Github user MLnick commented on a diff in the pull request: https://github.com/apache/spark/pull/12938#discussion_r65778263 --- Diff: python/pyspark/ml/classification.py --- @@ -183,7 +191,7 @@ def getThresholds(self): If :py:attr:`thresholds` is set, return its value. Otherwise, if :py:attr:`threshold` is set, return the equivalent thresholds for binary classification: (1-threshold, threshold). - If neither are set, throw an error. --- End diff -- If neither are explicitly set, it does in fact throw an error: ``` In [22]: if not lr.isSet(lr.thresholds) and lr.isSet(lr.threshold): ....: t = lr.getOrDefault(lr.threshold) ....: [1.0-t, t] ....: else: ....: lr.getOrDefault(lr.thresholds) ....: --------------------------------------------------------------------------- KeyError Traceback (most recent call last) <ipython-input-22-869f82439552> in <module>() 3 [1.0-t, t] 4 else: ----> 5 lr.getOrDefault(lr.thresholds) 6 /Users/nick/workspace/scala/mlnick-spark/python/pyspark/ml/param/__init__.pyc in getOrDefault(self, param) 348 return self._paramMap[param] 349 else: --> 350 return self._defaultParamMap[param] 351 352 @since("1.4.0") KeyError: Param(parent=u'LogisticRegression_4b97b6978cdc41d90ee3', name='thresholds', doc="Thresholds in multi-class classification to adjust the probability of predicting each class. Array must have length equal to the number of classes, with values >= 0. The class with largest value p/t is predicted, where p is the original probability of that class and t is the class' threshold.") ```
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org