pathlib_path.ipynb

pathlib_path.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "pathlib_path.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyPGzOqbZgZcj0PjzSRzTU+H",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/fastdaima/4b1093d1ecbfa3224678c23c077f37fa/pathlib_path.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2GGmWRFohbBc",
        "outputId": "6bafdb17-7eed-40fd-f807-edec041ac819"
      },
      "source": [
        "!pip install fastai -Uq"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[K     |████████████████████████████████| 189 kB 5.4 MB/s \n",
            "\u001b[K     |████████████████████████████████| 56 kB 4.5 MB/s \n",
            "\u001b[?25h"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IB6moqcxhe2U"
      },
      "source": [
        "from fastai.vision.all import *"
      ],
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zkWH7vSphCby"
      },
      "source": [
        "## Issue 1"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6YxWFHVqf2eU"
      },
      "source": [
        "from pathlib import Path"
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "08Dgpr4HgCOX"
      },
      "source": [
        "path = Path('bears')"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2MmcC8BRgI6T",
        "outputId": "fe241c79-ce93-4a40-eb69-7e3b6945576c"
      },
      "source": [
        "path"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "PosixPath('bears')"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1MdbE-gUgJu0",
        "outputId": "78c6e6a8-b953-42e6-9c75-3ab4d44fec4d"
      },
      "source": [
        "%ls"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[0m\u001b[01;34msample_data\u001b[0m/\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "FlJIWd9VgO71",
        "outputId": "d9e3bb40-ad48-4d53-8d06-18b353d7181a"
      },
      "source": [
        "path.exists()"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "False"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Eh0lhxpbgfcN"
      },
      "source": [
        "`Path('dir_name')` only creates posixpath object, it will not create directory "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "K2Tl7iMHgZeI"
      },
      "source": [
        "if not path.exists(): path.mkdir()"
      ],
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2CUwLEu3g2Jk",
        "outputId": "91bf8141-0677-4f12-d1ac-1a7a5159aeea"
      },
      "source": [
        "%ls"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[0m\u001b[01;34mbears\u001b[0m/  \u001b[01;34msample_data\u001b[0m/\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xIs-CUp5g3PM",
        "outputId": "4dfd5ee4-3963-488f-c076-139029340fe2"
      },
      "source": [
        "path.exists()"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "True"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "V6aQvik0hx8_"
      },
      "source": [
        "## Issue 2"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DJ9u0Vl1g5i7"
      },
      "source": [
        "??download_images"
      ],
      "execution_count": 12,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "2PLK_q-rh0Wl"
      },
      "source": [
        "def download_images(dest, url_file=None, urls=None, max_pics=1000, n_workers=8, timeout=4, preserve_filename=False):\n",
        "    \"Download images listed in text file `url_file` to path `dest`, at most `max_pics`\"\n",
        "    if urls is None: urls = url_file.read_text().strip().split(\"\\n\")[:max_pics]\n",
        "    dest = Path(dest)\n",
        "    dest.mkdir(exist_ok=True)\n",
        "    parallel(partial(_download_image_inner, dest, timeout=timeout, preserve_filename=preserve_filename),\n",
        "             list(enumerate(urls)), n_workers=n_workers, threadpool=True)"
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jXXMtSa-h8Tl"
      },
      "source": [
        "* On download image function, line 5 the directory will be created if destination folder is not present\n",
        "\n",
        "* so eventhough when you comment the mkdir line, on download_images function, the destination path is created.\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "eeCFXiKRh5YI"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}