jrmccluskey commented on code in PR #31026:
URL: https://github.com/apache/beam/pull/31026#discussion_r1571281534
##########
sdks/python/apache_beam/ml/transforms/tft.py:
##########
@@ -291,6 +291,41 @@ def apply_transform(
return output_dict
+@register_input_dtype(float)
+class ScaleToGaussian(TFTOperation):
+ def __init__(
+ self,
+ columns: List[str],
+ elementwise: bool = False,
+ name: Optional[str] = None):
+ """
+ This function applies a scaling transformation on the given columns
+ of incoming data. The operation transforms the input column values
+ to an approximately normal distribution with mean 0 and variance of 1.
+ The Gaussian transformation is only applied if the column has long tails;
Review Comment:
made a few changes to clarify, it's the latter
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
