{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Not Filter Demo\n",
    "\n",
    "Example how to wrap a filter in a not filter to negate a filter\n",
    "\n",
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark import SparkConf, SparkContext\n",
    "from mmtfPyspark.io import mmtfReader\n",
    "from mmtfPyspark.filters import ContainsDnaChain, ContainsLProteinChain, NotFilter\n",
    "from mmtfPyspark.structureViewer import view_structure"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Configure Spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Cannot run multiple SparkContexts at once; existing SparkContext(app=notFilterExample, master=local[*]) created by __init__ at <ipython-input-2-77ae329f866f>:2 ",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-6-77ae329f866f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mconf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mSparkConf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msetMaster\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"local[*]\"\u001b[0m\u001b[0;34m)\u001b[0m                       \u001b[0;34m.\u001b[0m\u001b[0msetAppName\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"notFilterExample\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0msc\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mSparkContext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mconf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/srv/spark/python/pyspark/context.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer, conf, gateway, jsc, profiler_cls)\u001b[0m\n\u001b[1;32m    113\u001b[0m         \"\"\"\n\u001b[1;32m    114\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_callsite\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfirst_spark_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mCallSite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 115\u001b[0;31m         \u001b[0mSparkContext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_ensure_initialized\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgateway\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mgateway\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconf\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mconf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    116\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    117\u001b[0m             self._do_init(master, appName, sparkHome, pyFiles, environment, batchSize, serializer,\n",
      "\u001b[0;32m/srv/spark/python/pyspark/context.py\u001b[0m in \u001b[0;36m_ensure_initialized\u001b[0;34m(cls, instance, gateway, conf)\u001b[0m\n\u001b[1;32m    273\u001b[0m                         \u001b[0;34m\" created by %s at %s:%s \"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    274\u001b[0m                         % (currentAppName, currentMaster,\n\u001b[0;32m--> 275\u001b[0;31m                             callsite.function, callsite.file, callsite.linenum))\n\u001b[0m\u001b[1;32m    276\u001b[0m                 \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    277\u001b[0m                     \u001b[0mSparkContext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_active_spark_context\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0minstance\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: Cannot run multiple SparkContexts at once; existing SparkContext(app=notFilterExample, master=local[*]) created by __init__ at <ipython-input-2-77ae329f866f>:2 "
     ]
    }
   ],
   "source": [
    "conf = SparkConf().setMaster(\"local[*]\") \\\n",
    "                      .setAppName(\"notFilterExample\")\n",
    "sc = SparkContext(conf = conf)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read in MMTF Files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = \"../../resources/mmtf_reduced_sample/\"\n",
    "\n",
    "pdb = mmtfReader.read_sequence_file(path, sc)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Filter by contains L Protein Chain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "structures = pdb.filter(ContainsLProteinChain())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using Not filter to reverse a filter\n",
    "\n",
    "Get entires that does not contain DNA Chains"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "structures = structures.filter(NotFilter(ContainsDnaChain()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Count number of entires"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PDB entires without DNA chains : 4820\n"
     ]
    }
   ],
   "source": [
    "count = structures.count()\n",
    "\n",
    "print(f\"PDB entires without DNA chains : {count}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visualize Structures"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d8ab56847c7d48b3ba6203275700490b",
       "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=4819), Output()), _dom_classes=('widget-interact',))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<function mmtfPyspark.structureViewer.view_structure.<locals>.view3d>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "view_structure(structures.keys().collect())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Terminate Spark "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "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
}