Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Port to Spark 3 #302

Open
wants to merge 9 commits into
base: master
Choose a base branch
from
Open

Port to Spark 3 #302

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
c68ab59
Port to Spark 3
thelabdude Jun 22, 2020
ee8a71e
us to_timestamp
thelabdude Jun 22, 2020
a5a346b
Update project version and shade plugin version
kiranchitturi Jun 22, 2020
ee7d302
Use inferTimestamp to get test passing
thelabdude Jun 22, 2020
f564ee5
remove import
thelabdude Jun 22, 2020
ab83577
Change `fMeasure()` to `accuracy()`
falloutdurham Jun 22, 2020
efd0179
Remove DocFilter support
thelabdude Jun 22, 2020
d823ba2
downgrade maven plugin for CI
kiranchitturi Jun 22, 2020
15ec64a
Revert "downgrade maven plugin for CI"
kiranchitturi Jun 22, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
72 changes: 31 additions & 41 deletions pom.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
<modelVersion>4.0.0</modelVersion>
<groupId>com.lucidworks.spark</groupId>
<artifactId>spark-solr</artifactId>
<version>3.9.0-SNAPSHOT</version>
<version>4.0.0-SNAPSHOT</version>
<packaging>jar</packaging>
<name>spark-solr</name>
<description>Tools for reading data from Spark into Solr</description>
Expand Down Expand Up @@ -36,14 +36,14 @@
</distributionManagement>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<java.version>1.8</java.version>
<spark.version>2.4.5</spark.version>
<java.version>11</java.version>
<spark.version>3.0.0</spark.version>
<solr.version>8.4.1</solr.version>
<hadoop.version>2.7.5</hadoop.version>
<fasterxml.version>2.10.1</fasterxml.version>
<scala.version>2.11.12</scala.version>
<scala.binary.version>2.11</scala.binary.version>
<scoverage.plugin.version>1.1.1</scoverage.plugin.version>
<fasterxml.version>2.11.0</fasterxml.version>
<scala.version>2.12.10</scala.version>
<scala.binary.version>2.12</scala.binary.version>
<scoverage.plugin.version>1.4.1</scoverage.plugin.version>
<MaxPermSize>128m</MaxPermSize>
</properties>
<pluginRepositories>
Expand Down Expand Up @@ -78,7 +78,7 @@
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<version>2.10.3</version>
<version>3.2.0</version>
<executions>
<execution>
<id>attach-javadocs</id>
Expand All @@ -98,7 +98,7 @@
<phase>verify</phase>
<goals>
<goal>sign</goal>
</goals>
</goals>
<configuration>
<gpgArguments>
<arg>--pinentry-mode</arg>
Expand All @@ -121,7 +121,7 @@
<plugin>
<groupId>org.jacoco</groupId>
<artifactId>jacoco-maven-plugin</artifactId>
<version>0.7.5.201505241946</version>
<version>0.8.5</version>
<configuration>
<excludes>
<exclude>com/lucidworks/spark/example/**</exclude>
Expand Down Expand Up @@ -156,9 +156,6 @@
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.18.1</version>
<configuration>
<argLine>${argLine} -XX:MaxPermSize=${MaxPermSize}</argLine>
</configuration>
</plugin>
</plugins>
</build>
Expand All @@ -169,7 +166,7 @@
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>3.2.2</version>
<version>4.4.0</version>
<executions>
<execution>
<id>eclipse-add-source</id>
Expand Down Expand Up @@ -213,7 +210,7 @@
</plugin>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.0</version>
<version>3.8.1</version>
<configuration>
<source>${java.version}</source>
<target>${java.version}</target>
Expand All @@ -222,16 +219,13 @@
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>versions-maven-plugin</artifactId>
<version>2.3</version>
<version>2.7</version>
</plugin>
<!-- Surefire runs Java tests -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.18.1</version>
<configuration>
<argLine> -XX:MaxPermSize=${MaxPermSize}</argLine>
</configuration>
<version>2.22.2</version>
</plugin>
<!-- ScalaTest runs Scala tests -->
<plugin>
Expand Down Expand Up @@ -262,7 +256,7 @@
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>3.1.0</version>
<version>3.2.4</version>
<executions>
<execution>
<phase>package</phase>
Expand Down Expand Up @@ -372,7 +366,7 @@
<relocation>
<pattern>org.apache.http</pattern>
<shadedPattern>shaded.apache.http</shadedPattern>
</relocation>
</relocation>
</relocations>
</configuration>
</execution>
Expand Down Expand Up @@ -446,7 +440,7 @@
<dependency>
<groupId>com.esotericsoftware</groupId>
<artifactId>kryo-shaded</artifactId>
<version>3.0.3</version>
<version>4.0.2</version>
<scope>compile</scope>
</dependency>
<dependency>
Expand All @@ -460,20 +454,15 @@
<artifactId>spark-mllib_${scala.binary.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.bahir</groupId>
<artifactId>spark-streaming-twitter_${scala.binary.version}</artifactId>
<version>2.0.1</version>
</dependency>
<dependency>
<groupId>commons-cli</groupId>
<artifactId>commons-cli</artifactId>
<version>1.3.1</version>
<version>1.4</version>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
<version>2.5</version>
<version>2.7</version>
</dependency>
<dependency>
<groupId>org.apache.solr</groupId>
Expand Down Expand Up @@ -594,12 +583,12 @@
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
<version>3.5</version>
<version>3.9</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.12</version>
<version>4.13</version>
<scope>test</scope>
</dependency>
<dependency>
Expand Down Expand Up @@ -639,7 +628,7 @@
<dependency>
<groupId>org.scalatest</groupId>
<artifactId>scalatest_${scala.binary.version}</artifactId>
<version>3.0.3</version>
<version>3.0.8</version>
<scope>test</scope>
</dependency>
<dependency>
Expand All @@ -650,19 +639,20 @@
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-compress</artifactId>
<version>1.19</version>
<version>1.20</version>
</dependency>
<dependency> <!-- optional dependency of joda-time that is mandatory in Scala -->
<!-- optional dependency of joda-time that is mandatory in Scala -->
<!--
<dependency>
<groupId>org.joda</groupId>
<artifactId>joda-convert</artifactId>
<version>1.2</version>
<version>2.2.1</version>
</dependency>
-->
<dependency>
<groupId>com.github.tomakehurst</groupId>
<artifactId>wiremock</artifactId>
<version>1.56</version>
<!-- Include everything below here if you have dependency conflicts -->
<classifier>standalone</classifier>
<groupId>com.github.tomakehurst</groupId>
<artifactId>wiremock-standalone</artifactId>
<version>2.26.3</version>
<exclusions>
<exclusion>
<groupId>org.mortbay.jetty</groupId>
Expand Down
10 changes: 1 addition & 9 deletions src/main/java/com/lucidworks/spark/SparkApp.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,8 +23,6 @@
import com.lucidworks.spark.example.hadoop.Logs2SolrRDDProcessor;
import com.lucidworks.spark.example.query.KMeansAnomaly;
import com.lucidworks.spark.example.query.*;
import com.lucidworks.spark.example.streaming.DocumentFilteringStreamProcessor;
import com.lucidworks.spark.example.streaming.TwitterToSolrStreamProcessor;

import org.apache.commons.cli.CommandLine;
import org.apache.commons.cli.GnuParser;
Expand Down Expand Up @@ -241,14 +239,10 @@ private static RDDProcessor newProcessor(String streamProcType) throws Exception

streamProcType = streamProcType.trim();

if ("twitter-to-solr".equals(streamProcType))
return new TwitterToSolrStreamProcessor();
else if ("word-count".equals(streamProcType))
if ("word-count".equals(streamProcType))
return new WordCount();
else if ("term-vectors".equals(streamProcType))
return new ReadTermVectors();
else if ("docfilter".equals(streamProcType))
return new DocumentFilteringStreamProcessor();
else if ("hdfs-to-solr".equals(streamProcType))
return new HdfsToSolrRDDProcessor();
else if ("logs2solr".equals(streamProcType))
Expand Down Expand Up @@ -278,10 +272,8 @@ else if ("eventsim".equals(streamProcType))

private static void displayProcessorOptions(PrintStream out) throws Exception {
HelpFormatter formatter = new HelpFormatter();
formatter.printHelp("twitter-to-solr", getProcessorOptions(new TwitterToSolrStreamProcessor()));
formatter.printHelp("word-count", getProcessorOptions(new WordCount()));
formatter.printHelp("term-vectors", getProcessorOptions(new ReadTermVectors()));
formatter.printHelp("docfilter", getProcessorOptions(new DocumentFilteringStreamProcessor()));
formatter.printHelp("hdfs-to-solr", getProcessorOptions(new HdfsToSolrRDDProcessor()));
formatter.printHelp("logs2solr", getProcessorOptions(new Logs2SolrRDDProcessor()));
formatter.printHelp("query-solr-benchmark", getProcessorOptions(new QueryBenchmark()));
Expand Down
4 changes: 2 additions & 2 deletions src/main/java/com/lucidworks/spark/example/ml/MLPipeline.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,8 +218,8 @@ public int run(SparkConf conf, CommandLine cli) throws Exception {
System.out.println(confusionMatrix);

// compute the false positive rate per label
System.out.println();
System.out.println("F-Measure: "+metrics.fMeasure());

System.out.println("Accuracy: "+metrics.accuracy());
System.out.println("label\tfpr\n");

String[] labels = labelConverter.getLabels();
Expand Down
Loading