fran0x

#!/usr/bin/env bash

set timeout 60
cd /tmp
/usr/bin/expect << EOF

spawn /bin/bash greenplum-db-4.2.6.1-build-1-RHEL5-x86_64.bin
expect {
	-ex "--More--" {
		send "\n"

fran0x

FROM centos:6.6
MAINTAINER "Francisco Lopez" [email protected]

# update & upgrade packages
RUN yum update -y & yum upgrade -y

# install extra packages and basic tools (included some required for Greenplum installer)
RUN yum install -y epel-release git unzip which tar sed wget curl nano expect

# cleanup packages

fran0x

package chapter1

import math._
import math.BigInt._
import util._

object ExercisesCh1 {

  3                                               //> res0: Int(3) = 3
  pow(sqrt(3),2)                                  //> res1: Double = 2.9999999999999996

fran0x

# Install Git from http://git-scm.com/ and then launch Git Bash

# Generate SSH key pair
ssh-keygen -t rsa -C <username>@gmail.com

#Turn on SSH agent
ssh-agent -s
eval $(ssh-agent -s)

# List SSH keys registered in the SSH agent

fran0x

package chapter2

import math._

object ExercisesCh2 {
  def signum(i: Int) = if (i < 0) -1 else if (i > 0) 1 else 0
                                                  //> signum: (i: Int)Int

  signum(5)                                       //> res0: Int = 1
  signum(-5)                                      //> res1: Int = -1

fran0x

package chapter3

import util._
import scala.collection.mutable.ArrayBuffer
import java.awt.datatransfer._
import scala.collection.JavaConverters._
import scala.collection.mutable.Buffer

object ExercisesCh3 {
  // 1. array of random ints

fran0x

import java.io.File
import java.io.PrintWriter

import scala.annotation.migration
import scala.collection.immutable.ListMap
import scala.collection.mutable.Map

object JoinDuplicatedLines {
  def main(args: Array[String]) {
    val input = io.Source fromFile "input.csv"

fran0x

def simpleWordTokenizer(string):
    """ A simple (for-comprehension) implementation  of input string tokenization
    Args:
        string (str): input string
    Returns:
        list: a list of tokens in lowercase and no empty strings
    """
    return [x for x in re.split(split_regex, string.lower()) if x]

starWarsDarkSide = 'Only at the end do you realize the power of the Dark Side.'

fran0x

# copy the Hive configuration file hive-site.xml to the spark configuration folder
# sudo cp /etc/hive/conf.dist/hive-site.xml /usr/lib/spark/conf/

# launch pyspark with the spark-csv package (note: version 1.2.0 has some issues thus better use 1.3.0)
# PYSPARK_DRIVER_PYTHON=ipython pyspark --packages com.databricks:spark-csv_2.10:1.3.0

# check dataframes are working
sqlCtx.createDataFrame([("somekey", 1)])

# load yelp dataset

fran0x

# load the "orders" table from Hive into a DataFrame
orders_df=sqlCtx.sql("select * from orders")
orders_df.printSchema()

# 1) calculate number of orders in SUSPECTED_FRAUD status
sqlCtx.select("select count(order_id) from orders where order_status='SUSPECTED_FRAUD'").show(5)

# load the "order_items" table from Hive into a DataFrame
order_items_df=sqlCtx.sql("select * from order_items")
order_items_df.printSchema()