shuffle.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from time import sleep\n",
    "from random import random\n",
    "import os, sys\n",
    "from socket import gethostname\n",
    "from dask.distributed import Queue\n",
    "from distributed import Client\n",
    "client = Client()\n",
    "client"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def read_fun(queues, src):\n",
    "    count = 0\n",
    "    for record in read_records(src):\n",
    "        shard = shard_fun(record)\n",
    "        queues[shard].put(record)\n",
    "        count += 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def write_fun(dest, queue):\n",
    "    count = 0\n",
    "    with RecordWriter(dest) as stream:\n",
    "        while True:\n",
    "            record = queue.get()\n",
    "            if record is None: break\n",
    "            stream.write(record)\n",
    "            count += 1\n",
    "    return count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "shards = list_shards(...)\n",
    "queues = [None] * len(shards)\n",
    "results = [None] * len(shards)\n",
    "for i, s in enumerate(shards):\n",
    "    queues[i] = Queue()\n",
    "    results[i] = client.submit(write_fun, s, queues[i])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sources = list_sources(...)\n",
    "inputs = [None] * len(sources)\n",
    "for s in sources:\n",
    "    inputs[i] = client.submit(read_fun, queues, s)"
   ]
  }
 ],
 "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
}