Created
August 3, 2016 19:28
-
-
Save dan-lind/e7ed80b0d64b807ef32e68dbbfa58919 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package kaggle; | |
import org.apache.commons.io.FilenameUtils; | |
import org.apache.spark.SparkConf; | |
import org.apache.spark.api.java.JavaRDD; | |
import org.apache.spark.api.java.JavaSparkContext; | |
import org.datavec.api.records.reader.RecordReader; | |
import org.datavec.api.records.reader.impl.csv.CSVRecordReader; | |
import org.datavec.api.transform.TransformProcess; | |
import org.datavec.api.transform.analysis.DataAnalysis; | |
import org.datavec.api.transform.condition.string.StringRegexColumnCondition; | |
import org.datavec.api.transform.quality.DataQualityAnalysis; | |
import org.datavec.api.transform.schema.Schema; | |
import org.datavec.api.transform.transform.string.ReplaceEmptyStringTransform; | |
import org.datavec.api.writable.DoubleWritable; | |
import org.datavec.api.writable.Writable; | |
import org.datavec.spark.transform.AnalyzeSpark; | |
import org.datavec.spark.transform.SparkTransformExecutor; | |
import org.datavec.spark.transform.misc.StringToWritablesFunction; | |
import java.util.List; | |
import java.util.Map; | |
/** | |
* Simple example performing some preprocessing/aggregation operations on some web log data using DataVec. | |
* Specifically: | |
* - Load some data | |
* - Perform data quality analysis | |
* - Perform basic data cleaning and preprocessing | |
* - Group records by host, and calculate some aggregate values for each (such as number of requests and total number of bytes) | |
* - Analyze the resulting data, and print some results | |
* | |
* | |
* Data is automatically downloaded from: http://ita.ee.lbl.gov/html/contrib/NASA-HTTP.html | |
* | |
* Examples of some log lines | |
* 199.72.81.55 - - [01/Jul/1995:00:00:01 -0400] "GET /history/apollo/ HTTP/1.0" 200 6245 | |
* unicomp6.unicomp.net - - [01/Jul/1995:00:00:06 -0400] "GET /shuttle/countdown/ HTTP/1.0" 200 3985 | |
* | |
* @author Alex Black | |
*/ | |
public class Analysis { | |
/** Data URL for downloading */ | |
public static final String DATA_URL = "ftp://ita.ee.lbl.gov/traces/NASA_access_log_Jul95.gz"; | |
/** Location to save and extract the training/testing data */ | |
public static final String DATA_PATH = FilenameUtils.concat(System.getProperty("java.io.tmpdir"), "datavec_log_example/"); | |
public static final String EXTRACTED_PATH = "/Users/danlin/git/dl4j-lab/src/main/resources/train_mod.csv"; | |
public static void main(String[] args) throws Exception { | |
//Setup | |
// downloadData(); | |
SparkConf conf = new SparkConf(); | |
conf.setMaster("local[*]"); | |
conf.setAppName("DataVec Analysis Data Example"); | |
JavaSparkContext sc = new JavaSparkContext(conf); | |
//===================================================================== | |
// Step 1: Define the input data schema | |
//===================================================================== | |
//First: let's specify a schema for the data. This is based on the information from: http://ita.ee.lbl.gov/html/contrib/NASA-HTTP.html | |
Schema schema = new Schema.Builder() | |
.addColumnInteger("PassengerId") | |
.addColumnCategorical("Survived","0","1") | |
.addColumnCategorical("Pclass","1","2","3") | |
.addColumnString("Name") | |
.addColumnCategorical("Sex","male","female") | |
.addColumnDouble("Age") | |
.addColumnInteger("SibSp") | |
.addColumnInteger("Parch") | |
.addColumnString("Ticket") | |
.addColumnString("Fare") | |
.addColumnString("Cabin") | |
.addColumnCategorical("Embarked", "C", "Q", "S") | |
.build(); | |
//===================================================================== | |
// Step 2: Clean Invalid Lines | |
//===================================================================== | |
//Second: let's load the data. Initially as Strings | |
JavaRDD<String> logLines = sc.textFile(EXTRACTED_PATH); | |
//===================================================================== | |
// Step 3: Parse Raw Data and Perform Initial Analysis | |
//===================================================================== | |
RecordReader rr = new CSVRecordReader(); | |
JavaRDD<List<Writable>> parsed = logLines.map(new StringToWritablesFunction(rr)); | |
Map<Writable, Long> occurences = parsed.map(x -> x.get(11)).countByValue(); | |
occurences.forEach((x,y) -> System.out.println(x.toString() + " : " + y.toString())); | |
double sum = parsed.map(x -> x.get(5)).filter(f -> f.toString().isEmpty() == false).map(y -> y.toDouble()).reduce((a,b) -> a + b); | |
double count = parsed.map(x -> x.get(5)).filter(f -> f.toString().isEmpty() == false).count(); | |
double mean = sum / count; | |
System.out.println("Sum of Age: " + sum); | |
System.out.println("Count of Age: " + count); | |
System.out.println("Mean of Age: " + mean); | |
//Now, let's check the quality, so we know if there's anything we need to clean up first... | |
DataQualityAnalysis dqa = AnalyzeSpark.analyzeQuality(schema, parsed); | |
System.out.println("----- Data Quality -----"); | |
System.out.println(dqa); | |
//==================================================================== | |
// Step 4: Perform Cleaning, Parsing and Aggregation | |
//===================================================================== | |
//Let's specify the transforms we want to do | |
TransformProcess tp = new TransformProcess.Builder(schema) | |
//First: clean up the "replyBytes" column by replacing any non-integer entries with the value 0 | |
.conditionalReplaceValueTransform("Age",new DoubleWritable(mean),new StringRegexColumnCondition ("Age","^$")) | |
.transform(new ReplaceEmptyStringTransform("Embarked","S")) | |
.build(); | |
SparkTransformExecutor executor = new SparkTransformExecutor(); | |
JavaRDD<List<Writable>> processed = executor.execute(parsed, tp); | |
processed.cache(); | |
// | |
// | |
// //===================================================================== | |
// // Step 5: Perform Analysis on Final Data; Display Results | |
// //===================================================================== | |
// | |
Schema finalDataSchema = tp.getFinalSchema(); | |
long finalDataCount = processed.count(); | |
List<List<Writable>> sample = processed.take(10); | |
DataAnalysis analysis = AnalyzeSpark.analyze(finalDataSchema, processed); | |
sc.stop(); | |
Thread.sleep(4000); //Give spark some time to shut down (and stop spamming console) | |
System.out.println("----- Final Data Schema -----"); | |
System.out.println(finalDataSchema); | |
System.out.println("\n\nFinal data count: " + finalDataCount); | |
System.out.println("\n\n----- Samples of final data -----"); | |
for(List<Writable> l : sample){ | |
System.out.println(l); | |
} | |
System.out.println("\n\n----- Analysis -----"); | |
System.out.println(analysis); | |
} | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/bin/java -Didea.launcher.port=7545 "-Didea.launcher.bin.path=/Applications/IntelliJ IDEA CE.app/Contents/bin" -Dfile.encoding=UTF-8 -classpath "/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/charsets.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/deploy.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext/cldrdata.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext/dnsns.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext/jfxrt.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext/localedata.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext/nashorn.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext/sunec.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext/sunjce_provider.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext/sunpkcs11.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/ext/zipfs.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/javaws.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jce.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jfr.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jfxswt.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/jsse.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/management-agent.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/plugin.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/resources.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/jre/lib/rt.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/lib/ant-javafx.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/lib/dt.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/lib/javafx-mx.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/lib/jconsole.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/lib/sa-jdi.jar:/Library/Java/JavaVirtualMachines/jdk1.8.0_25.jdk/Contents/Home/lib/tools.jar:/Users/danlin/git/dl4j-lab/target/classes:/Users/danlin/.m2/repository/org/deeplearning4j/deeplearning4j-nlp/0.4.0/deeplearning4j-nlp-0.4.0.jar:/Users/danlin/.m2/repository/org/apache/lucene/lucene-analyzers-common/5.3.1/lucene-analyzers-common-5.3.1.jar:/Users/danlin/.m2/repository/org/apache/lucene/lucene-core/5.3.1/lucene-core-5.3.1.jar:/Users/danlin/.m2/repository/org/apache/lucene/lucene-queryparser/5.3.1/lucene-queryparser-5.3.1.jar:/Users/danlin/.m2/repository/org/apache/lucene/lucene-queries/5.3.1/lucene-queries-5.3.1.jar:/Users/danlin/.m2/repository/org/apache/lucene/lucene-sandbox/5.3.1/lucene-sandbox-5.3.1.jar:/Users/danlin/.m2/repository/org/apache/directory/studio/org.apache.commons.codec/1.8/org.apache.commons.codec-1.8.jar:/Users/danlin/.m2/repository/commons-codec/commons-codec/1.8/commons-codec-1.8.jar:/Users/danlin/.m2/repository/it/unimi/dsi/dsiutils/2.2.2/dsiutils-2.2.2.jar:/Users/danlin/.m2/repository/it/unimi/dsi/fastutil/6.5.15/fastutil-6.5.15.jar:/Users/danlin/.m2/repository/com/martiansoftware/jsap/2.1/jsap-2.1.jar:/Users/danlin/.m2/repository/commons-configuration/commons-configuration/1.8/commons-configuration-1.8.jar:/Users/danlin/.m2/repository/commons-lang/commons-lang/2.6/commons-lang-2.6.jar:/Users/danlin/.m2/repository/commons-logging/commons-logging/1.1.1/commons-logging-1.1.1.jar:/Users/danlin/.m2/repository/commons-collections/commons-collections/20040616/commons-collections-20040616.jar:/Users/danlin/.m2/repository/org/cleartk/cleartk-snowball/2.0.0/cleartk-snowball-2.0.0.jar:/Users/danlin/.m2/repository/org/apache/lucene/lucene-snowball/3.0.3/lucene-snowball-3.0.3.jar:/Users/danlin/.m2/repository/org/cleartk/cleartk-util/2.0.0/cleartk-util-2.0.0.jar:/Users/danlin/.m2/repository/org/apache/uima/uimaj-core/2.5.0/uimaj-core-2.5.0.jar:/Users/danlin/.m2/repository/org/apache/uima/uimafit-core/2.0.0/uimafit-core-2.0.0.jar:/Users/danlin/.m2/repository/commons-logging/commons-logging-api/1.1/commons-logging-api-1.1.jar:/Users/danlin/.m2/repository/org/springframework/spring-core/3.1.2.RELEASE/spring-core-3.1.2.RELEASE.jar:/Users/danlin/.m2/repository/org/springframework/spring-asm/3.1.2.RELEASE/spring-asm-3.1.2.RELEASE.jar:/Users/danlin/.m2/repository/org/springframework/spring-context/3.1.2.RELEASE/spring-context-3.1.2.RELEASE.jar:/Users/danlin/.m2/repository/org/springframework/spring-aop/3.1.2.RELEASE/spring-aop-3.1.2.RELEASE.jar:/Users/danlin/.m2/repository/aopalliance/aopalliance/1.0/aopalliance-1.0.jar:/Users/danlin/.m2/repository/org/springframework/spring-expression/3.1.2.RELEASE/spring-expression-3.1.2.RELEASE.jar:/Users/danlin/.m2/repository/org/springframework/spring-beans/3.1.2.RELEASE/spring-beans-3.1.2.RELEASE.jar:/Users/danlin/.m2/repository/org/cleartk/cleartk-type-system/2.0.0/cleartk-type-system-2.0.0.jar:/Users/danlin/.m2/repository/org/cleartk/cleartk-opennlp-tools/2.0.0/cleartk-opennlp-tools-2.0.0.jar:/Users/danlin/.m2/repository/org/apache/opennlp/opennlp-maxent/3.0.3/opennlp-maxent-3.0.3.jar:/Users/danlin/.m2/repository/org/apache/opennlp/opennlp-tools/1.5.3/opennlp-tools-1.5.3.jar:/Users/danlin/.m2/repository/net/sf/jwordnet/jwnl/1.3.3/jwnl-1.3.3.jar:/Users/danlin/.m2/repository/org/apache/opennlp/opennlp-uima/1.5.3/opennlp-uima-1.5.3.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-assets/0.8.0/dropwizard-assets-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-core/0.8.0/dropwizard-core-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-util/0.8.0/dropwizard-util-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-jackson/0.8.0/dropwizard-jackson-0.8.0.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/datatype/jackson-datatype-jdk7/2.5.1/jackson-datatype-jdk7-2.5.1.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/datatype/jackson-datatype-guava/2.5.1/jackson-datatype-guava-2.5.1.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/module/jackson-module-afterburner/2.5.1/jackson-module-afterburner-2.5.1.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/datatype/jackson-datatype-joda/2.5.1/jackson-datatype-joda-2.5.1.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-validation/0.8.0/dropwizard-validation-0.8.0.jar:/Users/danlin/.m2/repository/org/hibernate/hibernate-validator/5.1.3.Final/hibernate-validator-5.1.3.Final.jar:/Users/danlin/.m2/repository/org/jboss/logging/jboss-logging/3.1.3.GA/jboss-logging-3.1.3.GA.jar:/Users/danlin/.m2/repository/com/fasterxml/classmate/1.0.0/classmate-1.0.0.jar:/Users/danlin/.m2/repository/org/glassfish/javax.el/3.0.0/javax.el-3.0.0.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-configuration/0.8.0/dropwizard-configuration-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-logging/0.8.0/dropwizard-logging-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-logback/3.1.0/metrics-logback-3.1.0.jar:/Users/danlin/.m2/repository/org/slf4j/log4j-over-slf4j/1.7.10/log4j-over-slf4j-1.7.10.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-util/9.2.9.v20150224/jetty-util-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-metrics/0.8.0/dropwizard-metrics-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-jersey/0.8.0/dropwizard-jersey-0.8.0.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/ext/jersey-metainf-services/2.16/jersey-metainf-services-2.16.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-jersey2/3.1.0/metrics-jersey2-3.1.0.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/jaxrs/jackson-jaxrs-json-provider/2.5.1/jackson-jaxrs-json-provider-2.5.1.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/jaxrs/jackson-jaxrs-base/2.5.1/jackson-jaxrs-base-2.5.1.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/module/jackson-module-jaxb-annotations/2.5.1/jackson-module-jaxb-annotations-2.5.1.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-server/9.2.9.v20150224/jetty-server-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-io/9.2.9.v20150224/jetty-io-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-webapp/9.2.9.v20150224/jetty-webapp-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-xml/9.2.9.v20150224/jetty-xml-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-continuation/9.2.9.v20150224/jetty-continuation-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-jetty/0.8.0/dropwizard-jetty-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-jetty9/3.1.0/metrics-jetty9-3.1.0.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-servlet/9.2.9.v20150224/jetty-servlet-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-security/9.2.9.v20150224/jetty-security-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-servlets/9.2.9.v20150224/jetty-servlets-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/jetty-http/9.2.9.v20150224/jetty-http-9.2.9.v20150224.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-lifecycle/0.8.0/dropwizard-lifecycle-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-servlets/3.1.0/metrics-servlets-3.1.0.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-healthchecks/3.1.0/metrics-healthchecks-3.1.0.jar:/Users/danlin/.m2/repository/net/sourceforge/argparse4j/argparse4j/0.4.4/argparse4j-0.4.4.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/toolchain/setuid/jetty-setuid-java/1.0.2/jetty-setuid-java-1.0.2.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-servlets/0.8.0/dropwizard-servlets-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-annotation/3.1.0/metrics-annotation-3.1.0.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-views-mustache/0.8.0/dropwizard-views-mustache-0.8.0.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-views/0.8.0/dropwizard-views-0.8.0.jar:/Users/danlin/.m2/repository/com/github/spullara/mustache/java/compiler/0.8.17/compiler-0.8.17.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-views-freemarker/0.8.0/dropwizard-views-freemarker-0.8.0.jar:/Users/danlin/.m2/repository/org/nd4j/nd4j-jackson/0.4.0/nd4j-jackson-0.4.0.jar:/Users/danlin/.m2/repository/org/deeplearning4j/deeplearning4j-core/0.4.0/deeplearning4j-core-0.4.0.jar:/Users/danlin/.m2/repository/org/nd4j/canova-nd4j-common/0.0.0.17/canova-nd4j-common-0.0.0.17.jar:/Users/danlin/.m2/repository/org/nd4j/canova-api/0.0.0.17/canova-api-0.0.0.17.jar:/Users/danlin/.m2/repository/org/slf4j/slf4j-api/1.7.12/slf4j-api-1.7.12.jar:/Users/danlin/.m2/repository/ch/qos/logback/logback-classic/1.1.2/logback-classic-1.1.2.jar:/Users/danlin/.m2/repository/ch/qos/logback/logback-core/1.1.2/logback-core-1.1.2.jar:/Users/danlin/.m2/repository/org/apache/commons/commons-math3/3.4.1/commons-math3-3.4.1.jar:/Users/danlin/.m2/repository/commons-io/commons-io/2.4/commons-io-2.4.jar:/Users/danlin/.m2/repository/org/apache/commons/commons-compress/1.8/commons-compress-1.8.jar:/Users/danlin/.m2/repository/org/tukaani/xz/1.5/xz-1.5.jar:/Users/danlin/.m2/repository/org/nd4j/nd4j-api/0.4.0/nd4j-api-0.4.0.jar:/Users/danlin/.m2/repository/org/nd4j/nd4j-context/0.4.0/nd4j-context-0.4.0.jar:/Users/danlin/.m2/repository/org/apache/commons/commons-lang3/3.3.1/commons-lang3-3.3.1.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/core/jackson-core/2.5.1/jackson-core-2.5.1.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/core/jackson-databind/2.4.4/jackson-databind-2.4.4.jar:/Users/danlin/.m2/repository/org/json/json/20131018/json-20131018.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/core/jackson-annotations/2.5.1/jackson-annotations-2.5.1.jar:/Users/danlin/.m2/repository/org/projectlombok/lombok/1.16.4/lombok-1.16.4.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/dataformat/jackson-dataformat-yaml/2.5.1/jackson-dataformat-yaml-2.5.1.jar:/Users/danlin/.m2/repository/org/yaml/snakeyaml/1.12/snakeyaml-1.12.jar:/Users/danlin/.m2/repository/org/datavec/datavec-nd4j-common/0.4.0/datavec-nd4j-common-0.4.0.jar:/Users/danlin/.m2/repository/org/datavec/datavec-data-image/0.4.0/datavec-data-image-0.4.0.jar:/Users/danlin/.m2/repository/org/deeplearning4j/deeplearning4j-ui/0.4.0/deeplearning4j-ui-0.4.0.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-client/0.8.0/dropwizard-client-0.8.0.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/core/jersey-client/2.16/jersey-client-2.16.jar:/Users/danlin/.m2/repository/javax/ws/rs/javax.ws.rs-api/2.0.1/javax.ws.rs-api-2.0.1.jar:/Users/danlin/.m2/repository/org/glassfish/hk2/hk2-api/2.4.0-b09/hk2-api-2.4.0-b09.jar:/Users/danlin/.m2/repository/org/glassfish/hk2/hk2-utils/2.4.0-b09/hk2-utils-2.4.0-b09.jar:/Users/danlin/.m2/repository/org/glassfish/hk2/external/aopalliance-repackaged/2.4.0-b09/aopalliance-repackaged-2.4.0-b09.jar:/Users/danlin/.m2/repository/org/glassfish/hk2/external/javax.inject/2.4.0-b09/javax.inject-2.4.0-b09.jar:/Users/danlin/.m2/repository/org/glassfish/hk2/hk2-locator/2.4.0-b09/hk2-locator-2.4.0-b09.jar:/Users/danlin/.m2/repository/org/javassist/javassist/3.18.1-GA/javassist-3.18.1-GA.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-httpclient/3.1.0/metrics-httpclient-3.1.0.jar:/Users/danlin/.m2/repository/org/apache/httpcomponents/httpclient/4.3.5/httpclient-4.3.5.jar:/Users/danlin/.m2/repository/org/apache/httpcomponents/httpcore/4.3.2/httpcore-4.3.2.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/connectors/jersey-apache-connector/2.16/jersey-apache-connector-2.16.jar:/Users/danlin/.m2/repository/io/dropwizard/dropwizard-forms/0.8.0/dropwizard-forms-0.8.0.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/media/jersey-media-multipart/2.16/jersey-media-multipart-2.16.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/core/jersey-common/2.16/jersey-common-2.16.jar:/Users/danlin/.m2/repository/javax/annotation/javax.annotation-api/1.2/javax.annotation-api-1.2.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/bundles/repackaged/jersey-guava/2.16/jersey-guava-2.16.jar:/Users/danlin/.m2/repository/org/glassfish/hk2/osgi-resource-locator/1.0.1/osgi-resource-locator-1.0.1.jar:/Users/danlin/.m2/repository/org/jvnet/mimepull/mimepull/1.9.3/mimepull-1.9.3.jar:/Users/danlin/.m2/repository/com/google/guava/guava/19.0/guava-19.0.jar:/Users/danlin/.m2/repository/org/nd4j/nd4j-native/0.4.0/nd4j-native-0.4.0.jar:/Users/danlin/.m2/repository/org/nd4j/nd4j-native/0.4.0/nd4j-native-0.4.0-macosx-x86_64.jar:/Users/danlin/.m2/repository/org/nd4j/nd4j-native-api/0.4.0/nd4j-native-api-0.4.0.jar:/Users/danlin/.m2/repository/org/bytedeco/javacpp/1.2.2/javacpp-1.2.2.jar:/Users/danlin/.m2/repository/org/nd4j/canova-nd4j-image/0.0.0.17/canova-nd4j-image-0.0.0.17.jar:/Users/danlin/.m2/repository/org/nd4j/nd4j-buffer/0.4.0/nd4j-buffer-0.4.0.jar:/Users/danlin/.m2/repository/org/nd4j/nd4j-common/0.4.0/nd4j-common-0.4.0.jar:/Users/danlin/.m2/repository/org/reflections/reflections/0.9.10/reflections-0.9.10.jar:/Users/danlin/.m2/repository/com/google/code/findbugs/annotations/2.0.1/annotations-2.0.1.jar:/Users/danlin/.m2/repository/org/nd4j/canova-data-image/0.0.0.17/canova-data-image-0.0.0.17.jar:/Users/danlin/.m2/repository/com/github/jai-imageio/jai-imageio-core/1.3.0/jai-imageio-core-1.3.0.jar:/Users/danlin/.m2/repository/com/twelvemonkeys/imageio/imageio-jpeg/3.1.1/imageio-jpeg-3.1.1.jar:/Users/danlin/.m2/repository/com/twelvemonkeys/imageio/imageio-core/3.1.1/imageio-core-3.1.1.jar:/Users/danlin/.m2/repository/com/twelvemonkeys/imageio/imageio-metadata/3.1.1/imageio-metadata-3.1.1.jar:/Users/danlin/.m2/repository/com/twelvemonkeys/common/common-lang/3.1.1/common-lang-3.1.1.jar:/Users/danlin/.m2/repository/com/twelvemonkeys/common/common-io/3.1.1/common-io-3.1.1.jar:/Users/danlin/.m2/repository/com/twelvemonkeys/common/common-image/3.1.1/common-image-3.1.1.jar:/Users/danlin/.m2/repository/com/twelvemonkeys/imageio/imageio-tiff/3.1.1/imageio-tiff-3.1.1.jar:/Users/danlin/.m2/repository/com/twelvemonkeys/imageio/imageio-psd/3.1.1/imageio-psd-3.1.1.jar:/Users/danlin/.m2/repository/com/twelvemonkeys/imageio/imageio-bmp/3.1.1/imageio-bmp-3.1.1.jar:/Users/danlin/.m2/repository/org/bytedeco/javacv/1.2/javacv-1.2.jar:/Users/danlin/.m2/repository/org/bytedeco/javacpp-presets/opencv/3.1.0-1.2/opencv-3.1.0-1.2.jar:/Users/danlin/.m2/repository/org/bytedeco/javacpp-presets/opencv/3.1.0-1.2/opencv-3.1.0-1.2-macosx-x86_64.jar:/Users/danlin/.m2/repository/org/bytedeco/javacpp-presets/ffmpeg/3.0.2-1.2/ffmpeg-3.0.2-1.2.jar:/Users/danlin/.m2/repository/org/bytedeco/javacpp-presets/ffmpeg/3.0.2-1.2/ffmpeg-3.0.2-1.2-macosx-x86_64.jar:/Users/danlin/.m2/repository/org/bytedeco/javacpp-presets/leptonica/1.73-1.2/leptonica-1.73-1.2.jar:/Users/danlin/.m2/repository/org/bytedeco/javacpp-presets/leptonica/1.73-1.2/leptonica-1.73-1.2-macosx-x86_64.jar:/Users/danlin/.m2/repository/org/nd4j/canova-nd4j-codec/0.0.0.17/canova-nd4j-codec-0.0.0.17.jar:/Users/danlin/.m2/repository/org/jcodec/jcodec/0.1.5/jcodec-0.1.5.jar:/Users/danlin/.m2/repository/org/deeplearning4j/arbiter-deeplearning4j/0.4.1-SNAPSHOT/arbiter-deeplearning4j-0.4.1-SNAPSHOT.jar:/Users/danlin/.m2/repository/org/deeplearning4j/arbiter-core/0.4.1-SNAPSHOT/arbiter-core-0.4.1-SNAPSHOT.jar:/Users/danlin/.m2/repository/args4j/args4j/2.33/args4j-2.33.jar:/Users/danlin/.m2/repository/org/deeplearning4j/deeplearning4j-ui-components/0.4.1-SNAPSHOT/deeplearning4j-ui-components-0.4.1-SNAPSHOT.jar:/Users/danlin/.m2/repository/org/datavec/datavec-api/0.4.0/datavec-api-0.4.0.jar:/Users/danlin/.m2/repository/joda-time/joda-time/2.9.2/joda-time-2.9.2.jar:/Users/danlin/.m2/repository/org/freemarker/freemarker/2.3.23/freemarker-2.3.23.jar:/Users/danlin/.m2/repository/org/datavec/datavec-spark_2.10/0.4.0/datavec-spark_2.10-0.4.0.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-core_2.11/1.5.1/spark-core_2.11-1.5.1.jar:/Users/danlin/.m2/repository/org/apache/avro/avro-mapred/1.7.7/avro-mapred-1.7.7-hadoop2.jar:/Users/danlin/.m2/repository/org/apache/avro/avro-ipc/1.7.7/avro-ipc-1.7.7.jar:/Users/danlin/.m2/repository/org/apache/avro/avro/1.7.7/avro-1.7.7.jar:/Users/danlin/.m2/repository/org/apache/avro/avro-ipc/1.7.7/avro-ipc-1.7.7-tests.jar:/Users/danlin/.m2/repository/org/codehaus/jackson/jackson-core-asl/1.9.13/jackson-core-asl-1.9.13.jar:/Users/danlin/.m2/repository/org/codehaus/jackson/jackson-mapper-asl/1.9.13/jackson-mapper-asl-1.9.13.jar:/Users/danlin/.m2/repository/com/twitter/chill_2.11/0.5.0/chill_2.11-0.5.0.jar:/Users/danlin/.m2/repository/com/esotericsoftware/kryo/kryo/2.21/kryo-2.21.jar:/Users/danlin/.m2/repository/com/esotericsoftware/reflectasm/reflectasm/1.07/reflectasm-1.07-shaded.jar:/Users/danlin/.m2/repository/com/esotericsoftware/minlog/minlog/1.2/minlog-1.2.jar:/Users/danlin/.m2/repository/org/objenesis/objenesis/1.2/objenesis-1.2.jar:/Users/danlin/.m2/repository/com/twitter/chill-java/0.5.0/chill-java-0.5.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-client/2.2.0/hadoop-client-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-common/2.2.0/hadoop-common-2.2.0.jar:/Users/danlin/.m2/repository/commons-cli/commons-cli/1.2/commons-cli-1.2.jar:/Users/danlin/.m2/repository/org/apache/commons/commons-math/2.1/commons-math-2.1.jar:/Users/danlin/.m2/repository/xmlenc/xmlenc/0.52/xmlenc-0.52.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-auth/2.2.0/hadoop-auth-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-hdfs/2.2.0/hadoop-hdfs-2.2.0.jar:/Users/danlin/.m2/repository/org/mortbay/jetty/jetty-util/6.1.26/jetty-util-6.1.26.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-mapreduce-client-app/2.2.0/hadoop-mapreduce-client-app-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-mapreduce-client-common/2.2.0/hadoop-mapreduce-client-common-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-yarn-client/2.2.0/hadoop-yarn-client-2.2.0.jar:/Users/danlin/.m2/repository/com/google/inject/guice/3.0/guice-3.0.jar:/Users/danlin/.m2/repository/javax/inject/javax.inject/1/javax.inject-1.jar:/Users/danlin/.m2/repository/com/sun/jersey/jersey-test-framework/jersey-test-framework-grizzly2/1.9/jersey-test-framework-grizzly2-1.9.jar:/Users/danlin/.m2/repository/com/sun/jersey/jersey-test-framework/jersey-test-framework-core/1.9/jersey-test-framework-core-1.9.jar:/Users/danlin/.m2/repository/com/sun/jersey/jersey-client/1.9/jersey-client-1.9.jar:/Users/danlin/.m2/repository/com/sun/jersey/jersey-grizzly2/1.9/jersey-grizzly2-1.9.jar:/Users/danlin/.m2/repository/org/glassfish/grizzly/grizzly-http/2.1.2/grizzly-http-2.1.2.jar:/Users/danlin/.m2/repository/org/glassfish/grizzly/grizzly-framework/2.1.2/grizzly-framework-2.1.2.jar:/Users/danlin/.m2/repository/org/glassfish/gmbal/gmbal-api-only/3.0.0-b023/gmbal-api-only-3.0.0-b023.jar:/Users/danlin/.m2/repository/org/glassfish/external/management-api/3.0.0-b012/management-api-3.0.0-b012.jar:/Users/danlin/.m2/repository/org/glassfish/grizzly/grizzly-http-server/2.1.2/grizzly-http-server-2.1.2.jar:/Users/danlin/.m2/repository/org/glassfish/grizzly/grizzly-rcm/2.1.2/grizzly-rcm-2.1.2.jar:/Users/danlin/.m2/repository/org/glassfish/grizzly/grizzly-http-servlet/2.1.2/grizzly-http-servlet-2.1.2.jar:/Users/danlin/.m2/repository/org/glassfish/javax.servlet/3.1/javax.servlet-3.1.jar:/Users/danlin/.m2/repository/com/sun/jersey/jersey-json/1.9/jersey-json-1.9.jar:/Users/danlin/.m2/repository/org/codehaus/jettison/jettison/1.1/jettison-1.1.jar:/Users/danlin/.m2/repository/stax/stax-api/1.0.1/stax-api-1.0.1.jar:/Users/danlin/.m2/repository/com/sun/xml/bind/jaxb-impl/2.2.3-1/jaxb-impl-2.2.3-1.jar:/Users/danlin/.m2/repository/javax/xml/bind/jaxb-api/2.2.2/jaxb-api-2.2.2.jar:/Users/danlin/.m2/repository/javax/activation/activation/1.1/activation-1.1.jar:/Users/danlin/.m2/repository/org/codehaus/jackson/jackson-jaxrs/1.8.3/jackson-jaxrs-1.8.3.jar:/Users/danlin/.m2/repository/org/codehaus/jackson/jackson-xc/1.8.3/jackson-xc-1.8.3.jar:/Users/danlin/.m2/repository/com/sun/jersey/contribs/jersey-guice/1.9/jersey-guice-1.9.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-yarn-server-common/2.2.0/hadoop-yarn-server-common-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-mapreduce-client-shuffle/2.2.0/hadoop-mapreduce-client-shuffle-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-yarn-api/2.2.0/hadoop-yarn-api-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-mapreduce-client-core/2.2.0/hadoop-mapreduce-client-core-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-yarn-common/2.2.0/hadoop-yarn-common-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-mapreduce-client-jobclient/2.2.0/hadoop-mapreduce-client-jobclient-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/hadoop/hadoop-annotations/2.2.0/hadoop-annotations-2.2.0.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-launcher_2.11/1.5.1/spark-launcher_2.11-1.5.1.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-network-common_2.11/1.5.1/spark-network-common_2.11-1.5.1.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-network-shuffle_2.11/1.5.1/spark-network-shuffle_2.11-1.5.1.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-unsafe_2.11/1.5.1/spark-unsafe_2.11-1.5.1.jar:/Users/danlin/.m2/repository/net/java/dev/jets3t/jets3t/0.7.1/jets3t-0.7.1.jar:/Users/danlin/.m2/repository/commons-httpclient/commons-httpclient/3.1/commons-httpclient-3.1.jar:/Users/danlin/.m2/repository/org/apache/curator/curator-recipes/2.4.0/curator-recipes-2.4.0.jar:/Users/danlin/.m2/repository/org/apache/curator/curator-framework/2.4.0/curator-framework-2.4.0.jar:/Users/danlin/.m2/repository/org/apache/zookeeper/zookeeper/3.4.5/zookeeper-3.4.5.jar:/Users/danlin/.m2/repository/jline/jline/0.9.94/jline-0.9.94.jar:/Users/danlin/.m2/repository/org/eclipse/jetty/orbit/javax.servlet/3.0.0.v201112011016/javax.servlet-3.0.0.v201112011016.jar:/Users/danlin/.m2/repository/com/google/code/findbugs/jsr305/1.3.9/jsr305-1.3.9.jar:/Users/danlin/.m2/repository/org/slf4j/jul-to-slf4j/1.7.10/jul-to-slf4j-1.7.10.jar:/Users/danlin/.m2/repository/org/slf4j/jcl-over-slf4j/1.7.10/jcl-over-slf4j-1.7.10.jar:/Users/danlin/.m2/repository/com/ning/compress-lzf/1.0.3/compress-lzf-1.0.3.jar:/Users/danlin/.m2/repository/org/xerial/snappy/snappy-java/1.1.1.7/snappy-java-1.1.1.7.jar:/Users/danlin/.m2/repository/net/jpountz/lz4/lz4/1.3.0/lz4-1.3.0.jar:/Users/danlin/.m2/repository/org/roaringbitmap/RoaringBitmap/0.4.5/RoaringBitmap-0.4.5.jar:/Users/danlin/.m2/repository/commons-net/commons-net/2.2/commons-net-2.2.jar:/Users/danlin/.m2/repository/com/typesafe/akka/akka-remote_2.11/2.3.11/akka-remote_2.11-2.3.11.jar:/Users/danlin/.m2/repository/com/typesafe/akka/akka-actor_2.11/2.3.11/akka-actor_2.11-2.3.11.jar:/Users/danlin/.m2/repository/com/typesafe/config/1.2.1/config-1.2.1.jar:/Users/danlin/.m2/repository/com/google/protobuf/protobuf-java/2.5.0/protobuf-java-2.5.0.jar:/Users/danlin/.m2/repository/org/uncommons/maths/uncommons-maths/1.2.2a/uncommons-maths-1.2.2a.jar:/Users/danlin/.m2/repository/com/typesafe/akka/akka-slf4j_2.11/2.3.11/akka-slf4j_2.11-2.3.11.jar:/Users/danlin/.m2/repository/org/scala-lang/scala-library/2.11.7/scala-library-2.11.7.jar:/Users/danlin/.m2/repository/org/json4s/json4s-jackson_2.11/3.2.10/json4s-jackson_2.11-3.2.10.jar:/Users/danlin/.m2/repository/org/json4s/json4s-core_2.11/3.2.10/json4s-core_2.11-3.2.10.jar:/Users/danlin/.m2/repository/org/json4s/json4s-ast_2.11/3.2.10/json4s-ast_2.11-3.2.10.jar:/Users/danlin/.m2/repository/org/scala-lang/scalap/2.11.0/scalap-2.11.0.jar:/Users/danlin/.m2/repository/org/scala-lang/scala-compiler/2.11.0/scala-compiler-2.11.0.jar:/Users/danlin/.m2/repository/org/scala-lang/modules/scala-xml_2.11/1.0.1/scala-xml_2.11-1.0.1.jar:/Users/danlin/.m2/repository/org/scala-lang/modules/scala-parser-combinators_2.11/1.0.1/scala-parser-combinators_2.11-1.0.1.jar:/Users/danlin/.m2/repository/com/sun/jersey/jersey-server/1.9/jersey-server-1.9.jar:/Users/danlin/.m2/repository/asm/asm/3.1/asm-3.1.jar:/Users/danlin/.m2/repository/com/sun/jersey/jersey-core/1.9/jersey-core-1.9.jar:/Users/danlin/.m2/repository/org/apache/mesos/mesos/0.21.1/mesos-0.21.1-shaded-protobuf.jar:/Users/danlin/.m2/repository/io/netty/netty-all/4.0.29.Final/netty-all-4.0.29.Final.jar:/Users/danlin/.m2/repository/com/clearspring/analytics/stream/2.7.0/stream-2.7.0.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-core/3.1.2/metrics-core-3.1.2.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-jvm/3.1.2/metrics-jvm-3.1.2.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-json/3.1.2/metrics-json-3.1.2.jar:/Users/danlin/.m2/repository/io/dropwizard/metrics/metrics-graphite/3.1.2/metrics-graphite-3.1.2.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/module/jackson-module-scala_2.11/2.4.4/jackson-module-scala_2.11-2.4.4.jar:/Users/danlin/.m2/repository/org/scala-lang/scala-reflect/2.11.2/scala-reflect-2.11.2.jar:/Users/danlin/.m2/repository/com/thoughtworks/paranamer/paranamer/2.6/paranamer-2.6.jar:/Users/danlin/.m2/repository/org/apache/ivy/ivy/2.4.0/ivy-2.4.0.jar:/Users/danlin/.m2/repository/oro/oro/2.0.8/oro-2.0.8.jar:/Users/danlin/.m2/repository/org/tachyonproject/tachyon-client/0.7.1/tachyon-client-0.7.1.jar:/Users/danlin/.m2/repository/org/apache/curator/curator-client/2.1.0-incubating/curator-client-2.1.0-incubating.jar:/Users/danlin/.m2/repository/org/tachyonproject/tachyon-underfs-hdfs/0.7.1/tachyon-underfs-hdfs-0.7.1.jar:/Users/danlin/.m2/repository/org/tachyonproject/tachyon-underfs-local/0.7.1/tachyon-underfs-local-0.7.1.jar:/Users/danlin/.m2/repository/net/razorvine/pyrolite/4.4/pyrolite-4.4.jar:/Users/danlin/.m2/repository/net/sf/py4j/py4j/0.8.2.1/py4j-0.8.2.1.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-mllib_2.10/2.0.0/spark-mllib_2.10-2.0.0.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-core_2.10/2.0.0/spark-core_2.10-2.0.0.jar:/Users/danlin/.m2/repository/com/twitter/chill_2.10/0.8.0/chill_2.10-0.8.0.jar:/Users/danlin/.m2/repository/com/esotericsoftware/kryo-shaded/3.0.3/kryo-shaded-3.0.3.jar:/Users/danlin/.m2/repository/com/esotericsoftware/minlog/1.3.0/minlog-1.3.0.jar:/Users/danlin/.m2/repository/org/apache/xbean/xbean-asm5-shaded/4.4/xbean-asm5-shaded-4.4.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-launcher_2.10/2.0.0/spark-launcher_2.10-2.0.0.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-network-common_2.10/2.0.0/spark-network-common_2.10-2.0.0.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-network-shuffle_2.10/2.0.0/spark-network-shuffle_2.10-2.0.0.jar:/Users/danlin/.m2/repository/org/fusesource/leveldbjni/leveldbjni-all/1.8/leveldbjni-all-1.8.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-unsafe_2.10/2.0.0/spark-unsafe_2.10-2.0.0.jar:/Users/danlin/.m2/repository/javax/servlet/javax.servlet-api/3.1.0/javax.servlet-api-3.1.0.jar:/Users/danlin/.m2/repository/org/json4s/json4s-jackson_2.10/3.2.11/json4s-jackson_2.10-3.2.11.jar:/Users/danlin/.m2/repository/org/json4s/json4s-core_2.10/3.2.11/json4s-core_2.10-3.2.11.jar:/Users/danlin/.m2/repository/org/json4s/json4s-ast_2.10/3.2.11/json4s-ast_2.10-3.2.11.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/core/jersey-server/2.22.2/jersey-server-2.22.2.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/media/jersey-media-jaxb/2.22.2/jersey-media-jaxb-2.22.2.jar:/Users/danlin/.m2/repository/javax/validation/validation-api/1.1.0.Final/validation-api-1.1.0.Final.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/containers/jersey-container-servlet/2.22.2/jersey-container-servlet-2.22.2.jar:/Users/danlin/.m2/repository/org/glassfish/jersey/containers/jersey-container-servlet-core/2.22.2/jersey-container-servlet-core-2.22.2.jar:/Users/danlin/.m2/repository/io/netty/netty/3.8.0.Final/netty-3.8.0.Final.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/module/jackson-module-scala_2.10/2.6.5/jackson-module-scala_2.10-2.6.5.jar:/Users/danlin/.m2/repository/com/fasterxml/jackson/module/jackson-module-paranamer/2.6.5/jackson-module-paranamer-2.6.5.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-streaming_2.10/2.0.0/spark-streaming_2.10-2.0.0.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-sql_2.10/2.0.0/spark-sql_2.10-2.0.0.jar:/Users/danlin/.m2/repository/com/univocity/univocity-parsers/2.1.1/univocity-parsers-2.1.1.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-sketch_2.10/2.0.0/spark-sketch_2.10-2.0.0.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-catalyst_2.10/2.0.0/spark-catalyst_2.10-2.0.0.jar:/Users/danlin/.m2/repository/org/codehaus/janino/janino/2.7.8/janino-2.7.8.jar:/Users/danlin/.m2/repository/org/codehaus/janino/commons-compiler/2.7.8/commons-compiler-2.7.8.jar:/Users/danlin/.m2/repository/org/antlr/antlr4-runtime/4.5.3/antlr4-runtime-4.5.3.jar:/Users/danlin/.m2/repository/org/apache/parquet/parquet-column/1.7.0/parquet-column-1.7.0.jar:/Users/danlin/.m2/repository/org/apache/parquet/parquet-common/1.7.0/parquet-common-1.7.0.jar:/Users/danlin/.m2/repository/org/apache/parquet/parquet-encoding/1.7.0/parquet-encoding-1.7.0.jar:/Users/danlin/.m2/repository/org/apache/parquet/parquet-generator/1.7.0/parquet-generator-1.7.0.jar:/Users/danlin/.m2/repository/org/apache/parquet/parquet-hadoop/1.7.0/parquet-hadoop-1.7.0.jar:/Users/danlin/.m2/repository/org/apache/parquet/parquet-format/2.3.0-incubating/parquet-format-2.3.0-incubating.jar:/Users/danlin/.m2/repository/org/apache/parquet/parquet-jackson/1.7.0/parquet-jackson-1.7.0.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-graphx_2.10/2.0.0/spark-graphx_2.10-2.0.0.jar:/Users/danlin/.m2/repository/com/github/fommil/netlib/core/1.1.2/core-1.1.2.jar:/Users/danlin/.m2/repository/net/sourceforge/f2j/arpack_combined_all/0.1/arpack_combined_all-0.1.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-mllib-local_2.10/2.0.0/spark-mllib-local_2.10-2.0.0.jar:/Users/danlin/.m2/repository/org/scalanlp/breeze_2.10/0.11.2/breeze_2.10-0.11.2.jar:/Users/danlin/.m2/repository/org/scalanlp/breeze-macros_2.10/0.11.2/breeze-macros_2.10-0.11.2.jar:/Users/danlin/.m2/repository/org/scalamacros/quasiquotes_2.10/2.0.0-M8/quasiquotes_2.10-2.0.0-M8.jar:/Users/danlin/.m2/repository/net/sf/opencsv/opencsv/2.3/opencsv-2.3.jar:/Users/danlin/.m2/repository/com/github/rwl/jtransforms/2.4.0/jtransforms-2.4.0.jar:/Users/danlin/.m2/repository/org/spire-math/spire_2.10/0.7.4/spire_2.10-0.7.4.jar:/Users/danlin/.m2/repository/org/spire-math/spire-macros_2.10/0.7.4/spire-macros_2.10-0.7.4.jar:/Users/danlin/.m2/repository/org/jpmml/pmml-model/1.2.15/pmml-model-1.2.15.jar:/Users/danlin/.m2/repository/org/jpmml/pmml-schema/1.2.15/pmml-schema-1.2.15.jar:/Users/danlin/.m2/repository/org/apache/spark/spark-tags_2.10/2.0.0/spark-tags_2.10-2.0.0.jar:/Users/danlin/.m2/repository/org/scalatest/scalatest_2.10/2.2.6/scalatest_2.10-2.2.6.jar:/Users/danlin/.m2/repository/org/spark-project/spark/unused/1.0.0/unused-1.0.0.jar:/Applications/IntelliJ IDEA CE.app/Contents/lib/idea_rt.jar" com.intellij.rt.execution.application.AppMain kaggle.Analysis | |
16/08/03 21:25:08 INFO o.a.s.SparkContext: Running Spark version 1.5.1 | |
16/08/03 21:25:10 INFO o.a.s.SecurityManager: Changing view acls to: danlin | |
16/08/03 21:25:10 INFO o.a.s.SecurityManager: Changing modify acls to: danlin | |
16/08/03 21:25:10 INFO o.a.s.SecurityManager: SecurityManager: authentication disabled; ui acls disabled; users with view permissions: Set(danlin); users with modify permissions: Set(danlin) | |
16/08/03 21:25:15 INFO o.a.s.u.Utils: Successfully started service 'sparkDriver' on port 50596. | |
16/08/03 21:25:16 INFO o.a.s.SparkEnv: Registering MapOutputTracker | |
16/08/03 21:25:16 INFO o.a.s.SparkEnv: Registering BlockManagerMaster | |
16/08/03 21:25:16 INFO o.a.s.s.DiskBlockManager: Created local directory at /private/var/folders/tk/2t_ll0bs5ml458g35b118h3r0000gp/T/blockmgr-561b0c3b-e564-49b8-b471-2011a154666f | |
16/08/03 21:25:16 INFO o.a.s.s.MemoryStore: MemoryStore started with capacity 983.1 MB | |
16/08/03 21:25:16 INFO o.a.s.HttpFileServer: HTTP File server directory is /private/var/folders/tk/2t_ll0bs5ml458g35b118h3r0000gp/T/spark-2a892f8e-3eb9-4a60-ba0c-fb661129ba9e/httpd-61969d90-88f9-4b68-8817-adb98523e201 | |
16/08/03 21:25:16 INFO o.a.s.HttpServer: Starting HTTP Server | |
16/08/03 21:25:16 INFO o.a.s.u.Utils: Successfully started service 'HTTP file server' on port 50597. | |
16/08/03 21:25:17 INFO o.a.s.SparkEnv: Registering OutputCommitCoordinator | |
16/08/03 21:25:17 INFO o.a.s.u.Utils: Successfully started service 'SparkUI' on port 4040. | |
16/08/03 21:25:17 INFO o.a.s.u.SparkUI: Started SparkUI at http://192.168.0.5:4040 | |
16/08/03 21:25:18 WARN o.a.s.m.MetricsSystem: Using default name DAGScheduler for source because spark.app.id is not set. | |
16/08/03 21:25:18 INFO o.a.s.e.Executor: Starting executor ID driver on host localhost | |
16/08/03 21:25:19 INFO o.a.s.u.Utils: Successfully started service 'org.apache.spark.network.netty.NettyBlockTransferService' on port 50602. | |
16/08/03 21:25:19 INFO o.a.s.n.n.NettyBlockTransferService: Server created on 50602 | |
16/08/03 21:25:19 INFO o.a.s.s.BlockManagerMaster: Trying to register BlockManager | |
16/08/03 21:25:19 INFO o.a.s.s.BlockManagerMasterEndpoint: Registering block manager localhost:50602 with 983.1 MB RAM, BlockManagerId(driver, localhost, 50602) | |
16/08/03 21:25:19 INFO o.a.s.s.BlockManagerMaster: Registered BlockManager | |
16/08/03 21:25:20 INFO o.a.s.s.MemoryStore: ensureFreeSpace(110248) called with curMem=0, maxMem=1030823608 | |
16/08/03 21:25:20 INFO o.a.s.s.MemoryStore: Block broadcast_0 stored as values in memory (estimated size 107.7 KB, free 983.0 MB) | |
16/08/03 21:25:20 INFO o.a.s.s.MemoryStore: ensureFreeSpace(10065) called with curMem=110248, maxMem=1030823608 | |
16/08/03 21:25:20 INFO o.a.s.s.MemoryStore: Block broadcast_0_piece0 stored as bytes in memory (estimated size 9.8 KB, free 983.0 MB) | |
16/08/03 21:25:20 INFO o.a.s.s.BlockManagerInfo: Added broadcast_0_piece0 in memory on localhost:50602 (size: 9.8 KB, free: 983.1 MB) | |
16/08/03 21:25:20 INFO o.a.s.SparkContext: Created broadcast 0 from textFile at Analysis.java:85 | |
16/08/03 21:25:22 INFO o.a.s.SparkContext: Starting job: countByValue at Analysis.java:95 | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Registering RDD 5 (countByValue at Analysis.java:95) | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Got job 0 (countByValue at Analysis.java:95) with 2 output partitions | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 1(countByValue at Analysis.java:95) | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Parents of final stage: List(ShuffleMapStage 0) | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Missing parents: List(ShuffleMapStage 0) | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Submitting ShuffleMapStage 0 (MapPartitionsRDD[5] at countByValue at Analysis.java:95), which has no missing parents | |
16/08/03 21:25:22 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5968) called with curMem=120313, maxMem=1030823608 | |
16/08/03 21:25:22 INFO o.a.s.s.MemoryStore: Block broadcast_1 stored as values in memory (estimated size 5.8 KB, free 982.9 MB) | |
16/08/03 21:25:22 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3333) called with curMem=126281, maxMem=1030823608 | |
16/08/03 21:25:22 INFO o.a.s.s.MemoryStore: Block broadcast_1_piece0 stored as bytes in memory (estimated size 3.3 KB, free 982.9 MB) | |
16/08/03 21:25:22 INFO o.a.s.s.BlockManagerInfo: Added broadcast_1_piece0 in memory on localhost:50602 (size: 3.3 KB, free: 983.1 MB) | |
16/08/03 21:25:22 INFO o.a.s.SparkContext: Created broadcast 1 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ShuffleMapStage 0 (MapPartitionsRDD[5] at countByValue at Analysis.java:95) | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 0.0 with 2 tasks | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 0.0 (TID 0, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 0.0 (TID 1, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:22 INFO o.a.s.e.Executor: Running task 0.0 in stage 0.0 (TID 0) | |
16/08/03 21:25:22 INFO o.a.s.e.Executor: Running task 1.0 in stage 0.0 (TID 1) | |
16/08/03 21:25:22 INFO o.a.s.r.HadoopRDD: Input split: file:/Users/danlin/git/dl4j-lab/src/main/resources/train_mod.csv:0+30111 | |
16/08/03 21:25:22 INFO o.a.s.r.HadoopRDD: Input split: file:/Users/danlin/git/dl4j-lab/src/main/resources/train_mod.csv:30111+30111 | |
16/08/03 21:25:22 INFO o.a.s.e.Executor: Finished task 1.0 in stage 0.0 (TID 1). 2254 bytes result sent to driver | |
16/08/03 21:25:22 INFO o.a.s.e.Executor: Finished task 0.0 in stage 0.0 (TID 0). 2254 bytes result sent to driver | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 0.0 (TID 1) in 482 ms on localhost (1/2) | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 0.0 (TID 0) in 544 ms on localhost (2/2) | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 0.0, whose tasks have all completed, from pool | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: ShuffleMapStage 0 (countByValue at Analysis.java:95) finished in 0,587 s | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: looking for newly runnable stages | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: running: Set() | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: waiting: Set(ResultStage 1) | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: failed: Set() | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Missing parents for ResultStage 1: List() | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 1 (ShuffledRDD[6] at countByValue at Analysis.java:95), which is now runnable | |
16/08/03 21:25:22 INFO o.a.s.s.MemoryStore: ensureFreeSpace(2256) called with curMem=129614, maxMem=1030823608 | |
16/08/03 21:25:22 INFO o.a.s.s.MemoryStore: Block broadcast_2 stored as values in memory (estimated size 2.2 KB, free 982.9 MB) | |
16/08/03 21:25:22 INFO o.a.s.s.MemoryStore: ensureFreeSpace(1328) called with curMem=131870, maxMem=1030823608 | |
16/08/03 21:25:22 INFO o.a.s.s.MemoryStore: Block broadcast_2_piece0 stored as bytes in memory (estimated size 1328.0 B, free 982.9 MB) | |
16/08/03 21:25:22 INFO o.a.s.s.BlockManagerInfo: Added broadcast_2_piece0 in memory on localhost:50602 (size: 1328.0 B, free: 983.1 MB) | |
16/08/03 21:25:22 INFO o.a.s.SparkContext: Created broadcast 2 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 1 (ShuffledRDD[6] at countByValue at Analysis.java:95) | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 1.0 with 2 tasks | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 1.0 (TID 2, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 1.0 (TID 3, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:22 INFO o.a.s.e.Executor: Running task 0.0 in stage 1.0 (TID 2) | |
16/08/03 21:25:22 INFO o.a.s.e.Executor: Running task 1.0 in stage 1.0 (TID 3) | |
16/08/03 21:25:22 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:22 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 7 ms | |
16/08/03 21:25:22 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:22 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 10 ms | |
16/08/03 21:25:22 INFO o.a.s.e.Executor: Finished task 1.0 in stage 1.0 (TID 3). 1402 bytes result sent to driver | |
16/08/03 21:25:22 INFO o.a.s.e.Executor: Finished task 0.0 in stage 1.0 (TID 2). 1485 bytes result sent to driver | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 1.0 (TID 3) in 104 ms on localhost (1/2) | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 1.0 (TID 2) in 108 ms on localhost (2/2) | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: ResultStage 1 (countByValue at Analysis.java:95) finished in 0,109 s | |
16/08/03 21:25:22 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 1.0, whose tasks have all completed, from pool | |
16/08/03 21:25:22 INFO o.a.s.s.DAGScheduler: Job 0 finished: countByValue at Analysis.java:95, took 0,929643 s | |
Q : 77 | |
C : 168 | |
S : 644 | |
: 2 | |
16/08/03 21:25:22 INFO o.a.s.SparkContext: Starting job: reduce at Analysis.java:99 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Got job 1 (reduce at Analysis.java:99) with 2 output partitions | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 2(reduce at Analysis.java:99) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 2 (MapPartitionsRDD[9] at map at Analysis.java:99), which has no missing parents | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5728) called with curMem=133198, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_3 stored as values in memory (estimated size 5.6 KB, free 982.9 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3100) called with curMem=138926, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_3_piece0 stored as bytes in memory (estimated size 3.0 KB, free 982.9 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added broadcast_3_piece0 in memory on localhost:50602 (size: 3.0 KB, free: 983.1 MB) | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Created broadcast 3 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 2 (MapPartitionsRDD[9] at map at Analysis.java:99) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 2.0 with 2 tasks | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 2.0 (TID 4, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 2.0 (TID 5, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 0.0 in stage 2.0 (TID 4) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 1.0 in stage 2.0 (TID 5) | |
16/08/03 21:25:23 INFO o.a.s.r.HadoopRDD: Input split: file:/Users/danlin/git/dl4j-lab/src/main/resources/train_mod.csv:0+30111 | |
16/08/03 21:25:23 INFO o.a.s.r.HadoopRDD: Input split: file:/Users/danlin/git/dl4j-lab/src/main/resources/train_mod.csv:30111+30111 | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 1.0 in stage 2.0 (TID 5). 2163 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 0.0 in stage 2.0 (TID 4). 2163 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 2.0 (TID 5) in 27 ms on localhost (1/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 2.0 (TID 4) in 29 ms on localhost (2/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 2.0, whose tasks have all completed, from pool | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: ResultStage 2 (reduce at Analysis.java:99) finished in 0,030 s | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Job 1 finished: reduce at Analysis.java:99, took 0,043801 s | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Starting job: count at Analysis.java:100 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Got job 2 (count at Analysis.java:100) with 2 output partitions | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 3(count at Analysis.java:100) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 3 (MapPartitionsRDD[11] at filter at Analysis.java:100), which has no missing parents | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5112) called with curMem=142026, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_4 stored as values in memory (estimated size 5.0 KB, free 982.9 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(2954) called with curMem=147138, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_4_piece0 stored as bytes in memory (estimated size 2.9 KB, free 982.9 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added broadcast_4_piece0 in memory on localhost:50602 (size: 2.9 KB, free: 983.1 MB) | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Created broadcast 4 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 3 (MapPartitionsRDD[11] at filter at Analysis.java:100) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 3.0 with 2 tasks | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 3.0 (TID 6, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 3.0 (TID 7, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 1.0 in stage 3.0 (TID 7) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 0.0 in stage 3.0 (TID 6) | |
16/08/03 21:25:23 INFO o.a.s.r.HadoopRDD: Input split: file:/Users/danlin/git/dl4j-lab/src/main/resources/train_mod.csv:0+30111 | |
16/08/03 21:25:23 INFO o.a.s.r.HadoopRDD: Input split: file:/Users/danlin/git/dl4j-lab/src/main/resources/train_mod.csv:30111+30111 | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 1.0 in stage 3.0 (TID 7). 2082 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 0.0 in stage 3.0 (TID 6). 2082 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 3.0 (TID 7) in 23 ms on localhost (1/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 3.0 (TID 6) in 25 ms on localhost (2/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 3.0, whose tasks have all completed, from pool | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: ResultStage 3 (count at Analysis.java:100) finished in 0,025 s | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Job 2 finished: count at Analysis.java:100, took 0,036531 s | |
Sum of Age: 21205.17 | |
Count of Age: 714.0 | |
Mean of Age: 29.69911764705882 | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:624 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Got job 3 (aggregate at AnalyzeSpark.java:624) with 2 output partitions | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 4(aggregate at AnalyzeSpark.java:624) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 4 (MapPartitionsRDD[12] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5312) called with curMem=150092, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_5 stored as values in memory (estimated size 5.2 KB, free 982.9 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3022) called with curMem=155404, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_5_piece0 stored as bytes in memory (estimated size 3.0 KB, free 982.9 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added broadcast_5_piece0 in memory on localhost:50602 (size: 3.0 KB, free: 983.0 MB) | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Created broadcast 5 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 4 (MapPartitionsRDD[12] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 4.0 with 2 tasks | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 4.0 (TID 8, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 4.0 (TID 9, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 0.0 in stage 4.0 (TID 8) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 1.0 in stage 4.0 (TID 9) | |
16/08/03 21:25:23 INFO o.a.s.CacheManager: Partition rdd_2_1 not found, computing it | |
16/08/03 21:25:23 INFO o.a.s.r.HadoopRDD: Input split: file:/Users/danlin/git/dl4j-lab/src/main/resources/train_mod.csv:30111+30111 | |
16/08/03 21:25:23 INFO o.a.s.CacheManager: Partition rdd_2_0 not found, computing it | |
16/08/03 21:25:23 INFO o.a.s.r.HadoopRDD: Input split: file:/Users/danlin/git/dl4j-lab/src/main/resources/train_mod.csv:0+30111 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(282600) called with curMem=158426, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block rdd_2_0 stored as values in memory (estimated size 276.0 KB, free 982.6 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added rdd_2_0 in memory on localhost:50602 (size: 276.0 KB, free: 982.8 MB) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 0.0 in stage 4.0 (TID 8). 2763 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 4.0 (TID 8) in 419 ms on localhost (1/2) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(281552) called with curMem=441026, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block rdd_2_1 stored as values in memory (estimated size 275.0 KB, free 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added rdd_2_1 in memory on localhost:50602 (size: 275.0 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 1.0 in stage 4.0 (TID 9). 2763 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 4.0 (TID 9) in 435 ms on localhost (2/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 4.0, whose tasks have all completed, from pool | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: ResultStage 4 (aggregate at AnalyzeSpark.java:624) finished in 0,437 s | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Job 3 finished: aggregate at AnalyzeSpark.java:624, took 0,455022 s | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:633 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Got job 4 (aggregate at AnalyzeSpark.java:633) with 2 output partitions | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 5(aggregate at AnalyzeSpark.java:633) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 5 (MapPartitionsRDD[13] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5488) called with curMem=722578, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_6 stored as values in memory (estimated size 5.4 KB, free 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3132) called with curMem=728066, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_6_piece0 stored as bytes in memory (estimated size 3.1 KB, free 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added broadcast_6_piece0 in memory on localhost:50602 (size: 3.1 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Created broadcast 6 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 5 (MapPartitionsRDD[13] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 5.0 with 2 tasks | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 5.0 (TID 10, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 5.0 (TID 11, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 0.0 in stage 5.0 (TID 10) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 1.0 in stage 5.0 (TID 11) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 0.0 in stage 5.0 (TID 10). 2239 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 5.0 (TID 10) in 14 ms on localhost (1/2) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 1.0 in stage 5.0 (TID 11). 2239 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 5.0 (TID 11) in 16 ms on localhost (2/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 5.0, whose tasks have all completed, from pool | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: ResultStage 5 (aggregate at AnalyzeSpark.java:633) finished in 0,020 s | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Job 4 finished: aggregate at AnalyzeSpark.java:633, took 0,039036 s | |
16/08/03 21:25:23 INFO o.a.s.ContextCleaner: Cleaned accumulator 4 | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:633 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Got job 5 (aggregate at AnalyzeSpark.java:633) with 2 output partitions | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 6(aggregate at AnalyzeSpark.java:633) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 6 (MapPartitionsRDD[14] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5496) called with curMem=731198, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_7 stored as values in memory (estimated size 5.4 KB, free 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3143) called with curMem=736694, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_7_piece0 stored as bytes in memory (estimated size 3.1 KB, free 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added broadcast_7_piece0 in memory on localhost:50602 (size: 3.1 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Created broadcast 7 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 6 (MapPartitionsRDD[14] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 6.0 with 2 tasks | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 6.0 (TID 12, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 6.0 (TID 13, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 0.0 in stage 6.0 (TID 12) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 1.0 in stage 6.0 (TID 13) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_6_piece0 on localhost:50602 in memory (size: 3.1 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 0.0 in stage 6.0 (TID 12). 2239 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 6.0 (TID 12) in 12 ms on localhost (1/2) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 1.0 in stage 6.0 (TID 13). 2239 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.ContextCleaner: Cleaned accumulator 6 | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 6.0 (TID 13) in 14 ms on localhost (2/2) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: ResultStage 6 (aggregate at AnalyzeSpark.java:633) finished in 0,015 s | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 6.0, whose tasks have all completed, from pool | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_5_piece0 on localhost:50602 in memory (size: 3.0 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Job 5 finished: aggregate at AnalyzeSpark.java:633, took 0,031377 s | |
16/08/03 21:25:23 INFO o.a.s.ContextCleaner: Cleaned accumulator 5 | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_4_piece0 on localhost:50602 in memory (size: 2.9 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_3_piece0 on localhost:50602 in memory (size: 3.0 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.ContextCleaner: Cleaned accumulator 3 | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_2_piece0 on localhost:50602 in memory (size: 1328.0 B, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.ContextCleaner: Cleaned accumulator 2 | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Starting job: count at AnalyzeSpark.java:617 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Registering RDD 16 (distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Got job 6 (count at AnalyzeSpark.java:617) with 2 output partitions | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 8(count at AnalyzeSpark.java:617) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Parents of final stage: List(ShuffleMapStage 7) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Missing parents: List(ShuffleMapStage 7) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting ShuffleMapStage 7 (MapPartitionsRDD[16] at distinct at AnalyzeSpark.java:617), which has no missing parents | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5168) called with curMem=702405, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_8 stored as values in memory (estimated size 5.0 KB, free 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3004) called with curMem=707573, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_8_piece0 stored as bytes in memory (estimated size 2.9 KB, free 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added broadcast_8_piece0 in memory on localhost:50602 (size: 2.9 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Created broadcast 8 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ShuffleMapStage 7 (MapPartitionsRDD[16] at distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 7.0 with 2 tasks | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 7.0 (TID 14, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 7.0 (TID 15, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 0.0 in stage 7.0 (TID 14) | |
16/08/03 21:25:23 INFO o.a.s.CacheManager: Partition rdd_15_0 not found, computing it | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 1.0 in stage 7.0 (TID 15) | |
16/08/03 21:25:23 INFO o.a.s.CacheManager: Partition rdd_15_1 not found, computing it | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(32080) called with curMem=710577, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block rdd_15_0 stored as values in memory (estimated size 31.3 KB, free 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added rdd_15_0 in memory on localhost:50602 (size: 31.3 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(31448) called with curMem=742657, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block rdd_15_1 stored as values in memory (estimated size 30.7 KB, free 982.3 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added rdd_15_1 in memory on localhost:50602 (size: 30.7 KB, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 0.0 in stage 7.0 (TID 14). 2753 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 1.0 in stage 7.0 (TID 15). 2753 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 7.0 (TID 14) in 98 ms on localhost (1/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 7.0 (TID 15) in 98 ms on localhost (2/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 7.0, whose tasks have all completed, from pool | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: ShuffleMapStage 7 (distinct at AnalyzeSpark.java:617) finished in 0,099 s | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: looking for newly runnable stages | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: running: Set() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: waiting: Set(ResultStage 8) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: failed: Set() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Missing parents for ResultStage 8: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 8 (MapPartitionsRDD[18] at distinct at AnalyzeSpark.java:617), which is now runnable | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(2880) called with curMem=774105, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_9 stored as values in memory (estimated size 2.8 KB, free 982.3 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(1690) called with curMem=776985, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_9_piece0 stored as bytes in memory (estimated size 1690.0 B, free 982.3 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added broadcast_9_piece0 in memory on localhost:50602 (size: 1690.0 B, free: 982.5 MB) | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Created broadcast 9 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 8 (MapPartitionsRDD[18] at distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 8.0 with 2 tasks | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 8.0 (TID 16, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 8.0 (TID 17, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 0.0 in stage 8.0 (TID 16) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 1.0 in stage 8.0 (TID 17) | |
16/08/03 21:25:23 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:23 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 1 ms | |
16/08/03 21:25:23 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:23 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 0 ms | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 1.0 in stage 8.0 (TID 17). 1203 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 8.0 (TID 17) in 42 ms on localhost (1/2) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 0.0 in stage 8.0 (TID 16). 1203 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 8.0 (TID 16) in 44 ms on localhost (2/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 8.0, whose tasks have all completed, from pool | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: ResultStage 8 (count at AnalyzeSpark.java:617) finished in 0,045 s | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Job 6 finished: count at AnalyzeSpark.java:617, took 0,163739 s | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:620 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Got job 7 (aggregate at AnalyzeSpark.java:620) with 2 output partitions | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 9(aggregate at AnalyzeSpark.java:620) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 9 (MapPartitionsRDD[15] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5432) called with curMem=778675, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_10 stored as values in memory (estimated size 5.3 KB, free 982.3 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3109) called with curMem=784107, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_10_piece0 stored as bytes in memory (estimated size 3.0 KB, free 982.3 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added broadcast_10_piece0 in memory on localhost:50602 (size: 3.0 KB, free: 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Created broadcast 10 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 9 (MapPartitionsRDD[15] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 9.0 with 2 tasks | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 9.0 (TID 18, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 9.0 (TID 19, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 1.0 in stage 9.0 (TID 19) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_15_1 locally | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 1.0 in stage 9.0 (TID 19). 2392 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 9.0 (TID 19) in 16 ms on localhost (1/2) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 0.0 in stage 9.0 (TID 18) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_15_0 locally | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 0.0 in stage 9.0 (TID 18). 2392 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 9.0 (TID 18) in 31 ms on localhost (2/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 9.0, whose tasks have all completed, from pool | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: ResultStage 9 (aggregate at AnalyzeSpark.java:620) finished in 0,033 s | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Job 7 finished: aggregate at AnalyzeSpark.java:620, took 0,042328 s | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:633 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Got job 8 (aggregate at AnalyzeSpark.java:633) with 2 output partitions | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 10(aggregate at AnalyzeSpark.java:633) | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 10 (MapPartitionsRDD[19] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5496) called with curMem=787216, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_11 stored as values in memory (estimated size 5.4 KB, free 982.3 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3142) called with curMem=792712, maxMem=1030823608 | |
16/08/03 21:25:23 INFO o.a.s.s.MemoryStore: Block broadcast_11_piece0 stored as bytes in memory (estimated size 3.1 KB, free 982.3 MB) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManagerInfo: Added broadcast_11_piece0 in memory on localhost:50602 (size: 3.1 KB, free: 982.4 MB) | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Created broadcast 11 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 10 (MapPartitionsRDD[19] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 10.0 with 2 tasks | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 10.0 (TID 20, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 10.0 (TID 21, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 1.0 in stage 10.0 (TID 21) | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Running task 0.0 in stage 10.0 (TID 20) | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:23 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 1.0 in stage 10.0 (TID 21). 2239 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.e.Executor: Finished task 0.0 in stage 10.0 (TID 20). 2239 bytes result sent to driver | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 10.0 (TID 21) in 5 ms on localhost (1/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 10.0 (TID 20) in 8 ms on localhost (2/2) | |
16/08/03 21:25:23 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 10.0, whose tasks have all completed, from pool | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: ResultStage 10 (aggregate at AnalyzeSpark.java:633) finished in 0,008 s | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Job 8 finished: aggregate at AnalyzeSpark.java:633, took 0,017659 s | |
16/08/03 21:25:23 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:630 | |
16/08/03 21:25:23 INFO o.a.s.s.DAGScheduler: Got job 9 (aggregate at AnalyzeSpark.java:630) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 11(aggregate at AnalyzeSpark.java:630) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 11 (MapPartitionsRDD[20] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5336) called with curMem=795854, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_12 stored as values in memory (estimated size 5.2 KB, free 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3048) called with curMem=801190, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_12_piece0 stored as bytes in memory (estimated size 3.0 KB, free 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_12_piece0 in memory on localhost:50602 (size: 3.0 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 12 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 11 (MapPartitionsRDD[20] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 11.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 11.0 (TID 22, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 11.0 (TID 23, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 11.0 (TID 23) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 11.0 (TID 22) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 11.0 (TID 23). 2303 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 11.0 (TID 23) in 10 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 11.0 (TID 22). 2303 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 11.0 (TID 22) in 14 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 11.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 11 (aggregate at AnalyzeSpark.java:630) finished in 0,014 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 9 finished: aggregate at AnalyzeSpark.java:630, took 0,024081 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:624 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 10 (aggregate at AnalyzeSpark.java:624) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 12(aggregate at AnalyzeSpark.java:624) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 12 (MapPartitionsRDD[21] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5312) called with curMem=804238, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_13 stored as values in memory (estimated size 5.2 KB, free 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3026) called with curMem=809550, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_13_piece0 stored as bytes in memory (estimated size 3.0 KB, free 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_13_piece0 in memory on localhost:50602 (size: 3.0 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 13 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 12 (MapPartitionsRDD[21] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 12.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 12.0 (TID 24, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 12.0 (TID 25, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 12.0 (TID 24) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 12.0 (TID 25) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 12.0 (TID 25). 2264 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 12.0 (TID 24). 2264 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 12.0 (TID 25) in 7 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 12.0 (TID 24) in 7 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 12.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 12 (aggregate at AnalyzeSpark.java:624) finished in 0,009 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 10 finished: aggregate at AnalyzeSpark.java:624, took 0,017409 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:624 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 11 (aggregate at AnalyzeSpark.java:624) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 13(aggregate at AnalyzeSpark.java:624) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 13 (MapPartitionsRDD[22] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5312) called with curMem=812576, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_14 stored as values in memory (estimated size 5.2 KB, free 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3026) called with curMem=817888, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_14_piece0 stored as bytes in memory (estimated size 3.0 KB, free 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_14_piece0 in memory on localhost:50602 (size: 3.0 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 14 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 13 (MapPartitionsRDD[22] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 13.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 13.0 (TID 26, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 13.0 (TID 27, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 13.0 (TID 27) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 13.0 (TID 26) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 13.0 (TID 26). 2264 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 13.0 (TID 27). 2264 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 13.0 (TID 26) in 7 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 13.0 (TID 27) in 8 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 13.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 13 (aggregate at AnalyzeSpark.java:624) finished in 0,009 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 11 finished: aggregate at AnalyzeSpark.java:624, took 0,017168 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: count at AnalyzeSpark.java:617 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Registering RDD 24 (distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 12 (count at AnalyzeSpark.java:617) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 15(count at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List(ShuffleMapStage 14) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List(ShuffleMapStage 14) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ShuffleMapStage 14 (MapPartitionsRDD[24] at distinct at AnalyzeSpark.java:617), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5168) called with curMem=820914, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_15 stored as values in memory (estimated size 5.0 KB, free 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3004) called with curMem=826082, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_15_piece0 stored as bytes in memory (estimated size 2.9 KB, free 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_15_piece0 in memory on localhost:50602 (size: 2.9 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 15 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ShuffleMapStage 14 (MapPartitionsRDD[24] at distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 14.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 14.0 (TID 28, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 14.0 (TID 29, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 14.0 (TID 29) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 14.0 (TID 28) | |
16/08/03 21:25:24 INFO o.a.s.CacheManager: Partition rdd_23_0 not found, computing it | |
16/08/03 21:25:24 INFO o.a.s.CacheManager: Partition rdd_23_1 not found, computing it | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(21448) called with curMem=829086, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block rdd_23_1 stored as values in memory (estimated size 20.9 KB, free 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added rdd_23_1 in memory on localhost:50602 (size: 20.9 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(21680) called with curMem=850534, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block rdd_23_0 stored as values in memory (estimated size 21.2 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added rdd_23_0 in memory on localhost:50602 (size: 21.2 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 14.0 (TID 29). 2753 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 14.0 (TID 28). 2753 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 14.0 (TID 29) in 27 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 14.0 (TID 28) in 28 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 14.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ShuffleMapStage 14 (distinct at AnalyzeSpark.java:617) finished in 0,030 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: looking for newly runnable stages | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: running: Set() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: waiting: Set(ResultStage 15) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: failed: Set() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents for ResultStage 15: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 15 (MapPartitionsRDD[26] at distinct at AnalyzeSpark.java:617), which is now runnable | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(2880) called with curMem=872214, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_16 stored as values in memory (estimated size 2.8 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(1688) called with curMem=875094, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_16_piece0 stored as bytes in memory (estimated size 1688.0 B, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_16_piece0 in memory on localhost:50602 (size: 1688.0 B, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 16 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 15 (MapPartitionsRDD[26] at distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 15.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 15.0 (TID 30, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 15.0 (TID 31, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 15.0 (TID 30) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 15.0 (TID 31) | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 1 ms | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 0 ms | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 15.0 (TID 30). 1203 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 15.0 (TID 30) in 22 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 15.0 (TID 31). 1203 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 15.0 (TID 31) in 23 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 15.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 15 (count at AnalyzeSpark.java:617) finished in 0,024 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 12 finished: count at AnalyzeSpark.java:617, took 0,071391 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:620 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 13 (aggregate at AnalyzeSpark.java:620) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 16(aggregate at AnalyzeSpark.java:620) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 16 (MapPartitionsRDD[23] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5432) called with curMem=876782, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_17 stored as values in memory (estimated size 5.3 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3109) called with curMem=882214, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_17_piece0 stored as bytes in memory (estimated size 3.0 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_17_piece0 in memory on localhost:50602 (size: 3.0 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 17 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 16 (MapPartitionsRDD[23] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 16.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 16.0 (TID 32, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 16.0 (TID 33, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 16.0 (TID 33) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 16.0 (TID 32) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_23_1 locally | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_23_0 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 16.0 (TID 33). 2392 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 16.0 (TID 32). 2392 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 16.0 (TID 33) in 7 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 16.0 (TID 32) in 9 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 16.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 16 (aggregate at AnalyzeSpark.java:620) finished in 0,009 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 13 finished: aggregate at AnalyzeSpark.java:620, took 0,018106 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: count at AnalyzeSpark.java:617 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Registering RDD 28 (distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 14 (count at AnalyzeSpark.java:617) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 18(count at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List(ShuffleMapStage 17) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List(ShuffleMapStage 17) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ShuffleMapStage 17 (MapPartitionsRDD[28] at distinct at AnalyzeSpark.java:617), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5168) called with curMem=885323, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_18 stored as values in memory (estimated size 5.0 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3005) called with curMem=890491, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_18_piece0 stored as bytes in memory (estimated size 2.9 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_18_piece0 in memory on localhost:50602 (size: 2.9 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 18 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ShuffleMapStage 17 (MapPartitionsRDD[28] at distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 17.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 17.0 (TID 34, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 17.0 (TID 35, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 17.0 (TID 34) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 17.0 (TID 35) | |
16/08/03 21:25:24 INFO o.a.s.CacheManager: Partition rdd_27_0 not found, computing it | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:24 INFO o.a.s.CacheManager: Partition rdd_27_1 not found, computing it | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(21008) called with curMem=893496, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block rdd_27_1 stored as values in memory (estimated size 20.5 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added rdd_27_1 in memory on localhost:50602 (size: 20.5 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(20992) called with curMem=914504, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block rdd_27_0 stored as values in memory (estimated size 20.5 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added rdd_27_0 in memory on localhost:50602 (size: 20.5 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 17.0 (TID 35). 2753 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 17.0 (TID 35) in 63 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 17.0 (TID 34). 2753 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 17.0 (TID 34) in 80 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 17.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ShuffleMapStage 17 (distinct at AnalyzeSpark.java:617) finished in 0,082 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: looking for newly runnable stages | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: running: Set() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: waiting: Set(ResultStage 18) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: failed: Set() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents for ResultStage 18: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 18 (MapPartitionsRDD[30] at distinct at AnalyzeSpark.java:617), which is now runnable | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(2880) called with curMem=935496, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_19 stored as values in memory (estimated size 2.8 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(1692) called with curMem=938376, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_19_piece0 stored as bytes in memory (estimated size 1692.0 B, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_19_piece0 in memory on localhost:50602 (size: 1692.0 B, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 19 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 18 (MapPartitionsRDD[30] at distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 18.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 18.0 (TID 36, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 18.0 (TID 37, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 18.0 (TID 37) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 18.0 (TID 36) | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 0 ms | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 0 ms | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 18.0 (TID 37). 1203 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 18.0 (TID 37) in 25 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 18.0 (TID 36). 1203 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 18.0 (TID 36) in 28 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 18.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 18 (count at AnalyzeSpark.java:617) finished in 0,029 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 14 finished: count at AnalyzeSpark.java:617, took 0,164778 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:620 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 15 (aggregate at AnalyzeSpark.java:620) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 19(aggregate at AnalyzeSpark.java:620) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 19 (MapPartitionsRDD[27] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5432) called with curMem=940068, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_20 stored as values in memory (estimated size 5.3 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3109) called with curMem=945500, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_20_piece0 stored as bytes in memory (estimated size 3.0 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_20_piece0 in memory on localhost:50602 (size: 3.0 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 20 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 19 (MapPartitionsRDD[27] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 19.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 19.0 (TID 38, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 19.0 (TID 39, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 19.0 (TID 39) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 19.0 (TID 38) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_27_1 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 19.0 (TID 39). 2392 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 19.0 (TID 39) in 9 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_27_0 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 19.0 (TID 38). 2392 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 19.0 (TID 38) in 15 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 19 (aggregate at AnalyzeSpark.java:620) finished in 0,016 s | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 19.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 15 finished: aggregate at AnalyzeSpark.java:620, took 0,026930 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: count at AnalyzeSpark.java:617 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Registering RDD 32 (distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 16 (count at AnalyzeSpark.java:617) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 21(count at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List(ShuffleMapStage 20) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List(ShuffleMapStage 20) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ShuffleMapStage 20 (MapPartitionsRDD[32] at distinct at AnalyzeSpark.java:617), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5168) called with curMem=948609, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_21 stored as values in memory (estimated size 5.0 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3004) called with curMem=953777, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_21_piece0 stored as bytes in memory (estimated size 2.9 KB, free 982.2 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_21_piece0 in memory on localhost:50602 (size: 2.9 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 21 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ShuffleMapStage 20 (MapPartitionsRDD[32] at distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 20.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 20.0 (TID 40, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 20.0 (TID 41, localhost, PROCESS_LOCAL, 2081 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 20.0 (TID 40) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 20.0 (TID 41) | |
16/08/03 21:25:24 INFO o.a.s.CacheManager: Partition rdd_31_0 not found, computing it | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:24 INFO o.a.s.CacheManager: Partition rdd_31_1 not found, computing it | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(18592) called with curMem=956781, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block rdd_31_0 stored as values in memory (estimated size 18.2 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(18480) called with curMem=975373, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block rdd_31_1 stored as values in memory (estimated size 18.0 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added rdd_31_0 in memory on localhost:50602 (size: 18.2 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added rdd_31_1 in memory on localhost:50602 (size: 18.0 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 20.0 (TID 40). 2753 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 20.0 (TID 40) in 29 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 20.0 (TID 41). 2753 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 20.0 (TID 41) in 32 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 20.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ShuffleMapStage 20 (distinct at AnalyzeSpark.java:617) finished in 0,032 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: looking for newly runnable stages | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: running: Set() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: waiting: Set(ResultStage 21) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: failed: Set() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents for ResultStage 21: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 21 (MapPartitionsRDD[34] at distinct at AnalyzeSpark.java:617), which is now runnable | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(2880) called with curMem=993853, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_22 stored as values in memory (estimated size 2.8 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(1691) called with curMem=996733, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_22_piece0 stored as bytes in memory (estimated size 1691.0 B, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_22_piece0 in memory on localhost:50602 (size: 1691.0 B, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 22 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 21 (MapPartitionsRDD[34] at distinct at AnalyzeSpark.java:617) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 21.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 21.0 (TID 42, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 21.0 (TID 43, localhost, PROCESS_LOCAL, 1820 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 21.0 (TID 43) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 21.0 (TID 42) | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 0 ms | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Getting 2 non-empty blocks out of 2 blocks | |
16/08/03 21:25:24 INFO o.a.s.s.ShuffleBlockFetcherIterator: Started 0 remote fetches in 0 ms | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 21.0 (TID 42). 1203 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 21.0 (TID 42) in 19 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 21.0 (TID 43). 1203 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 21.0 (TID 43) in 22 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 21.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 21 (count at AnalyzeSpark.java:617) finished in 0,024 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 16 finished: count at AnalyzeSpark.java:617, took 0,087752 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:620 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 17 (aggregate at AnalyzeSpark.java:620) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 22(aggregate at AnalyzeSpark.java:620) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 22 (MapPartitionsRDD[31] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5432) called with curMem=998424, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_23 stored as values in memory (estimated size 5.3 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3109) called with curMem=1003856, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_23_piece0 stored as bytes in memory (estimated size 3.0 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_23_piece0 in memory on localhost:50602 (size: 3.0 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 23 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 22 (MapPartitionsRDD[31] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 22.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 22.0 (TID 44, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 22.0 (TID 45, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 22.0 (TID 45) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 22.0 (TID 44) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_31_1 locally | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_31_0 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 22.0 (TID 44). 2392 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 22.0 (TID 45). 2392 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 22.0 (TID 44) in 8 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 22.0 (TID 45) in 8 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 22.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 22 (aggregate at AnalyzeSpark.java:620) finished in 0,009 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 17 finished: aggregate at AnalyzeSpark.java:620, took 0,022002 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:633 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 18 (aggregate at AnalyzeSpark.java:633) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 23(aggregate at AnalyzeSpark.java:633) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 23 (MapPartitionsRDD[35] at map at AnalyzeSpark.java:659), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(5496) called with curMem=1006965, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_24 stored as values in memory (estimated size 5.4 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(3146) called with curMem=1012461, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_24_piece0 stored as bytes in memory (estimated size 3.1 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_24_piece0 in memory on localhost:50602 (size: 3.1 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 24 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 23 (MapPartitionsRDD[35] at map at AnalyzeSpark.java:659) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 23.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 23.0 (TID 46, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 23.0 (TID 47, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 23.0 (TID 47) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 23.0 (TID 46) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 23.0 (TID 46). 2239 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 23.0 (TID 46) in 6 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 23.0 (TID 47). 2239 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 23.0 (TID 47) in 8 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 23.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 23 (aggregate at AnalyzeSpark.java:633) finished in 0,009 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 18 finished: aggregate at AnalyzeSpark.java:633, took 0,019992 s | |
----- Data Quality ----- | |
idx name type quality details | |
0 "PassengerId" Integer ok IntegerQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891, countNonInteger=0) | |
1 "Survived" Categorical ok CategoricalQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891) | |
2 "Pclass" Categorical ok CategoricalQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891) | |
3 "Name" String ok StringQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891, countEmptyString=0, countAlphabetic=0, countNumerical=0, countWordCharacter=0, countWhitespace=0, countUnique=891) | |
4 "Sex" Categorical ok CategoricalQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891) | |
5 "Age" Double FAIL DoubleQuality(countValid=714, countInvalid=0, countMissing=177, countTotal=891, countNonReal=177, countNaN=0, countInfinite=0) | |
6 "SibSp" Integer ok IntegerQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891, countNonInteger=0) | |
7 "Parch" Integer ok IntegerQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891, countNonInteger=0) | |
8 "Ticket" String ok StringQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891, countEmptyString=0, countAlphabetic=0, countNumerical=661, countWordCharacter=665, countWhitespace=0, countUnique=681) | |
9 "Fare" String ok StringQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891, countEmptyString=0, countAlphabetic=0, countNumerical=161, countWordCharacter=161, countWhitespace=0, countUnique=248) | |
10 "Cabin" String ok StringQuality(countValid=891, countInvalid=0, countMissing=0, countTotal=891, countEmptyString=687, countAlphabetic=4, countNumerical=0, countWordCharacter=180, countWhitespace=0, countUnique=148) | |
11 "Embarked" Categorical FAIL CategoricalQuality(countValid=889, countInvalid=0, countMissing=2, countTotal=891) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: count at Analysis.java:134 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 19 (count at Analysis.java:134) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 24(count at Analysis.java:134) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 24 (MapPartitionsRDD[37] at map at SparkTransformExecutor.java:110), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(7088) called with curMem=1015607, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_25 stored as values in memory (estimated size 6.9 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(4029) called with curMem=1022695, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_25_piece0 stored as bytes in memory (estimated size 3.9 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_25_piece0 in memory on localhost:50602 (size: 3.9 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 25 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_15_piece0 on localhost:50602 in memory (size: 2.9 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 24 (MapPartitionsRDD[37] at map at SparkTransformExecutor.java:110) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 24.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 14 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_13_piece0 on localhost:50602 in memory (size: 3.0 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 24.0 (TID 48, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 24.0 (TID 49, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 13 | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 24.0 (TID 48) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 24.0 (TID 49) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_12_piece0 on localhost:50602 in memory (size: 3.0 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 12 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_11_piece0 on localhost:50602 in memory (size: 3.1 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 11 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_10_piece0 on localhost:50602 in memory (size: 3.0 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.CacheManager: Partition rdd_37_0 not found, computing it | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 10 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_0 locally | |
16/08/03 21:25:24 INFO o.a.s.CacheManager: Partition rdd_37_1 not found, computing it | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_2_1 locally | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_9_piece0 on localhost:50602 in memory (size: 1690.0 B, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 9 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_8_piece0 on localhost:50602 in memory (size: 2.9 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 8 | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned shuffle 1 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Removing RDD 15 | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned RDD 15 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_7_piece0 on localhost:50602 in memory (size: 3.1 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 7 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_24_piece0 on localhost:50602 in memory (size: 3.1 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 24 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_23_piece0 on localhost:50602 in memory (size: 3.0 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 23 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_22_piece0 on localhost:50602 in memory (size: 1691.0 B, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 22 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_21_piece0 on localhost:50602 in memory (size: 2.9 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 21 | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned shuffle 4 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Removing RDD 31 | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned RDD 31 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_20_piece0 on localhost:50602 in memory (size: 3.0 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 20 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_19_piece0 on localhost:50602 in memory (size: 1692.0 B, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 19 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_18_piece0 on localhost:50602 in memory (size: 2.9 KB, free: 982.4 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 18 | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned shuffle 3 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Removing RDD 27 | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned RDD 27 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_17_piece0 on localhost:50602 in memory (size: 3.0 KB, free: 982.5 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 17 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_16_piece0 on localhost:50602 in memory (size: 1688.0 B, free: 982.5 MB) | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 16 | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned accumulator 15 | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned shuffle 2 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Removing RDD 23 | |
16/08/03 21:25:24 INFO o.a.s.ContextCleaner: Cleaned RDD 23 | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Removed broadcast_14_piece0 on localhost:50602 in memory (size: 3.0 KB, free: 982.5 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(273528) called with curMem=704883, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block rdd_37_0 stored as values in memory (estimated size 267.1 KB, free 982.1 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added rdd_37_0 in memory on localhost:50602 (size: 267.1 KB, free: 982.3 MB) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 24.0 (TID 48). 2581 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 24.0 (TID 48) in 90 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(271944) called with curMem=978411, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block rdd_37_1 stored as values in memory (estimated size 265.6 KB, free 981.9 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added rdd_37_1 in memory on localhost:50602 (size: 265.6 KB, free: 982.0 MB) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 24.0 (TID 49). 2581 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 24.0 (TID 49) in 98 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 24 (count at Analysis.java:134) finished in 0,099 s | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 24.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 19 finished: count at Analysis.java:134, took 0,121251 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: take at Analysis.java:135 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 20 (take at Analysis.java:135) with 1 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 25(take at Analysis.java:135) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 25 (MapPartitionsRDD[37] at map at SparkTransformExecutor.java:110), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(7256) called with curMem=1250355, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_26 stored as values in memory (estimated size 7.1 KB, free 981.9 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(4107) called with curMem=1257611, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_26_piece0 stored as bytes in memory (estimated size 4.0 KB, free 981.9 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_26_piece0 in memory on localhost:50602 (size: 4.0 KB, free: 982.0 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 26 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 1 missing tasks from ResultStage 25 (MapPartitionsRDD[37] at map at SparkTransformExecutor.java:110) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 25.0 with 1 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 25.0 (TID 50, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 25.0 (TID 50) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_37_0 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 25.0 (TID 50). 5432 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 25.0 (TID 50) in 7 ms on localhost (1/1) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 25.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 25 (take at Analysis.java:135) finished in 0,007 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 20 finished: take at Analysis.java:135, took 0,016261 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:361 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 21 (aggregate at AnalyzeSpark.java:361) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 26(aggregate at AnalyzeSpark.java:361) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 26 (MapPartitionsRDD[37] at map at SparkTransformExecutor.java:110), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(8024) called with curMem=1261718, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_27 stored as values in memory (estimated size 7.8 KB, free 981.9 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(4488) called with curMem=1269742, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_27_piece0 stored as bytes in memory (estimated size 4.4 KB, free 981.9 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_27_piece0 in memory on localhost:50602 (size: 4.4 KB, free: 982.0 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 27 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 26 (MapPartitionsRDD[37] at map at SparkTransformExecutor.java:110) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 26.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 26.0 (TID 51, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 26.0 (TID 52, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 26.0 (TID 51) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 26.0 (TID 52) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_37_0 locally | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_37_1 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 26.0 (TID 51). 3723 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 26.0 (TID 52). 3723 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 26.0 (TID 51) in 29 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 26.0 (TID 52) in 28 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 26.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 26 (aggregate at AnalyzeSpark.java:361) finished in 0,030 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 21 finished: aggregate at AnalyzeSpark.java:361, took 0,039593 s | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Starting job: aggregate at AnalyzeSpark.java:495 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Got job 22 (aggregate at AnalyzeSpark.java:495) with 2 output partitions | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Final stage: ResultStage 27(aggregate at AnalyzeSpark.java:495) | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Parents of final stage: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Missing parents: List() | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting ResultStage 27 (MapPartitionsRDD[37] at map at SparkTransformExecutor.java:110), which has no missing parents | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(8400) called with curMem=1274230, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_28 stored as values in memory (estimated size 8.2 KB, free 981.8 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: ensureFreeSpace(4625) called with curMem=1282630, maxMem=1030823608 | |
16/08/03 21:25:24 INFO o.a.s.s.MemoryStore: Block broadcast_28_piece0 stored as bytes in memory (estimated size 4.5 KB, free 981.8 MB) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManagerInfo: Added broadcast_28_piece0 in memory on localhost:50602 (size: 4.5 KB, free: 982.0 MB) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Created broadcast 28 from broadcast at DAGScheduler.scala:861 | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Submitting 2 missing tasks from ResultStage 27 (MapPartitionsRDD[37] at map at SparkTransformExecutor.java:110) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Adding task set 27.0 with 2 tasks | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 0.0 in stage 27.0 (TID 53, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Starting task 1.0 in stage 27.0 (TID 54, localhost, PROCESS_LOCAL, 2092 bytes) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 0.0 in stage 27.0 (TID 53) | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Running task 1.0 in stage 27.0 (TID 54) | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_37_0 locally | |
16/08/03 21:25:24 INFO o.a.s.s.BlockManager: Found block rdd_37_1 locally | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 0.0 in stage 27.0 (TID 53). 7158 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.e.Executor: Finished task 1.0 in stage 27.0 (TID 54). 7158 bytes result sent to driver | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 0.0 in stage 27.0 (TID 53) in 20 ms on localhost (1/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSetManager: Finished task 1.0 in stage 27.0 (TID 54) in 21 ms on localhost (2/2) | |
16/08/03 21:25:24 INFO o.a.s.s.TaskSchedulerImpl: Removed TaskSet 27.0, whose tasks have all completed, from pool | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: ResultStage 27 (aggregate at AnalyzeSpark.java:495) finished in 0,023 s | |
16/08/03 21:25:24 INFO o.a.s.s.DAGScheduler: Job 22 failed: aggregate at AnalyzeSpark.java:495, took 0,036230 s | |
Exception in thread "main" org.apache.spark.SparkDriverExecutionException: Execution error | |
at org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:1024) | |
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493) | |
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458) | |
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447) | |
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) | |
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567) | |
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1822) | |
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1942) | |
at org.apache.spark.rdd.RDD$$anonfun$aggregate$1.apply(RDD.scala:1078) | |
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147) | |
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108) | |
at org.apache.spark.rdd.RDD.withScope(RDD.scala:306) | |
at org.apache.spark.rdd.RDD.aggregate(RDD.scala:1071) | |
at org.apache.spark.api.java.JavaRDDLike$class.aggregate(JavaRDDLike.scala:416) | |
at org.apache.spark.api.java.AbstractJavaRDDLike.aggregate(JavaRDDLike.scala:47) | |
at org.datavec.spark.transform.AnalyzeSpark.analyze(AnalyzeSpark.java:495) | |
at org.datavec.spark.transform.AnalyzeSpark.analyze(AnalyzeSpark.java:123) | |
at kaggle.Analysis.main(Analysis.java:137) | |
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) | |
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) | |
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) | |
at java.lang.reflect.Method.invoke(Method.java:483) | |
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:144) | |
Caused by: java.lang.NullPointerException | |
at org.datavec.spark.transform.analysis.histogram.HistogramCombineFunction.call(HistogramCombineFunction.java:38) | |
at org.datavec.spark.transform.analysis.histogram.HistogramCombineFunction.call(HistogramCombineFunction.java:28) | |
at org.apache.spark.api.java.JavaPairRDD$$anonfun$toScalaFunction2$1.apply(JavaPairRDD.scala:1024) | |
at org.apache.spark.rdd.RDD$$anonfun$aggregate$1$$anonfun$22.apply(RDD.scala:1077) | |
at org.apache.spark.rdd.RDD$$anonfun$aggregate$1$$anonfun$22.apply(RDD.scala:1077) | |
at org.apache.spark.scheduler.JobWaiter.taskSucceeded(JobWaiter.scala:56) | |
at org.apache.spark.scheduler.DAGScheduler.handleTaskCompletion(DAGScheduler.scala:1020) | |
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493) | |
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458) | |
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447) | |
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) | |
16/08/03 21:25:24 INFO o.a.s.SparkContext: Invoking stop() from shutdown hook | |
16/08/03 21:25:25 INFO o.a.s.u.SparkUI: Stopped Spark web UI at http://192.168.0.5:4040 | |
16/08/03 21:25:25 INFO o.a.s.s.DAGScheduler: Stopping DAGScheduler | |
16/08/03 21:25:25 INFO o.a.s.MapOutputTrackerMasterEndpoint: MapOutputTrackerMasterEndpoint stopped! | |
16/08/03 21:25:25 INFO o.a.s.s.MemoryStore: MemoryStore cleared | |
16/08/03 21:25:25 INFO o.a.s.s.BlockManager: BlockManager stopped | |
16/08/03 21:25:25 INFO o.a.s.s.BlockManagerMaster: BlockManagerMaster stopped | |
16/08/03 21:25:25 INFO o.a.s.s.OutputCommitCoordinator$OutputCommitCoordinatorEndpoint: OutputCommitCoordinator stopped! | |
16/08/03 21:25:25 INFO o.a.s.SparkContext: Successfully stopped SparkContext | |
16/08/03 21:25:25 INFO o.a.s.u.ShutdownHookManager: Shutdown hook called | |
16/08/03 21:25:25 INFO o.a.s.u.ShutdownHookManager: Deleting directory /private/var/folders/tk/2t_ll0bs5ml458g35b118h3r0000gp/T/spark-2a892f8e-3eb9-4a60-ba0c-fb661129ba9e | |
Process finished with exit code 1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?xml version="1.0" encoding="UTF-8"?> | |
<project xmlns="http://maven.apache.org/POM/4.0.0" | |
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" | |
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> | |
<modelVersion>4.0.0</modelVersion> | |
<groupId>com.danlin</groupId> | |
<artifactId>dl4j</artifactId> | |
<version>1.0-SNAPSHOT</version> | |
<properties> | |
<nd4j.backend>nd4j-native</nd4j.backend> | |
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding> | |
<shadedClassifier>bin</shadedClassifier> | |
<java.version>1.7</java.version> | |
<nd4j.version>0.5.0</nd4j.version> | |
<dl4j.version>0.5.0</dl4j.version> | |
<canova.version>0.0.0.17</canova.version> | |
<arbiter.version>0.5.0</arbiter.version> | |
<guava.version>19.0</guava.version> | |
<jfreechart.version>1.0.13</jfreechart.version> | |
<maven-shade-plugin.version>2.4.3</maven-shade-plugin.version> | |
<exec-maven-plugin.version>1.4.0</exec-maven-plugin.version> | |
<datavec.version>0.5.0</datavec.version> | |
<scala.binary.version>2.10</scala.binary.version> | |
</properties> | |
<dependencyManagement> | |
<dependencies> | |
<dependency> | |
<groupId>org.nd4j</groupId> | |
<artifactId>nd4j-native</artifactId> | |
<version>${nd4j.version}</version> | |
</dependency> | |
<dependency> | |
<groupId>org.nd4j</groupId> | |
<artifactId>nd4j-cuda-7.5</artifactId> | |
<version>${nd4j.version}</version> | |
</dependency> | |
<dependency> | |
<groupId>com.fasterxml.jackson.core</groupId> | |
<artifactId>jackson-databind</artifactId> | |
<version>2.4.4</version> | |
</dependency> | |
</dependencies> | |
</dependencyManagement> | |
<dependencies> | |
<dependency> | |
<groupId>org.deeplearning4j</groupId> | |
<artifactId>deeplearning4j-nlp</artifactId> | |
<version>${dl4j.version}</version> | |
</dependency> | |
<dependency> | |
<groupId>org.deeplearning4j</groupId> | |
<artifactId>deeplearning4j-core</artifactId> | |
<version>${dl4j.version}</version> | |
</dependency> | |
<dependency> | |
<groupId>org.deeplearning4j</groupId> | |
<artifactId>deeplearning4j-ui</artifactId> | |
<version>${dl4j.version}</version> | |
</dependency> | |
<dependency> | |
<groupId>com.google.guava</groupId> | |
<artifactId>guava</artifactId> | |
<version>${guava.version}</version> | |
</dependency> | |
<dependency> | |
<groupId>org.nd4j</groupId> | |
<artifactId>${nd4j.backend}</artifactId> | |
</dependency> | |
<dependency> | |
<artifactId>canova-nd4j-image</artifactId> | |
<groupId>org.nd4j</groupId> | |
<version>${canova.version}</version> | |
</dependency> | |
<dependency> | |
<artifactId>canova-nd4j-codec</artifactId> | |
<groupId>org.nd4j</groupId> | |
<version>${canova.version}</version> | |
</dependency> | |
<!-- Used in the RegressionMathFunctions example --> | |
<!--<dependency>--> | |
<!--<groupId>jfree</groupId>--> | |
<!--<artifactId>jfreechart</artifactId>--> | |
<!--<version>${jfreechart.version}</version>--> | |
<!--</dependency>--> | |
<!-- Arbiter: used for hyperparameter optimization examples --> | |
<dependency> | |
<groupId>org.deeplearning4j</groupId> | |
<artifactId>arbiter-deeplearning4j</artifactId> | |
<version>${arbiter.version}</version> | |
</dependency> | |
<dependency> | |
<groupId>org.datavec</groupId> | |
<artifactId>datavec-api</artifactId> | |
<version>${datavec.version}</version> | |
</dependency> | |
<dependency> | |
<groupId>org.datavec</groupId> | |
<artifactId>datavec-spark_${scala.binary.version}</artifactId> | |
<version>${datavec.version}</version> | |
<exclusions> | |
<exclusion> | |
<groupId>org.slf4j</groupId> | |
<artifactId>slf4j-log4j12</artifactId> | |
</exclusion> | |
<exclusion> | |
<groupId>log4j</groupId> | |
<artifactId>log4j</artifactId> | |
</exclusion> | |
</exclusions> | |
</dependency> | |
<dependency> | |
<groupId>org.apache.spark</groupId> | |
<artifactId>spark-mllib_2.10</artifactId> | |
<version>2.0.0</version> | |
<exclusions> | |
<exclusion> | |
<groupId>org.slf4j</groupId> | |
<artifactId>slf4j-log4j12</artifactId> | |
</exclusion> | |
<exclusion> | |
<groupId>log4j</groupId> | |
<artifactId>log4j</artifactId> | |
</exclusion> | |
</exclusions> | |
</dependency> | |
</dependencies> | |
<build> | |
<plugins> | |
<plugin> | |
<groupId>org.codehaus.mojo</groupId> | |
<artifactId>exec-maven-plugin</artifactId> | |
<version>${exec-maven-plugin.version}</version> | |
<executions> | |
<execution> | |
<goals> | |
<goal>exec</goal> | |
</goals> | |
</execution> | |
</executions> | |
<configuration> | |
<executable>java</executable> | |
</configuration> | |
</plugin> | |
<plugin> | |
<groupId>org.apache.maven.plugins</groupId> | |
<artifactId>maven-shade-plugin</artifactId> | |
<version>${maven-shade-plugin.version}</version> | |
<configuration> | |
<shadedArtifactAttached>true</shadedArtifactAttached> | |
<shadedClassifierName>${shadedClassifier}</shadedClassifierName> | |
<createDependencyReducedPom>true</createDependencyReducedPom> | |
<filters> | |
<filter> | |
<artifact>*:*</artifact> | |
<excludes> | |
<exclude>org/datanucleus/**</exclude> | |
<exclude>META-INF/*.SF</exclude> | |
<exclude>META-INF/*.DSA</exclude> | |
<exclude>META-INF/*.RSA</exclude> | |
</excludes> | |
</filter> | |
</filters> | |
</configuration> | |
<executions> | |
<execution> | |
<phase>package</phase> | |
<goals> | |
<goal>shade</goal> | |
</goals> | |
<configuration> | |
<transformers> | |
<transformer | |
implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer"> | |
<resource>reference.conf</resource> | |
</transformer> | |
<transformer | |
implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/> | |
<transformer | |
implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer"> | |
</transformer> | |
</transformers> | |
</configuration> | |
</execution> | |
</executions> | |
</plugin> | |
<plugin> | |
<groupId>org.apache.maven.plugins</groupId> | |
<artifactId>maven-compiler-plugin</artifactId> | |
<version>3.5.1</version> | |
<configuration> | |
<source>1.8</source> | |
<target>1.8</target> | |
</configuration> | |
</plugin> | |
</plugins> | |
</build> | |
</project> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment