{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Map To List Demo\n",
    "\n",
    "This example shows how to filter pdb proteins by X-Ray Diffraction, and store information (protein name, resolution, rFree, rWork) of the results in a list\n",
    "\n",
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark import SparkConf, SparkContext\n",
    "from mmtfPyspark.filters import ExperimentalMethods\n",
    "from mmtfPyspark.io import mmtfReader"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Configure Spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "conf = SparkConf().setMaster(\"local[*]\") \\\n",
    "                  .setAppName(\"MapToListDemo\")\n",
    "sc = SparkContext(conf = conf)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read in MMTF Files and sample a small fraction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = \"../../resources/mmtf_full_sample/\"\n",
    "fraction = 0.001\n",
    "seed = 123\n",
    "\n",
    "pdb = mmtfReader.read_sequence_file(path, sc, fraction = fraction, seed = seed)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Filter by X-Ray Diffraction experimental method"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "pdb = pdb.filter(ExperimentalMethods(ExperimentalMethods.X_RAY_DIFFRACTION))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Map results to a list of information, and print each list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[['4DOI', 1.5499999523162842, 0.20280000567436218, 0.18170000612735748],\n",
       " ['2QNI', 1.7999999523162842, 0.22066999971866608, 0.19931000471115112],\n",
       " ['3RNQ', 1.600000023841858, 0.20679999887943268, 0.1826999932527542],\n",
       " ['2W6A', 1.399999976158142, 0.19900000095367432, 0.16099999845027924],\n",
       " ['4QKW', 1.7000000476837158, 0.24490000307559967, 0.21230000257492065],\n",
       " ['4CVO', 1.850000023841858, 0.25529998540878296, 0.23639999330043793],\n",
       " ['2V0Z', 2.200000047683716, 0.26600000262260437, 0.20499999821186066],\n",
       " ['1MNN', 1.399999976158142, 0.20635999739170074, 0.19483999907970428],\n",
       " ['3CLO', 2.0399999618530273, 0.21699999272823334, 0.18700000643730164],\n",
       " ['1GVP', 1.600000023841858, 0.2879999876022339, 0.20900000631809235]]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pdb.map(lambda t: [t[0], t[1].resolution, t[1].r_free, t[1].r_work]).collect()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Terminate Spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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
}