crocker

// define your json views
object MyViews {
  class ViewA {}
  class ViewB {}
  class ViewC {}
}

// configure your object mapper
val mapper = new ObjectMapper with ScalaObjectMapper
mapper.registerModule(DefaultScalaModule)

crocker

val elastic = injector.getInstance[ElasticClient](
  Key.get(classOf[ElasticClient], 
  Names.named("elastic"))
)

crocker

package com.signalpath.model

import scala.collection.mutable

class Forest[A]()(ordering: Ordering[A]) {
  val tree = new mutable.LinkedHashMap[Option[A], mutable.ListBuffer[A]]()

  def addNode(parent: Option[A], node: A): Unit = {
    val children = tree.get(parent).map(_ += node).getOrElse(mutable.ListBuffer[A](node))
    tree.put(parent,children.sorted(ordering))

crocker

db.subscription.updateMany({}, {$set: {last_processed: null}})

crocker

def getDateRange(year: Int, week: Int): (LocalDate, LocalDate) = {
  val date = new LocalDate().withYear(year).withWeekOfWeekyear(week)
  val startDate = date.withDayOfWeek(1)
  val endDate = date.withDayOfWeek(7)

  (startDate, endDate)
}
  
val dateFormat = "yyyy-MM-dd E"
val year = 2016

crocker

// This will not print to your logs (no matter how many times you run it)
dataRDD.map(c => println(c))

crocker

// This will print to the logs for the executors
dataRDD.map(c => println(c)).collect()

crocker

db.getCollection('patient').find().snapshot().forEach(
  function (p) {
    var lower_middle_name;
    if(p.middle_name) lower_middle_name = p.middle_name.toLowerCase(); else lower_middle_name = null;
     
    var lower_mrn;
    if(p.mrn) lower_mrn = p.mrn.toLowerCase(); else lower_mrn = null;
     
    var lower_email_address;
    if(p.email_address) lower_email_address = p.email_address.toLowerCase(); else lower_email_address = null;

crocker

package com.databricks.spark.jira

import scala.io.Source

import org.apache.spark.rdd.RDD

import org.apache.spark.sql._
import org.apache.spark.sql.functions._
import org.apache.spark.sql.sources.{TableScan, BaseRelation, RelationProvider}

crocker

val transactions = spark.read
  .option("header", "true")
  .option("inferSchema", "true")
  .json("s3n://bucket-name/transaction.json")

transactions.groupBy("id", "organization").count.sort($"count".desc).show