ARROW-3246 Benchmarks

AfterArrow3246.ipynb

BeforeArrow3246.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pyarrow as pa\n",
    "import pyarrow.parquet as pq\n",
    "import pandas as pd\n",
    "from pandas.util.testing import rands\n",
    "        \n",
    "NUNIQUE = 1000\n",
    "STRING_SIZE = 50\n",
    "LENGTH = 10_000_000\n",
    "REPEATS = LENGTH // NUNIQUE\n",
    "\n",
    "uniques = np.array([rands(STRING_SIZE) for i in range(NUNIQUE)], dtype='O')\n",
    "indices = np.random.randint(0, NUNIQUE, size=LENGTH).astype('i4')        \n",
    "data = uniques.take(indices)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import gc\n",
    "class memory_use:\n",
    "    \n",
    "    def __init__(self):\n",
    "        self.start_use = pa.total_allocated_bytes()        \n",
    "        self.pool = pa.default_memory_pool()\n",
    "        self.start_peak_use = self.pool.max_memory()\n",
    "        \n",
    "    def __enter__(self):\n",
    "        return\n",
    "    \n",
    "    def __exit__(self, type, value, traceback):\n",
    "        gc.collect()\n",
    "        print(\"Change in memory use: {}\"\n",
    "              .format(pa.total_allocated_bytes() - self.start_use))\n",
    "        print(\"Change in peak use: {}\"\n",
    "              .format(self.pool.max_memory() - self.start_peak_use))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "dict_data = pa.DictionaryArray.from_arrays(indices, uniques)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "72320"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pa.default_memory_pool().max_memory()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Change in memory use: 16777216\n",
      "Change in peak use: 753475648\n"
     ]
    }
   ],
   "source": [
    "table = pa.table([dict_data], names=['f0'])\n",
    "with memory_use():\n",
    "    out_stream = pa.BufferOutputStream()\n",
    "    pq.write_table(table, out_stream)\n",
    "    contents = out_stream.getvalue()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "820 ms ± 11.3 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "out_stream = pa.BufferOutputStream()\n",
    "pq.write_table(table, out_stream)\n",
    "contents = out_stream.getvalue()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12576182"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(contents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "495 ms ± 8.04 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%timeit returned_table = pq.read_table(contents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "93.1 ms ± 3.12 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit returned_table = pq.read_table(contents, read_dictionary=['f0'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "dense_data = dict_data.cast(pa.utf8())\n",
    "table = pa.table([dense_data], names=['f0'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "405 ms ± 27.5 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "out_stream = pa.BufferOutputStream()\n",
    "pq.write_table(table, out_stream)\n",
    "contents = out_stream.getvalue()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "out_stream = pa.BufferOutputStream()\n",
    "pq.write_table(table, out_stream)\n",
    "contents = out_stream.getvalue()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "430 ms ± 8.12 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit\n",
    "returned_table = pq.read_table(contents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pyarrow.Table\n",
       "f0: string"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pq.read_table(contents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}