purels_smallfilesdf.ipynb

  {
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import subprocess\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "SRC=\"/datahub/onewiki/split_230k/\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "def readContents(f):\n",
    "    with open(f, \"rb\") as fd:\n",
    "        return fd.read().splitlines()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def pureReadText(path):\n",
    "    result = subprocess.check_output([\"pls\", path])\n",
    "    listing = sc.parallelize(result.decode('utf-8').splitlines(), 2400)\n",
    "    listing = listing.filter(lambda x: os.path.isfile(x))\n",
    "    return listing.flatMap(readContents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 892 ms, sys: 1.13 s, total: 2.02 s\n",
      "Wall time: 1min 20s\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "2756675251"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%time pureReadText(SRC).count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 16 ms, sys: 0 ns, total: 16 ms\n",
      "Wall time: 2min 37s\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "2756678137"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%time spark.read.text(SRC).count()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}