Benjamin Trent eff7f06ca6

[ML] fix inference binary classification predication label and feature importance (#63688) (#63930) ...

When calculating feature importance, the leaf values directly correlate the value of the importance.

Consequently, positive leaf values -> positive feature importance

negative leaf values -> negative feature importance.

It follows that for binary classification, this is done such that the importance relates to the leaf values, which relate directly to the "probability of class 1".

So, the feature importance calculated is always for the importance as it relates to class 1.

The inverse is the importance as it relates to class 0.

2020-10-20 08:50:15 -04:00

..

forbidden

Ensure SHA256 is not used in tests (#42289)

2019-05-22 09:54:24 +03:00

licenses

Enforce strict license distribution requirements (#56642)

2020-05-14 13:57:56 -07:00

src

[ML] fix inference binary classification predication label and feature importance (#63688) (#63930)

2020-10-20 08:50:15 -04:00

build.gradle

Replace immediate task creations by using task avoidance api (#60071) (#60504)

2020-07-31 13:09:04 +02:00

snapshot.key

Make licensing FIPS-140 compliant (#30251)

2018-05-02 22:19:43 +03:00