Parallel Reservoir Sampling Equivalent

parallel_reservoir_sampling_equivalent.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Reservoir sampling is not normally parallel,\n",
    "# but RNG generation, sorting and gather can be parallelized.\n",
    "# This is for demonstrating the capability only\n",
    "# See more here: https://en.wikipedia.org/wiki/Fisher%E2%80%93Yates_shuffle#Sorting\n",
    "def sim_parallel_shuffle(data):\n",
    "    rands = np.random.rand(data.size)\n",
    "    indices = np.argsort(rands)\n",
    "    return data[indices]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 1 2 3 4 5 6 7 8 9]\n",
      "[5 7 4 1 6 9 8 3 2 0]\n"
     ]
    }
   ],
   "source": [
    "data = np.arange(10)\n",
    "print(data)\n",
    "shuffled = sim_parallel_shuffle(data)\n",
    "print(shuffled)"
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}