Is there a better way to normalize and standardize our data ? #45
-
|
Is there a better way to normalize and standardize our data ? |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment 1 reply
-
|
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) |
Beta Was this translation helpful? Give feedback.
-
|
ok thank you so much @mrdbourke |
Beta Was this translation helpful? Give feedback.
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)