{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import json\n",
    "from os.path import join"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "OUT_DIR = 'output/'\n",
    "EXP_DIR = join(OUT_DIR, 'semsup_descs_amzn13k_curie_nocoil', 'predictions')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/n/fs/nlp-pranjal/SemSup-LMLC/training\n"
     ]
    }
   ],
   "source": [
    "%cd .."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "files = dict()\n",
    "for file in os.listdir(EXP_DIR):\n",
    "    t = float(file.split('_')[-1].replace('.pkl',''))\n",
    "    if t not in files:\n",
    "        files[t] = []\n",
    "    files[t] += [join(EXP_DIR, file)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "21.792958695441484"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import itertools\n",
    "tsize = 0\n",
    "for file in itertools.chain(*files.values()):\n",
    "    tsize += os.path.getsize(file)\n",
    "tsize/ (1024**3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "files = {k:files[k] for k in sorted(files.keys())}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10.170047391206026"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import random\n",
    "tsize = 0\n",
    "for k in sorted(list(files.keys()))[10:]:\n",
    "    if random.random() > 0.6:\n",
    "        continue\n",
    "    for f in files[k]:\n",
    "        tsize += os.path.getsize(f)\n",
    "        os.remove(f)\n",
    "tsize/ (1024**3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "90fcbf6f06d9a30c70fdaff45e14c5534421a599dc22a7267c486c9cb67dea6d"
  },
  "kernelspec": {
   "display_name": "Python 3.9.12 ('base')",
   "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": "3.9.12"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}