João Antonio Ferreira joao-parana

## Workflow01UDAF.scala
// UserDefinedAggregateFunction is the contract to define
// user-defined aggregate functions (UDAFs)
class MyCountUDAF extends UserDefinedAggregateFunction {
  // Este método abaixo define pode ser invocado apenas assim: inputSchema(0)
  // Isto é feito via inversão de dependência pelo Spark
  // o retorno é um objeto StructField assim:
  // StructField("id", LongType, true, {})
  // o objeto StructField é do pacote org.apache.spark.sql.types
  override def inputSchema: StructType = {
    new StructType().add("id", LongType, nullable = true)

## theme.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                joao-parana
                / theme.md
            
            
              Created Oct 2, 2018
            
          
      View theme.md
  
    
    <img src="data:image/png;base64,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

  
## diagrama-W1.svg

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                joao-parana
                / diagrama-W1.svg
            
            
              Created Oct 2, 2018
            
          
      View diagrama-W1.svg
  
    
      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## W1.scala
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.SparkSession.Builder
import org.apache.spark.SparkContext
import org.apache.log4j.{Level, Logger}
// A sparkSession é provida pelo proprio Spark Shell
// O nivel de log também já é configurado pela Spark Shell
def boolean_udf_wrapper(a:String, b:String, t:Any): Boolean = { true }
def string_udf_wrapper(a:String, b:String, t:Any): String = { "••••" }
import org.apache.spark.sql.functions.expr
import org.apache.spark.sql.functions.sum

## Workflow01UDFs.scala
def happyEmployees(salary: Int) => salary > 2200

def smartTextCase(name: String) => name.toUpperCase()

## kubernetes-dnd.sh
# Usando o Kubernetes com Docker in Docker (DIND)

sudo mkdir -p /usr/local
cd /usr/local
sudo mkdir dind-cluster
cd dind-cluster/
sudo chmod o+w .
ls -lat .. | head
# wget https://cdn.rawgit.com/kubernetes-sigs/kubeadm-dind-cluster/master/fixed/dind-cluster-v1.10.sh
curl -O https://cdn.rawgit.com/kubernetes-sigs/kubeadm-dind-cluster/master/fixed/dind-cluster-v1.10.sh

## .block
license: gpl-3.0
height: 960
border: no

## map-pushdow.sc
// Este script é para rodar no Ammonite.
// Crie o arquivo catalyst_04.sc com este conteúdo
// Dentro da shell REPL do Ammonitem, você deve invocar assim:
//   import $file.catalyst_04, catalyst_04._
//
// Mas antes execute estes tres comandos abaixo
// import coursier.MavenRepository
// interp.repositories() ++= Seq(MavenRepository("file:/Users/admin/.m2/repository"))
// import $ivy.`org.apache.spark::spark-sql:2.3.0`

## index.html
<!DOCTYPE html>
<html>
<head>
    <meta name="description" content="data-binding">
</head>
<body>
    <script src="https://d3js.org/d3.v4.min.js" charset=" utf-8"></script>
    <script>
        var selector = d3.select('body')
            .selectAll('span')

## index.html
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="description" content="SOMA 01 - Hello World">
    <title>SOMA 01 - Hello World</title>
</head>
<body>
  <div id="page"></div>
    <script src="https://d3js.org/d3.v4.min.js" charset="utf-8"></script>
	// UserDefinedAggregateFunction is the contract to define
	// user-defined aggregate functions (UDAFs)
	class MyCountUDAF extends UserDefinedAggregateFunction {
	// Este método abaixo define pode ser invocado apenas assim: inputSchema(0)
	// Isto é feito via inversão de dependência pelo Spark
	// o retorno é um objeto StructField assim:
	// StructField("id", LongType, true, {})
	// o objeto StructField é do pacote org.apache.spark.sql.types
	override def inputSchema: StructType = {
	new StructType().add("id", LongType, nullable = true)
	import org.apache.spark.sql.SparkSession
	import org.apache.spark.sql.SparkSession.Builder
	import org.apache.spark.SparkContext
	import org.apache.log4j.{Level, Logger}
	// A sparkSession é provida pelo proprio Spark Shell
	// O nivel de log também já é configurado pela Spark Shell
	def boolean_udf_wrapper(a:String, b:String, t:Any): Boolean = { true }
	def string_udf_wrapper(a:String, b:String, t:Any): String = { "••••" }
	import org.apache.spark.sql.functions.expr
	import org.apache.spark.sql.functions.sum
	def happyEmployees(salary: Int) => salary > 2200

	def smartTextCase(name: String) => name.toUpperCase()
	# Usando o Kubernetes com Docker in Docker (DIND)

	sudo mkdir -p /usr/local
	cd /usr/local
	sudo mkdir dind-cluster
	cd dind-cluster/
	sudo chmod o+w .
	ls -lat .. \| head
	# wget https://cdn.rawgit.com/kubernetes-sigs/kubeadm-dind-cluster/master/fixed/dind-cluster-v1.10.sh
	curl -O https://cdn.rawgit.com/kubernetes-sigs/kubeadm-dind-cluster/master/fixed/dind-cluster-v1.10.sh
	// Este script é para rodar no Ammonite.
	// Crie o arquivo catalyst_04.sc com este conteúdo
	// Dentro da shell REPL do Ammonitem, você deve invocar assim:
	// import $file.catalyst_04, catalyst_04._
	//
	// Mas antes execute estes tres comandos abaixo
	// import coursier.MavenRepository
	// interp.repositories() ++= Seq(MavenRepository("file:/Users/admin/.m2/repository"))
	// import $ivy.`org.apache.spark::spark-sql:2.3.0`
	<!DOCTYPE html>
	<html>
	<head>
	<meta name="description" content="data-binding">
	</head>
	<body>
	<script src="https://d3js.org/d3.v4.min.js" charset=" utf-8"></script>
	<script>
	var selector = d3.select('body')
	.selectAll('span')
	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="description" content="SOMA 01 - Hello World">
	<title>SOMA 01 - Hello World</title>
	</head>
	<body>
	<div id="page"></div>
	<script src="https://d3js.org/d3.v4.min.js" charset="utf-8"></script>