-dev
See the migration guide:
https://spark.apache.org/docs/3.0.0/ml-migration-guide.html
Use ml.LogisticRegression, which should still let you use SGD
On Tue, Sep 22, 2020 at 12:54 AM Lyx <1181245...@qq.com> wrote:
>
> Hi,
> I have updated my Spark to the version of 3.0.0,
> and it seems
Hi,
I have updated my Spark to the version of 3.0.0,
and it seems that the LogisticRegressionWithSGD's constructor is private
within the mllib package,
So i can't initialize an instance of this class.
How can i still use this class rather than switch to the
LogisticRegressionWithLBFGS ?
