11 (from cudf-cu11)\n",
            "  Downloading https://pypi.nvidia.com/ptxcompiler-cu11/ptxcompiler_cu11-0.7.0.post1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (8.8 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.8/8.8 MB\u001b[0m \u001b[31m105.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting pyarrow==12.* (from cudf-cu11)\n",
            "  Downloading pyarrow-12.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (38.9 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.9/38.9 MB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hCollecting rmm-cu11==23.10.* (from cudf-cu11)\n",
            "  Downloading https://pypi.nvidia.com/rmm-cu11/rmm_cu11-23.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.0 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m92.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: typing-extensions>=4.0.0 in /usr/local/lib/python3.10/dist-packages (from cudf-cu11) (4.5.0)\n",
            "Requirement already satisfied: fastrlock>=0.5 in /usr/local/lib/python3.10/dist-packages (from cupy-cuda11x>=12.0.0->cudf-cu11) (0.8.2)\n",
            "Collecting llvmlite<0.41,>=0.40.0dev0 (from numba<0.58,>=0.57->cudf-cu11)\n",
            "  Downloading llvmlite-0.40.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (42.1 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m42.1/42.1 MB\u001b[0m \u001b[31m15.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas<1.6.0dev0,>=1.3->cudf-cu11) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<1.6.0dev0,>=1.3->cudf-cu11) (2023.3.post1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas<1.6.0dev0,>=1.3->cudf-cu11) (1.16.0)\n",
            "Installing collected packages: ptxcompiler-cu11, nvtx, cuda-python, cubinlinker-cu11, pyarrow, protobuf, llvmlite, cupy-cuda11x, numba, rmm-cu11, cudf-cu11\n",
            "  Attempting uninstall: pyarrow\n",
            "    Found existing installation: pyarrow 9.0.0\n",
            "    Uninstalling pyarrow-9.0.0:\n",
            "      Successfully uninstalled pyarrow-9.0.0\n",
            "  Attempting uninstall: protobuf\n",
            "    Found existing installation: protobuf 3.20.3\n",
            "    Uninstalling protobuf-3.20.3:\n",
            "      Successfully uninstalled protobuf-3.20.3\n",
            "  Attempting uninstall: llvmlite\n",
            "    Found existing installation: llvmlite 0.39.1\n",
            "    Uninstalling llvmlite-0.39.1:\n",
            "      Successfully uninstalled llvmlite-0.39.1\n",
            "  Attempting uninstall: cupy-cuda11x\n",
            "    Found existing installation: cupy-cuda11x 11.0.0\n",
            "    Uninstalling cupy-cuda11x-11.0.0:\n",
            "      Successfully uninstalled cupy-cuda11x-11.0.0\n",
            "  Attempting uninstall: numba\n",
            "    Found existing installation: numba 0.56.4\n",
            "    Uninstalling numba-0.56.4:\n",
            "      Successfully uninstalled numba-0.56.4\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "pandas-gbq 0.17.9 requires pyarrow<10.0dev,>=3.0.0, but you have pyarrow 12.0.1 which is incompatible.\n",
            "tensorflow-metadata 1.14.0 requires protobuf<4.21,>=3.20.3, but you have protobuf 4.24.4 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0mSuccessfully installed cubinlinker-cu11-0.3.0.post1 cuda-python-11.8.3 cudf-cu11-23.10.0 cupy-cuda11x-12.2.0 llvmlite-0.40.1 numba-0.57.1 nvtx-0.2.8 protobuf-4.24.4 ptxcompiler-cu11-0.7.0.post1 pyarrow-12.0.1 rmm-cu11-23.10.0\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.colab-display-data+json": {
              "pip_warning": {
                "packages": [
                  "pyarrow"
                ]
              }
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install -q \"/content/drive/MyDrive/Temp/cudf_private_cu11-23.10.0.231024-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl\""
      ],
      "metadata": {
        "id": "X22MflK0ZosT"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SH_h6ci1Sx0u"
      },
      "source": [
        "# GPU & cuDF Check"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Y2vPCtXcCvUR",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "da6913fb-0291-41b0-cd20-4993d2346d55"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Tue Oct 31 05:01:38 2023       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 525.105.17   Driver Version: 525.105.17   CUDA Version: 12.0     |\n",
            "|-------------------------------+----------------------+----------------------+\n",
            "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
            "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
            "|                               |                      |               MIG M. |\n",
            "|===============================+======================+======================|\n",
            "|   0  Tesla T4            Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   35C    P8     9W /  70W |      0MiB / 15360MiB |      0%      Default |\n",
            "|                               |                      |                  N/A |\n",
            "+-------------------------------+----------------------+----------------------+\n",
            "                                                                               \n",
            "+-----------------------------------------------------------------------------+\n",
            "| Processes:                                                                  |\n",
            "|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |\n",
            "|        ID   ID                                                   Usage      |\n",
            "|=============================================================================|\n",
            "|  No running processes found                                                 |\n",
            "+-----------------------------------------------------------------------------+\n"
          ]
        }
      ],
      "source": [
        "!nvidia-smi  # this should display information about available GPUs"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "zhPt4Xj8THgo"
      },
      "outputs": [],
      "source": [
        "import cudf  # this should work without any errors"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "get_ipython().kernel.do_shutdown(restart=True)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tvLhmfmmckrI",
        "outputId": "c4aa0967-87a4-4de1-be05-f1d0e01aa1fa"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'status': 'ok', 'restart': True}"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "%load_ext cudf.pandas"
      ],
      "metadata": {
        "id": "CpcooWkeclIt"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "28kTiptHHPhI"
      },
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": [],
      "collapsed_sections": [
        "uvIr81mtpWVK",
        "jj2fmr01qcxe",
        "jz8h2E9qsmje",
        "uu_oVTx3qsIc",
        "fUQi8IELs3im",
        "OCKTpyIEtW-E",
        "y8x-KvrUqM1M",
        "SH_h6ci1Sx0u"
      ]
    },
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.10.12"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}