[GitHub] [spark] zhengruifeng commented on pull request #30013: [SPARK-32455][ML][Follow-Up] LogisticRegressionModel prediction optimization - fix incorrect initialization

2020-10-12 Thread GitBox
zhengruifeng commented on pull request #30013: URL: https://github.com/apache/spark/pull/30013#issuecomment-707491859 Merged to master, thanks all! This is an automated message from the Apache Git Service. To respond to the

[GitHub] [spark] zhengruifeng commented on pull request #30013: [SPARK-32455][ML][Follow-Up] LogisticRegressionModel prediction optimization - fix incorrect initialization

2020-10-12 Thread GitBox
zhengruifeng commented on pull request #30013: URL: https://github.com/apache/spark/pull/30013#issuecomment-707432942 @huaxingao I find that in [suite `test("thresholds

[GitHub] [spark] zhengruifeng commented on pull request #30013: [SPARK-32455][ML][Follow-Up] LogisticRegressionModel prediction optimization - fix incorrect initialization

2020-10-12 Thread GitBox
zhengruifeng commented on pull request #30013: URL: https://github.com/apache/spark/pull/30013#issuecomment-707430678 @huaxingao In #29255, if threshold is set in binary lor **Estimator**, then in the model, the values of `_threshold` and `_rawThreshold` are wrong (they are initialized by

[GitHub] [spark] zhengruifeng commented on pull request #30013: [SPARK-32455][ML][Follow-Up] LogisticRegressionModel prediction optimization - fix incorrect initialization

2020-10-12 Thread GitBox
zhengruifeng commented on pull request #30013: URL: https://github.com/apache/spark/pull/30013#issuecomment-706970421 @srowen @huaxingao This is an automated message from the Apache Git Service. To respond to the message,