performance_comparison_larger_files.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import io\n",
    "import os\n",
    "import shlex\n",
    "import timeit\n",
    "import MDAnalysis as mda\n",
    "from MDAnalysis.core.universe import Merge\n",
    "import pickle "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import multiprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from functools import partial"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Large Trajecory Generation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "u = mda.Universe('test_multi.pdb')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "u_larger = Merge(u.atoms, u.atoms, u.atoms, u.atoms)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/scottzhuang/mdanalysis/package/MDAnalysis/coordinates/PDB.py:718: UserWarning: Unit cell dimensions not found. CRYST1 record set to unitary values.\n",
      "  warnings.warn(\"Unit cell dimensions not found. \"\n"
     ]
    }
   ],
   "source": [
    "u_larger.atoms.write('test_larger.pdb')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with mda.Writer(\"test_larger_longer.pdb\", n_atoms=u_larger.trajectory.n_atoms) as W:\n",
    "    for repeat in range(500):\n",
    "        W.write(u_larger.atoms)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with mda.Writer(\"test_larger_longer.xyz\", n_atoms=u_larger.trajectory.n_atoms) as W:\n",
    "    for repeat in range(500):\n",
    "        W.write(u_larger.atoms)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Serialize IO"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### PDB 7GB\n",
    "- 190725 atoms\n",
    "- 500 frames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "testfile = 'test_larger_longer.pdb'\n",
    "def create_universe(testfile):\n",
    "    u = mda.Universe(testfile)\n",
    "\n",
    "    \n",
    "u = mda.Universe(testfile)\n",
    "def pickle_time(u):\n",
    "    u_p = pickle.loads(pickle.dumps(u.trajectory))\n",
    "\n",
    "    \n",
    "def cog(u, ag, ts):\n",
    "    u.trajectory[ts]\n",
    "    return ag.center_of_geometry()\n",
    "\n",
    "def analysis_through_traj(u):\n",
    "    result = []\n",
    "    n_frames = u.trajectory.n_frames\n",
    "    ag = u.select_atoms('protein')\n",
    "    for ts in range(n_frames):\n",
    "        result.append(cog(u, ag, ts))\n",
    "    return result\n",
    "        \n",
    "result_serilize = timeit.timeit(\"create_universe(testfile)\", globals=globals(), number=10)\n",
    "result_pickle = timeit.timeit(\"pickle_time(u)\", globals=globals(), number=10)\n",
    "result_iter = timeit.timeit(\"analysis_through_traj(u)\", globals=globals(), number=10)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Create Universe: 705.544\n",
      "Pickle/Unpickle Trajectory: 0.020\n",
      "Analysis along traj: 1664.560\n"
     ]
    }
   ],
   "source": [
    "print(f\"Create Universe: {result_serilize:.3f}\")\n",
    "print(f\"Pickle/Unpickle Trajectory: {result_pickle:.3f}\")\n",
    "print(f\"Analysis along traj: {result_iter:.3f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### XYZ 3.8GB\n",
    "- 190725 atoms\n",
    "- 500 frames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "testfile = 'test_larger_longer.xyz'\n",
    "def create_universe(testfile):\n",
    "    u = mda.Universe(testfile)\n",
    "\n",
    "    \n",
    "u = mda.Universe(testfile)\n",
    "def pickle_time(u):\n",
    "    u_p = pickle.loads(pickle.dumps(u.trajectory))\n",
    "\n",
    "    \n",
    "def cog(u, ag, ts):\n",
    "    u.trajectory[ts]\n",
    "    return ag.center_of_geometry()\n",
    "\n",
    "def analysis_through_traj(u):\n",
    "    result = []\n",
    "    n_frames = u.trajectory.n_frames\n",
    "    ag = u.atoms\n",
    "    for ts in range(n_frames):\n",
    "        result.append(cog(u, ag, ts))\n",
    "    return result\n",
    "        \n",
    "result_serilize = timeit.timeit(\"create_universe(testfile)\", globals=globals(), number=10)\n",
    "result_pickle = timeit.timeit(\"pickle_time(u)\", globals=globals(), number=10)\n",
    "result_iter = timeit.timeit(\"analysis_through_traj(u)\", globals=globals(), number=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "In #PR 2723, XYZ file\n",
      "Create Universe: 10.063\n",
      "Pickle/Unpickle Trajectory: 0.005\n",
      "Analysis along traj: 1141.099\n"
     ]
    }
   ],
   "source": [
    "print('In #PR 2723, XYZ file')\n",
    "print(f\"Create Universe: {result_serilize:.3f}\")\n",
    "print(f\"Pickle/Unpickle Trajectory: {result_pickle:.3f}\")\n",
    "print(f\"Analysis along traj: {result_iter:.3f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Serialize PR #2703"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### PDB 7GB\n",
    "- 190725 atoms\n",
    "- 500 frames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "testfile = 'test_larger_longer.pdb'\n",
    "def create_universe(testfile):\n",
    "    u = mda.Universe(testfile)\n",
    "\n",
    "    \n",
    "u = mda.Universe(testfile)\n",
    "def pickle_time(u):\n",
    "    u_p = pickle.loads(pickle.dumps(u.trajectory))\n",
    "\n",
    "    \n",
    "def cog(u, ag, ts):\n",
    "    u.trajectory[ts]\n",
    "    return ag.center_of_geometry()\n",
    "\n",
    "def analysis_through_traj(u):\n",
    "    result = []\n",
    "    n_frames = u.trajectory.n_frames\n",
    "    ag = u.select_atoms('protein')\n",
    "    for ts in range(n_frames):\n",
    "        result.append(cog(u, ag, ts))\n",
    "    return result\n",
    "        \n",
    "result_serilize = timeit.timeit(\"create_universe(testfile)\", globals=globals(), number=10)\n",
    "result_pickle = timeit.timeit(\"pickle_time(u)\", globals=globals(), number=10)\n",
    "result_iter = timeit.timeit(\"analysis_through_traj(u)\", globals=globals(), number=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "In #PR 2704, PDB file\n",
      "Create Universe: 619.693\n",
      "Pickle/Unpickle Trajectory: 0.014\n",
      "Analysis along traj: 1556.207\n"
     ]
    }
   ],
   "source": [
    "print('In #PR 2704, PDB file')\n",
    "print(f\"Create Universe: {result_serilize:.3f}\")\n",
    "print(f\"Pickle/Unpickle Trajectory: {result_pickle:.3f}\")\n",
    "print(f\"Analysis along traj: {result_iter:.3f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### XYZ 3.8GB\n",
    "- 190725 atoms\n",
    "- 500 frames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "testfile = 'test_larger_longer.xyz'\n",
    "def create_universe(testfile):\n",
    "    u = mda.Universe(testfile)\n",
    "\n",
    "    \n",
    "u = mda.Universe(testfile)\n",
    "def pickle_time(u):\n",
    "    u_p = pickle.loads(pickle.dumps(u.trajectory))\n",
    "\n",
    "    \n",
    "def cog(u, ag, ts):\n",
    "    u.trajectory[ts]\n",
    "    return ag.center_of_geometry()\n",
    "\n",
    "def analysis_through_traj(u):\n",
    "    result = []\n",
    "    n_frames = u.trajectory.n_frames\n",
    "    ag = u.atoms\n",
    "    for ts in range(n_frames):\n",
    "        result.append(cog(u, ag, ts))\n",
    "    return result\n",
    "        \n",
    "result_serilize = timeit.timeit(\"create_universe(testfile)\", globals=globals(), number=10)\n",
    "result_pickle = timeit.timeit(\"pickle_time(u)\", globals=globals(), number=10)\n",
    "result_iter = timeit.timeit(\"analysis_through_traj(u)\", globals=globals(), number=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "In #PR 2704, XYZ file\n",
      "Create Universe: 9.322\n",
      "Pickle/Unpickle Trajectory: 0.007\n",
      "Analysis along traj: 1120.986\n"
     ]
    }
   ],
   "source": [
    "print('In #PR 2704, XYZ file')\n",
    "print(f\"Create Universe: {result_serilize:.3f}\")\n",
    "print(f\"Pickle/Unpickle Trajectory: {result_pickle:.3f}\")\n",
    "print(f\"Analysis along traj: {result_iter:.3f}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "mda_py38",
   "language": "python",
   "name": "gsoc"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}