Skip to content

Is there a better way to normalize and standardize our data ? #45

Answered by mrdbourke
Programmer-RD-AI asked this question in Q&A

You must be logged in to vote

Hey Ranuga,

Those are some of the most effective methods for preparing data.

You could craft your own custom TensorFlow functions to perform the same as Sklearn but the Sklearn classes are very well established.

This article sheds some more light on scaling, standardizing and normalizing: https://towardsdatascience.com/scale-standardize-or-normalize-with-scikit-learn-6ccc7d176a02

TensorFlow also has a built-in utility for normalizing NumPy arrays: https://www.tensorflow.org/api_docs/python/tf/keras/utils/normalize (there may be more methods like this built-in too if you wanted to stick with pure TensorFlow)

Replies: 1 comment 1 reply

You must be logged in to vote
1 reply
@Programmer-RD-AI

Answer selected by mrdbourke
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants