105 lines (104 with data), 2.5 kB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import shutil\n",
    "src = \"/home/serge/database/data/genomes/bacillus/ncbi-genomes-2019-06-25/train/\"\n",
    "t = \"/home/serge/database/data/genomes/bacillus/ncbi-genomes-2019-06-25\"\n",
    "\n",
    "src_files = os.listdir(src)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3966"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(src_files)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "num=500\n",
    "\n",
    "for i, file_name in enumerate(src_files):\n",
    "    if i % num == 0:\n",
    "        dest = f\"{t}/{i}/\"\n",
    "        if not os.path.exists(dest):\n",
    "            os.mkdir(dest)\n",
    "    full_file_name = os.path.join(src, file_name)\n",
    "    if os.path.isfile(full_file_name):\n",
    "        shutil.copy(full_file_name, dest)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "train, test = train_test_split(src_files,test_size=0.2, random_state=42)\n",
    "portions = {\"train\":train, \"valid\":test}\n",
    "\n",
    "for part in portions.keys():\n",
    "    for file_name in portions[part]:\n",
    "        dest = f\"{t}/{part}\"\n",
    "        if not os.path.exists(dest):\n",
    "            os.mkdir(dest)\n",
    "        full_file_name = os.path.join(src, file_name)\n",
    "        if os.path.isfile(full_file_name):\n",
    "            shutil.copy(full_file_name, dest)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:bio] *",
   "language": "python",
   "name": "conda-env-bio-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}