Repo cleanup

.bloop/bloop.settings.json

@@ -1,23 +0,0 @@
-{
-    "javaSemanticDBVersion": "0.9.8",
-    "semanticDBVersion": "4.8.14",
-    "supportedScalaVersions": [
-        "2.13.12",
-        "2.12.18",
-        "2.12.17",
-        "2.12.16",
-        "2.12.15",
-        "2.13.9",
-        "2.13.10",
-        "2.13.11",
-        "2.11.12",
-        "2.12.11",
-        "2.12.12",
-        "2.12.13",
-        "2.12.14",
-        "2.13.5",
-        "2.13.6",
-        "2.13.7",
-        "2.13.8"
-    ]
-}

.vscode/settings.json

@@ -1,5 +0,0 @@
-{
-    "files.watcherExclude": {
-        "**/target": true
-    }
-}

build.sc

@@ -12,26 +12,43 @@ object mimir_pip extends RootModule with ScalaModule {
 
   def scalaVersion = "2.12.15"
 
-  def mainClass = Some("org.mimirdb.Pip")
+  def mainClass = Some("org.mimirdb.pip.Main")
 
-  def repositoriesTask = T.task { super.repositoriesTask() ++ Seq(
-  MavenRepository("https://repo.osgeo.org/repository/release/"),
-)}
+  // def sourceRoots = T.sources(millSourcePath / "bin" / "src")
 
+  def moduleDeps = Seq(lib)
 
-  def ivyDeps = Agg(
-    ivy"org.apache.spark::spark-sql:3.3.1",
-    ivy"org.apache.spark::spark-core:3.3.1",
-    ivy"org.apache.sedona:sedona-common:1.5.0",
-    ivy"org.apache.sedona::sedona-spark-shaded-3.0:1.5.0",
-    ivy"org.datasyslab:geotools-wrapper:1.5.0-28.2"
-  )
-
-  object test extends ScalaTests with TestModule {
-    def ivyDeps = Agg(ivy"org.scalactic::scalactic:3.2.17", 
-                      ivy"org.scalatest::scalatest:3.2.17"
-                    )
-    def testFramework = "org.scalatest.tools.Framework"
+  def repositoriesTask = T.task { 
+    super.repositoriesTask() ++ 
+    lib.repositoriesTask()
   }
 
+  def test = lib.test
+
+  object lib extends ScalaModule {
+    val VERSION     = "0.0.1-SNAPSHOT"
+
+    def scalaVersion = "2.12.15"
+
+    def repositoriesTask = T.task { super.repositoriesTask() ++ Seq(
+      MavenRepository("https://repo.osgeo.org/repository/release/"),
+    )}
+
+    def ivyDeps = Agg(
+      ivy"org.apache.spark::spark-sql:3.3.1",
+      ivy"org.apache.spark::spark-core:3.3.1",
+      ivy"org.apache.sedona:sedona-common:1.5.0",
+      ivy"org.apache.sedona::sedona-spark-shaded-3.0:1.5.0",
+      ivy"org.datasyslab:geotools-wrapper:1.5.0-28.2"
+    )
+
+    object test extends ScalaTests with TestModule {
+      def ivyDeps = Agg(ivy"org.scalactic::scalactic:3.2.17", 
+                        ivy"org.scalatest::scalatest:3.2.17"
+                      )
+      def testFramework = "org.scalatest.tools.Framework"
+    }
+  }
+
+
 }

lib/src/org/mimirdb/pip/Gauss.scala

@@ -1,7 +1,10 @@
-package org.mimirdb
+package org.mimirdb.pip
+
 import scala.util.Random
 import java.io.Serializable
-   /* Gaussian object NOTE: Scala uses Camel Case; create a new class file for this UDT and its associated methods */
+
+
+/* Gaussian object NOTE: Scala uses Camel Case; create a new class file for this UDT and its associated methods */
 final case class Gauss(mean: Float, sd: Float) {
     def generate_value():Float = {
         Random.nextGaussian().asInstanceOf[Float] * sd + mean

lib/src/org/mimirdb/pip/GaussDistribution.scala

@@ -1,4 +1,4 @@
-package org.mimirdb
+package org.mimirdb.pip
 
 trait GaussDistribution {
   

lib/src/org/mimirdb/pip/GaussType.scala

@@ -1,4 +1,4 @@
-package org.mimirdb
+package org.mimirdb.pip
 import org.apache.spark.sql.types._
 import org.apache.spark.unsafe.types.UTF8String
 import org.apache.hadoop.shaded.com.nimbusds.jose.util.StandardCharset
@@ -57,4 +57,4 @@ class GaussType extends UserDefinedType[Gauss]{
   
 }
 
-case object GaussType extends org.mimirdb.GaussType with Serializable
+case object GaussType extends org.mimirdb.pip.GaussType with Serializable

lib/src/org/mimirdb/pip/Histogram.scala

@@ -1,4 +1,4 @@
-package org.mimirdb
+package org.mimirdb.pip
 
 import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
 import org.apache.spark.sql.expressions.Aggregator
@@ -21,7 +21,8 @@ case class DataRow(id: Int, speed: Double, interval: Int, prob: Double)
           OUT schema is simply the list of bin values (i.e. probability sums for the encoded interval) in order from least
           speed interval (bin) to greatest.
         */
-object histogram extends Aggregator[DataRow, List[(Int, Double)], Array[Double]] {
+object Histogram extends Aggregator[DataRow, List[(Int, Double)], Array[Double]] 
+{
 
 /* 
     ASSUME: The set of tuples being aggregated share the same (observation) point and are thus from the same distribution

lib/src/org/mimirdb/pip/Pip.scala

@@ -1,11 +1,12 @@
-package org.mimirdb
+package org.mimirdb.pip
 
 
 import org.apache.spark.sql.types.UDTRegistration
 import org.apache.spark.sql.functions
 
 
-object MimirUDTRegistrator {//by convention uppercase first letter of class/object name
+object Mimir {
+  //by convention uppercase first letter of class/object name
   //then just model this after the sedona registrator
 
   def registerAll(): Unit = {

lib/src/org/mimirdb/pip/RandomVariable.scala

@@ -1,4 +1,4 @@
-package org.mimirdb
+package org.mimirdb.pip
 
 final case class RandomVariable(i: ()=> Float){