sorting.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    }
   ],
   "source": [
    "%pylab inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dlinputs import tarrecords, utils\n",
    "import hashlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'5d41402abc4b2a76b9719d911017c592'"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def md5hash(x):\n",
    "    return hashlib.md5(str(x)).hexdigest()\n",
    "md5hash(\"hello\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-rw-r--r-- tmb/tmb           1 1969-12-31 16:00 10.cls\n",
      "-rw-r--r-- tmb/tmb         306 1969-12-31 16:00 10.png\n",
      "-rw-r--r-- tmb/tmb           1 1969-12-31 16:00 11.cls\n",
      "-rw-r--r-- tmb/tmb         345 1969-12-31 16:00 11.png\n",
      "-rw-r--r-- tmb/tmb           1 1969-12-31 16:00 12.cls\n",
      "tar: write error\n"
     ]
    }
   ],
   "source": [
    "!tar -ztvf testdata/sample.tgz | sed 5q"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "__key__ '10'\n",
      "__source__ <type 'NoneType'> None\n",
      "cls 0\n",
      "png float32 (28, 28)\n"
     ]
    }
   ],
   "source": [
    "data = tarrecords.tariterator(open(\"testdata/sample.tgz\"))\n",
    "data = list(data)\n",
    "utils.print_sample(data[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Help on built-in function sorted in module __builtin__:\n",
      "\n",
      "sorted(...)\n",
      "    sorted(iterable, cmp=None, key=None, reverse=False) --> new sorted list\n",
      "\n"
     ]
    }
   ],
   "source": [
    "help(sorted)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_by_key = sorted(data, key=lambda x: x[\"__key__\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_by_content = sorted(data, key=lambda x: x[\"cls\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_by_keyhash = sorted(data, key=lambda x: md5hash(x[\"__key__\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_by_contenthash = sorted(data, key=lambda x: md5hash(x[\"png\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}