{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Write MMTF Subset Demo\n",
    "\n",
    "Simple example writting a subset of mmtf files\n",
    "\n",
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark import SparkConf, SparkContext\n",
    "from mmtfPyspark.io import mmtfReader, mmtfWriter\n",
    "from mmtfPyspark.filters import ExperimentalMethods, Resolution, RFree\n",
    "from mmtfPyspark.structureViewer import view_structure"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Configure Spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "conf = SparkConf().setMaster(\"local[*]\") \\\n",
    "                      .setAppName(\"WriteMMTFCustomSubset\")\n",
    "sc = SparkContext(conf = conf)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read in a fractions of entries from a local Hadoop Sequence File"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "number of pdb entries read : 2215\n"
     ]
    }
   ],
   "source": [
    "path = \"../../resources/mmtf_full_sample/\"\n",
    "fraction= 0.5\n",
    "seed = 123\n",
    "\n",
    "pdb = mmtfReader.read_sequence_file(path, sc, fraction = fraction, seed = seed)\n",
    "\n",
    "count = pdb.count()\n",
    "\n",
    "print(f'number of pdb entries read : {count}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Retain high resolution X-ray structures"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "number of pdb entries left : 510\n"
     ]
    }
   ],
   "source": [
    "pdb = pdb.filter(ExperimentalMethods(ExperimentalMethods.X_RAY_DIFFRACTION)) \\\n",
    "         .filter(Resolution(0,2.0)) \\\n",
    "         .filter(RFree(0,2.0))\n",
    "\n",
    "print(f'number of pdb entries left : {pdb.count()}')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visualize Structures"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "22b3bb2a0a2149be880469adfae48cd0",
       "version_major": 2,
       "version_minor": 0
      },
      "text/html": [
       "<p>Failed to display Jupyter Widget of type <code>interactive</code>.</p>\n",
       "<p>\n",
       "  If you're reading this message in the Jupyter Notebook or JupyterLab Notebook, it may mean\n",
       "  that the widgets JavaScript is still loading. If this message persists, it\n",
       "  likely means that the widgets JavaScript library is either not installed or\n",
       "  not enabled. See the <a href=\"https://ipywidgets.readthedocs.io/en/stable/user_install.html\">Jupyter\n",
       "  Widgets Documentation</a> for setup instructions.\n",
       "</p>\n",
       "<p>\n",
       "  If you're reading this message in another frontend (for example, a static\n",
       "  rendering on GitHub or <a href=\"https://nbviewer.jupyter.org/\">NBViewer</a>),\n",
       "  it may mean that your frontend doesn't currently support widgets.\n",
       "</p>\n"
      ],
      "text/plain": [
       "interactive(children=(IntSlider(value=0, description='i', max=509), Output()), _dom_classes=('widget-interact',))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<function mmtfPyspark.structureViewer.view_structure.<locals>.view3d>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "structures = pdb.keys().collect()\n",
    "view_structure(structures)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Save this subset in a Hadoop Sequence File"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "write_path = \"./mmtf_subset_xray\"\n",
    "\n",
    "# Reduce RDD to 8 partitiions\n",
    "pdb = pdb.coalesce(8)\n",
    "mmtfWriter.write_sequence_file(write_path, sc, pdb)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Terminate Spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "sc.stop()"
   ]
  }
 ],
 "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}