{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Problem 1\n",
    "Apply your skills to classify protein foldType with Decision Tree Classifier\n",
    "\n",
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from mmtfPyspark.ml import SparkMultiClassClassifier, datasetBalancer                                 \n",
    "from pyspark.sql import SparkSession\n",
    "from pyspark.sql.functions import *\n",
    "import mltoolkit"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Configure Spark Session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "spark = SparkSession.builder.appName(\"Problem-1\").getOrCreate()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## TODO-1: Read in data from parquet file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "ename": "SyntaxError",
     "evalue": "invalid syntax (<ipython-input-3-cf53e0a2b799>, line 2)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;36m  File \u001b[0;32m\"<ipython-input-3-cf53e0a2b799>\"\u001b[0;36m, line \u001b[0;32m2\u001b[0m\n\u001b[0;31m    data = # Your Code Here #\u001b[0m\n\u001b[0m                             ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
     ]
    }
   ],
   "source": [
    "parquetFile = './input_features/'\n",
    "data = # Your Code Here #"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## TODO-2: Select alpha, beta, alpha+beta foldtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = # Your Code Here #\n",
    "print(f\"Total number of data: {data.count()}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## TODO-3: Downsample data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "label = 'foldType'\n",
    "\n",
    "data = # Your Code Here #\n",
    "print(f\"Dataset size (balanced)  : {data.count()}\")\n",
    "    \n",
    "data.groupby(label).count().show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## TODO-4: Decision Tree Classifier with PySpark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark.ml.classification import DecisionTreeClassifier\n",
    "\n",
    "dtc = # Your Code Here: Make Decision Tree Classifier Class #\n",
    "mcc = # Your Code Here: Use MulticlassClassifier wrapper on dtc#\n",
    "matrics = # Your Code Here: fit data#\n",
    "for k,v in matrics.items(): print(f\"{k}\\t{v}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## BONUS: Decision Tree Classifier with sklearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier\n",
    "\n",
    "df = # Your Code Here: convert data to Pandas Dataframe #\n",
    "dtc = # Your Code Here: Make Decision Tree Classifier Class #\n",
    "mcc = # Your Code Here: Use MulticlassClassifier wrapper on dtc#\n",
    "matrics = # Your Code Here: fit data#\n",
    "for k,v in matrics.items(): print(f\"{k}\\t{v}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "spark.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": "3.6.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}