163 lines (162 with data), 3.5 kB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "308eca10",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "586edd82",
   "metadata": {},
   "source": [
    "## Downloading MACCROBAT_DATA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "3ac872ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "MACCROBAT_DATA_URL = \"https://figshare.com/ndownloader/files/17493650\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "03dca362",
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "\n",
    "def download_zip_from_url(url, save_path, chunk_size=128):\n",
    "    r = requests.get(url, stream=True)\n",
    "    with open(save_path, 'wb') as fd:\n",
    "        for chunk in r.iter_content(chunk_size=chunk_size):\n",
    "            fd.write(chunk)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "f8dd4c16",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_zipfile = \"../data/MACCROBAT2018.zip\"\n",
    "MACCROBAT_data_dir = \"../data/MACCROBAT\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "29bfcbd2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Directory '../data/MACCROBAT' created.\n"
     ]
    }
   ],
   "source": [
    "if not os.path.exists(MACCROBAT_data_dir):\n",
    "    os.makedirs(MACCROBAT_data_dir)\n",
    "    print(f\"Directory '{MACCROBAT_data_dir}' created.\")\n",
    "else:\n",
    "    print(f\"Directory '{MACCROBAT_data_dir}' already exists.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "d75e5ad8",
   "metadata": {},
   "outputs": [],
   "source": [
    "download_zip_from_url(MACCROBAT_DATA_URL, data_zipfile)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "7dcfb4b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import zipfile\n",
    "with zipfile.ZipFile(data_zipfile, 'r') as zip_ref:\n",
    "    zip_ref.extractall(MACCROBAT_data_dir)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "880dd367",
   "metadata": {},
   "outputs": [],
   "source": [
    "os.remove(data_zipfile)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "5baefc11",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of txt files corresponding with ann files is 200\n"
     ]
    }
   ],
   "source": [
    "\n",
    "print(f\"Number of txt files corresponding with ann files is\\\n",
    " {len([file for file in os.listdir(MACCROBAT_data_dir) if file.endswith('.txt') and file.split('.')[0]+ '.ann' in os.listdir(MACCROBAT_data_dir)])}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d6a58508",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}