courses/unstructured/PySpark-Test-Solution.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from pyspark import SparkContext\n",
    "\n",
    "if 'sc' not in locals():\n",
    "  sc = SparkContext(\"local\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "499.5\n"
     ]
    }
   ],
   "source": [
    "rdd = sc.parallelize(range(1000), 10)\n",
    "print(rdd.mean())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "231\n"
     ]
    }
   ],
   "source": [
    "data = [1, 2, 3, 5, 8, 13, 21, 34, 55, 89]\n",
    "distData = sc.parallelize(data)\n",
    "res = distData.reduce(lambda a, b: a + b)\n",
    "print(res)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Row(animal=u'Frog', count(1)=2), Row(animal=u'Pig', count(1)=3), Row(animal=u'Cat', count(1)=5), Row(animal=u'Dog', count(1)=6)]\n"
     ]
    }
   ],
   "source": [
    "from pyspark.sql.types import *\n",
    "header = 'animal,name'\n",
    "schema = StructType([StructField(colname, StringType(), True) for colname in header.split(',')])\n",
    "pets = spark.read.schema(schema).csv('gs://BUCKET_NAME/unstructured/pets.txt')\n",
    "\n",
    "pets.createOrReplaceTempView('pets')\n",
    "countsByPet = spark.sql('SELECT animal, COUNT(*) from pets GROUP BY animal')\n",
    "\n",
    "print(countsByPet.take(10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[(u'Frog', [u'Kermit', u'Hoppy']), (u'Pig', [u'Bacon', u'Babe', u'Tasty']), (u'Dog', [u'Noir', u'Bree', u'Pickles', u'Sparky', u'Gigi', u'Fred']), (u'Cat', [u'Tom', u'Alley', u'Cleo', u'George', u'Suzy'])]\n"
     ]
    }
   ],
   "source": [
    "file = sc.textFile(\"gs://BUCKET_NAME/unstructured/pets.txt\")\n",
    "\n",
    "pets = file.map(lambda s: s.split(\",\")).map(lambda x : (x[0], [x[1]]))\n",
    "petsByType = pets.reduceByKey(lambda a, b: a + b)\n",
    "print(petsByType.take(10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.5.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}