Target interval

Hello everybody!

First of all: Thank you for the great tutorial.

I have a question regarding the target interval. The text says that

> Orders after the threshold date are used to compute the target value

and that makes intuitively sense. It's also how _lifetimes_ are doing it in their [example](https://lifetimes.readthedocs.io/en/latest/More%20examples%20and%20recipes.html#create-table-with-rfm-summary-matrix-with-holdout), which I think is the foundation for the SQL statements in the tutorial.

However, here the WHERE condition is commented out and the whole dataset is used for the target computation:
https://github.com/GoogleCloudPlatform/tensorflow-lifetime-value/blob/0f8c16ea70a2e7da370965e23e9e2154978364fa/preparation/sql/common/features_n_target.sql#L107

I was wondering what the ratio was behind that decision?

Thank you in advance and best regards,
Florian