Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-14046

RandomForest improvement umbrella

    XMLWordPrintableJSON

Details

    • Umbrella
    • Status: Resolved
    • Major
    • Resolution: Incomplete
    • None
    • None
    • ML

    Description

      This is an umbrella for improvements to learning Random Forests: RandomForestClassifier, RandomForestRegressor.

      Note: Aspects of RFs which are related to individual trees should be listed under SPARK-14045.

      Attachments

        Issue Links

          contains

          Sub-task - The sub-task of the issue SPARK-9623 RandomForestRegressor: provide variance of predictions

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Bug - A problem which impairs or prevents the functions of the product. SPARK-20081 RandomForestClassifier doesn't seem to support more than 100 labels

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-16719 RandomForest: communicate fewer trees on each iteration

          • Critical - Crashes, loss of data, severe memory leak.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-9478 Add sample weights to Random Forest

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-13434 Reduce Spark RandomForest memory footprint

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-13868 Random forest accuracy exploration

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-3723 DecisionTree, RandomForest: Add more instrumentation

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-3724 RandomForest: More options for feature subset size

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-3728 RandomForest: Learn models too large to store in memory

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-23704 PySpark access of individual trees in random forest is slow

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. SPARK-23730 Save and expose "in bag" tracking for random forest model

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved
          relates to

          Bug - A problem which impairs or prevents the functions of the product. SPARK-34591 Pyspark undertakes pruning of decision trees and random forests outside the control of the user, leading to undesirable and unexpected outcomes that are challenging to diagnose and impossible to correct

          • Major - Major loss of function.
          • In Progress

          Umbrella - An overarching type made of sub-tasks SPARK-14045 DecisionTree improvement umbrella

          • Major - Major loss of function.
          • Resolved

          Activity

            People

              Unassigned Unassigned
              josephkb Joseph K. Bradley
              Votes:
              1 Vote for this issue
              Watchers:
              6 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: