You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Keepun (JIRA)" <ji...@apache.org> on 2018/02/23 18:48:00 UTC
[jira] [Updated] (SPARK-23471) RandomForestClassificationModel
save() - incorrect metadata
[ https://issues.apache.org/jira/browse/SPARK-23471?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Keepun updated SPARK-23471:
---------------------------
Description:
RandomForestClassificationMode.load() does not work after save()
{code:java}
RandomForestClassifier rf = new RandomForestClassifier()
.setFeaturesCol("features")
.setLabelCol("result")
.setNumTrees(100)
.setMaxDepth(30)
.setMinInstancesPerNode(1)
//.setCacheNodeIds(true)
.setMaxMemoryInMB(500)
.setSeed(System.currentTimeMillis() + System.nanoTime());
RandomForestClassificationModel rfmodel = rf.train(data);
try {
rfmodel.save(args[2] + "." + System.currentTimeMillis());
} catch (IOException e) {
LOG.error(e.getMessage(), e);
e.printStackTrace();
}
{code}
File metadata\part-00000:
{code:java}
{"class":"org.apache.spark.ml.classification.RandomForestClassificationModel",
"timestamp":1519136783983,"sparkVersion":"2.2.1","uid":"rfc_7c7e84ce7488",
"paramMap":{"featureSubsetStrategy":"auto","cacheNodeIds":false,"impurity":"gini",
"checkpointInterval":10,
"numTrees":20,"maxDepth":5,
"probabilityCol":"probability","labelCol":"label","featuresCol":"features",
"maxMemoryInMB":256,"minInstancesPerNode":1,"subsamplingRate":1.0,
"rawPredictionCol":"rawPrediction","predictionCol":"prediction","maxBins":32,
"minInfoGain":0.0,"seed":-491520797},"numFeatures":1354,"numClasses":2,
"numTrees":20}
{code}
should be:
{code:java}
"numTrees":100,"maxDepth":30,{code}
was:
RandomForestClassificationMode.load() does not work after save():
{code:java}
RandomForestClassifier rf = new RandomForestClassifier()
.setFeaturesCol("features")
.setLabelCol("result")
.setNumTrees(100)
.setMaxDepth(30)
.setMinInstancesPerNode(1)
//.setCacheNodeIds(true)
.setMaxMemoryInMB(500)
.setSeed(System.currentTimeMillis() + System.nanoTime());
RandomForestClassificationModel rfmodel = rf.train(data);
try {
rfmodel.save(args[2] + "." + System.currentTimeMillis());
} catch (IOException e) {
LOG.error(e.getMessage(), e);
e.printStackTrace();
}
{code}
File metadata\part-00000:
{code:java}
{"class":"org.apache.spark.ml.classification.RandomForestClassificationModel",
"timestamp":1519136783983,"sparkVersion":"2.2.1","uid":"rfc_7c7e84ce7488",
"paramMap":{"featureSubsetStrategy":"auto","cacheNodeIds":false,"impurity":"gini",
"checkpointInterval":10,
"numTrees":20,"maxDepth":5,
"probabilityCol":"probability","labelCol":"label","featuresCol":"features",
"maxMemoryInMB":256,"minInstancesPerNode":1,"subsamplingRate":1.0,
"rawPredictionCol":"rawPrediction","predictionCol":"prediction","maxBins":32,
"minInfoGain":0.0,"seed":-491520797},"numFeatures":1354,"numClasses":2,
"numTrees":20}
{code}
should be:
{code:java}
"numTrees":100,"maxDepth":30,{code}
> RandomForestClassificationModel save() - incorrect metadata
> -----------------------------------------------------------
>
> Key: SPARK-23471
> URL: https://issues.apache.org/jira/browse/SPARK-23471
> Project: Spark
> Issue Type: Bug
> Components: ML
> Affects Versions: 2.2.1
> Reporter: Keepun
> Priority: Major
>
> RandomForestClassificationMode.load() does not work after save()
> {code:java}
> RandomForestClassifier rf = new RandomForestClassifier()
> .setFeaturesCol("features")
> .setLabelCol("result")
> .setNumTrees(100)
> .setMaxDepth(30)
> .setMinInstancesPerNode(1)
> //.setCacheNodeIds(true)
> .setMaxMemoryInMB(500)
> .setSeed(System.currentTimeMillis() + System.nanoTime());
> RandomForestClassificationModel rfmodel = rf.train(data);
> try {
> rfmodel.save(args[2] + "." + System.currentTimeMillis());
> } catch (IOException e) {
> LOG.error(e.getMessage(), e);
> e.printStackTrace();
> }
> {code}
> File metadata\part-00000:
> {code:java}
> {"class":"org.apache.spark.ml.classification.RandomForestClassificationModel",
> "timestamp":1519136783983,"sparkVersion":"2.2.1","uid":"rfc_7c7e84ce7488",
> "paramMap":{"featureSubsetStrategy":"auto","cacheNodeIds":false,"impurity":"gini",
> "checkpointInterval":10,
> "numTrees":20,"maxDepth":5,
> "probabilityCol":"probability","labelCol":"label","featuresCol":"features",
> "maxMemoryInMB":256,"minInstancesPerNode":1,"subsamplingRate":1.0,
> "rawPredictionCol":"rawPrediction","predictionCol":"prediction","maxBins":32,
> "minInfoGain":0.0,"seed":-491520797},"numFeatures":1354,"numClasses":2,
> "numTrees":20}
> {code}
> should be:
> {code:java}
> "numTrees":100,"maxDepth":30,{code}
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org