[jira] [Commented] (SPARK-19282) RandomForestRegressionModel should expose getMaxDepth
[ https://issues.apache.org/jira/browse/SPARK-19282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15900938#comment-15900938 ] Apache Spark commented on SPARK-19282: -- User 'keypointt' has created a pull request for this issue: https://github.com/apache/spark/pull/17207 > RandomForestRegressionModel should expose getMaxDepth > - > > Key: SPARK-19282 > URL: https://issues.apache.org/jira/browse/SPARK-19282 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.1.0 >Reporter: Nick Lothian >Priority: Minor > > Currently it isn't clear hot to get the max depth of a > RandomForestRegressionModel (eg, after doing a grid search) > It is possible to call > {{regressor._java_obj.getMaxDepth()}} > but most other decision trees allow > {{regressor.getMaxDepth()}} -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19282) RandomForestRegressionModel should expose getMaxDepth
[ https://issues.apache.org/jira/browse/SPARK-19282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15858744#comment-15858744 ] Xin Ren commented on SPARK-19282: - I just got approved by my company to work on this one resuming my work on this task :) > RandomForestRegressionModel should expose getMaxDepth > - > > Key: SPARK-19282 > URL: https://issues.apache.org/jira/browse/SPARK-19282 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.1.0 >Reporter: Nick Lothian >Priority: Minor > > Currently it isn't clear hot to get the max depth of a > RandomForestRegressionModel (eg, after doing a grid search) > It is possible to call > {{regressor._java_obj.getMaxDepth()}} > but most other decision trees allow > {{regressor.getMaxDepth()}} -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19282) RandomForestRegressionModel should expose getMaxDepth
[ https://issues.apache.org/jira/browse/SPARK-19282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15848963#comment-15848963 ] Bryan Cutler commented on SPARK-19282: -- Is this another case of SPARK-10931? The PySpark ML models generally do not copy over parameters from the wrapped Java object, so many of the functions to get those params are missing. That issue will need to be resolved first. > RandomForestRegressionModel should expose getMaxDepth > - > > Key: SPARK-19282 > URL: https://issues.apache.org/jira/browse/SPARK-19282 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.1.0 >Reporter: Nick Lothian >Priority: Minor > > Currently it isn't clear hot to get the max depth of a > RandomForestRegressionModel (eg, after doing a grid search) > It is possible to call > {{regressor._java_obj.getMaxDepth()}} > but most other decision trees allow > {{regressor.getMaxDepth()}} -- This message was sent by Atlassian JIRA (v6.3.15#6346) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19282) RandomForestRegressionModel should expose getMaxDepth
[ https://issues.apache.org/jira/browse/SPARK-19282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15833973#comment-15833973 ] Xin Ren commented on SPARK-19282: - sorry Nick, now I cannot make it for this fix. anyone else please take a look? thanks a lot > RandomForestRegressionModel should expose getMaxDepth > - > > Key: SPARK-19282 > URL: https://issues.apache.org/jira/browse/SPARK-19282 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.1.0 >Reporter: Nick Lothian >Priority: Minor > > Currently it isn't clear hot to get the max depth of a > RandomForestRegressionModel (eg, after doing a grid search) > It is possible to call > {{regressor._java_obj.getMaxDepth()}} > but most other decision trees allow > {{regressor.getMaxDepth()}} -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19282) RandomForestRegressionModel should expose getMaxDepth
[ https://issues.apache.org/jira/browse/SPARK-19282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15832022#comment-15832022 ] Xin Ren commented on SPARK-19282: - Thank you Nick. I'll give it a try to fix it. :) > RandomForestRegressionModel should expose getMaxDepth > - > > Key: SPARK-19282 > URL: https://issues.apache.org/jira/browse/SPARK-19282 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.1.0 >Reporter: Nick Lothian >Priority: Minor > > Currently it isn't clear hot to get the max depth of a > RandomForestRegressionModel (eg, after doing a grid search) > It is possible to call > {{regressor._java_obj.getMaxDepth()}} > but most other decision trees allow > {{regressor.getMaxDepth()}} -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19282) RandomForestRegressionModel should expose getMaxDepth
[ https://issues.apache.org/jira/browse/SPARK-19282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15831444#comment-15831444 ] Nick Lothian commented on SPARK-19282: -- Yes. There are basically two parameters that are tuned in RandomForests: the number of trees and the max depth. The example in the docs shows this: {{rf = RandomForestRegressor(numTrees=2, maxDepth=2, seed=42)}} http://spark.apache.org/docs/latest/api/python/pyspark.ml.html#pyspark.ml.regression.RandomForestRegressor During parameter tuning it is common to try many, many combinations of these parameters which can take reasonable amount of time (I've had parameter turning run for over 12 hours before). It's pretty annoying if one can't easily find what the best parameters found are! > RandomForestRegressionModel should expose getMaxDepth > - > > Key: SPARK-19282 > URL: https://issues.apache.org/jira/browse/SPARK-19282 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.1.0 >Reporter: Nick Lothian >Priority: Minor > > Currently it isn't clear hot to get the max depth of a > RandomForestRegressionModel (eg, after doing a grid search) > It is possible to call > {{regressor._java_obj.getMaxDepth()}} > but most other decision trees allow > {{regressor.getMaxDepth()}} -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19282) RandomForestRegressionModel should expose getMaxDepth
[ https://issues.apache.org/jira/browse/SPARK-19282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15831342#comment-15831342 ] Xin Ren commented on SPARK-19282: - sorry being naive, I'm not familiar with random forest, but is "max depth" an important metrics/param of RF model? > RandomForestRegressionModel should expose getMaxDepth > - > > Key: SPARK-19282 > URL: https://issues.apache.org/jira/browse/SPARK-19282 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.1.0 >Reporter: Nick Lothian >Priority: Minor > > Currently it isn't clear hot to get the max depth of a > RandomForestRegressionModel (eg, after doing a grid search) > It is possible to call > {{regressor._java_obj.getMaxDepth()}} > but most other decision trees allow > {{regressor.getMaxDepth()}} -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19282) RandomForestRegressionModel should expose getMaxDepth
[ https://issues.apache.org/jira/browse/SPARK-19282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15830962#comment-15830962 ] Nick Lothian commented on SPARK-19282: -- The docs say it is available in Java and Scala. In Java: https://spark.apache.org/docs/2.1.0/api/java/org/apache/spark/ml/regression/RandomForestRegressionModel.html#getMaxDepth() In Scala: https://spark.apache.org/docs/2.1.0/api/scala/index.html#org.apache.spark.ml.regression.RandomForestRegressionModel@maxDepth:org.apache.spark.ml.param.IntParam I don't know how to find the RandomForestRegressionModel in the R docs. R does take the parameter, but it is unclear if it exposes it on the model. > RandomForestRegressionModel should expose getMaxDepth > - > > Key: SPARK-19282 > URL: https://issues.apache.org/jira/browse/SPARK-19282 > Project: Spark > Issue Type: Improvement > Components: ML >Affects Versions: 2.1.0 >Reporter: Nick Lothian >Priority: Minor > > Currently it isn't clear hot to get the max depth of a > RandomForestRegressionModel (eg, after doing a grid search) > It is possible to call > {{regressor._java_obj.getMaxDepth()}} > but most other decision trees allow > {{regressor.getMaxDepth()}} -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org
[jira] [Commented] (SPARK-19282) RandomForestRegressionModel should expose getMaxDepth
[ https://issues.apache.org/jira/browse/SPARK-19282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15829538#comment-15829538 ] Sean Owen commented on SPARK-19282: --- Is this specific to Pyspark? > RandomForestRegressionModel should expose getMaxDepth > - > > Key: SPARK-19282 > URL: https://issues.apache.org/jira/browse/SPARK-19282 > Project: Spark > Issue Type: Bug > Components: ML >Affects Versions: 2.1.0 >Reporter: Nick Lothian >Priority: Minor > > Currently it isn't clear hot to get the max depth of a > RandomForestRegressionModel (eg, after doing a grid search) > It is possible to call > {{regressor._java_obj.getMaxDepth()}} > but most other decision trees allow > {{regressor.getMaxDepth()}} -- This message was sent by Atlassian JIRA (v6.3.4#6332) - To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org