profiling proposed changes in obspy PR 2091

time_cat.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Profile potential changes made to resoruce_ids\n",
    "Profiles the changes made to ResourceIdentifier objects proposed in obspy [PR #2091](https://github.com/obspy/obspy/pull/2091)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import gc\n",
    "import io\n",
    "import pickle\n",
    "\n",
    "import obspy\n",
    "import obspy.core.event as ev\n",
    "from obspy.core.util.testing import create_diverse_catalog\n",
    "from obspy import read_events\n",
    "from obspy import UTCDateTime, Catalog\n",
    "\n",
    "    \n",
    "catalog = create_diverse_catalog()\n",
    "\n",
    "\n",
    "def read_quakeml(*args):\n",
    "    cat_bytes = io.BytesIO()\n",
    "    catalog.write(cat_bytes, 'quakeml')\n",
    "    return obspy.read_events(cat_bytes)\n",
    "\n",
    "\n",
    "def copy_catalog():\n",
    "    return catalog.copy()\n",
    "\n",
    "\n",
    "def pickle_catalog():\n",
    "    cat_pickle_bytes = pickle.dumps(catalog)\n",
    "    return pickle.loads(cat_pickle_bytes)\n",
    "    \n",
    "\n",
    "def make_catalog_list(*args):\n",
    "    \"\"\"\n",
    "    Make a list of complex catalogs (and copies) and return it.\n",
    "    \"\"\"\n",
    "    cat1 = create_diverse_catalog()\n",
    "    cat2 = read_quakeml()\n",
    "    cat3 = copy_catalog()\n",
    "    cat4 = pickle_catalog()\n",
    "    return [cat1, cat2, cat3, cat4]\n",
    "\n",
    "\n",
    "gc.disable()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Without scope resource_ids\n",
    "Swap out `scope_resource_ids` method with a dummy function to simulate not using the method. These serve as a baseline. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "old = ev.Event.scope_resource_ids\n",
    "ev.Event.scope_resource_ids = lambda x: x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "13.3 ms ± 130 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit read_quakeml()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4.8 ms ± 393 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit copy_catalog()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.71 ms ± 13.2 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit pickle_catalog()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "22.5 ms ± 239 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit make_catalog_list()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Scopped Resource_Ids\n",
    "Restore `scope_resource_ids` method in order to profile the performance effecot of the proposed changes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "ev.Event.scope_resource_ids = old"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "13.6 ms ± 66.6 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit read_quakeml()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5.07 ms ± 36 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit copy_catalog()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.21 ms ± 20.1 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit pickle_catalog()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "24.6 ms ± 74.5 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit make_catalog_list()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# uncomment the next two lines to run snakeviz for profiling\n",
    "# %load_ext snakeviz\n",
    "# %snakeviz copy_catalog()"
   ]
  },
  {
   "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}