70 lines (69 with data), 1.5 kB

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8468ad0d",
   "metadata": {},
   "source": [
    "# Undersampling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "cfc764c8",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1694\n",
      "Done\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import random\n",
    "import shutil\n",
    "\n",
    "source = r\"F:\\Leuk study re-designed\\C-NMC\\High imbalance\\Train - 1 to 102 ratio\\enhanched\\hem\"\n",
    "dest = r\"F:\\Leuk study re-designed\\C-NMC\\High imbalance\\Majority Calss Undersample\\enhanched\\hem\"\n",
    "files = os.listdir(source)\n",
    "\n",
    "percentage = 50 #High Imbalance\n",
    "# percentage = 10 #Low Imbalance\n",
    "\n",
    "no_of_files = int((percentage/100)*len(files))\n",
    "print(no_of_files)\n",
    "# no_of_files = len(files) // 5\n",
    "\n",
    "for file_name in random.sample(files, no_of_files):\n",
    "    shutil.copy(os.path.join(source, file_name), dest)\n",
    "print('Done')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "leukemia",
   "language": "python",
   "name": "leukemia"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}