brockn

import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.hive.HiveContext;
import org.apache.spark.sql.SQLContext;

public class JavaSparkSQL {
  public static void main(String[] args) throws Exception {
    SparkConf sparkConf = new SparkConf().setAppName("Spark SQL Test");
    JavaSparkContext ctx = new JavaSparkContext(sparkConf);
    HiveContext hiveContext = new HiveContext(ctx.sc());

brockn

- hosts: all
  become: true
  become_method: sudo
  become_user: root
  vars:
    anaconda_version: 4.3.0
    anaconda_parent_dir: /opt/
    anaconda3_path: "/opt/Anaconda3-{{ anaconda_version }}-Linux-x86_64"
  pre_tasks:
    - name: Check if Anaconda 3 is already installed

brockn

#!/bin/bash
DEBUG="$@"
run() {
  if [[ -z "$DEBUG" ]]
  then
    sudo "$@"
  else
    echo sudo "$@"
  fi
}

brockn

diff --git a/parquet-avro/pom.xml b/parquet-avro/pom.xml
index aeba102..34efc1b 100644
--- a/parquet-avro/pom.xml
+++ b/parquet-avro/pom.xml
@@ -49,7 +49,6 @@
       <groupId>com.google.guava</groupId>
       <artifactId>guava</artifactId>
       <version>11.0</version>
-      <scope>test</scope>
     </dependency>

brockn

import java.io.FileOutputStream;
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
import java.sql.ResultSetMetaData;
import java.sql.Statement;
import java.util.Random;
import java.util.concurrent.ArrayBlockingQueue;
import java.util.concurrent.BlockingQueue;

brockn

    } catch (NullPointerException e) {
      throw npe(e, " of "+schema.getFullName());
    }
  }

  /** Helper method for adding a message to an NPE. */
  protected NullPointerException npe(NullPointerException e, String s) {
    NullPointerException result = new NullPointerException(e.getMessage()+s);
    result.initCause(e.getCause() == null ? e : e.getCause());
    return result;

brockn

import java.io.IOException;
import java.net.InetSocketAddress;
import java.net.InetAddress;
import java.util.Arrays;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hdfs.server.namenode.NameNode;
import org.apache.hadoop.ipc.RPC;
import org.apache.hadoop.ipc.Server;
import org.apache.hadoop.net.DNS;

brockn

# In this lesson we will learn about navigating the shell aka the prompt. 
#
# When you see, this:

$ 

# it means you have clicked the "Terminal" application on the right
# hand side and the application is ready for you to type.

# Now we are going to connect to "big computer" so that you can 

brockn

"""
We going to use BBEdit to edit files now, but first we must learn a few command line skills
so we can execute our scripts when needed. Let's open the Terminal and type pwd:

$ pwd
/Users/noland

The "$" simply means I am executing these commands in the Terminal. It should say /Users/brianna 
which is known as your working directory. The pwd command stands for print working directory.

brockn

#  In addition to the while loop, there is a an "if" construct. It works like so:

if drunk:
  do not drive

# or

if tired:
  sleep