[ https://issues.apache.org/jira/browse/MAHOUT-1554?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Karol Grzegorczyk updated MAHOUT-1554: -------------------------------------- Status: Patch Available (was: Open) I'm submitting a patch (statistics.diff) which introduce weighted average of precision, recall and F1 score. I decided to compute weighted average, because it is a default choice in a popular scikit-learn library. Weights are actual number of test examples (sum of true positives and false negatives). > Provide more comprehensive classification statistics > ---------------------------------------------------- > > Key: MAHOUT-1554 > URL: https://issues.apache.org/jira/browse/MAHOUT-1554 > Project: Mahout > Issue Type: Improvement > Components: Classification > Reporter: Karol Grzegorczyk > Priority: Minor > Attachments: statistics.diff > > > Currently only limited classification statistics are provided. To better > understand classification results, it would be worth to provide at lease > average precision, recall and F1 score. -- This message was sent by Atlassian JIRA (v6.2#6252)