#featurescaling #standardization #Normalization
what is feature scaling and how to do feature scaling in python feature scaling machine learning is a feature engineering method used to normalize the range of features of data/ independent variables in machine learning. In data processing, it is also known as data normalization/standardization or z score normalization and is generally performed during the data preprocessing step.
it is also to use feature feature scaling if you use regularization in your model
Feature scaling is required because:
The coefficients of linear models are influenced by the scale of the variable.
Variables with bigger magnitude dominate over those with smaller magnitude
Gradient descent converges much faster on scaled data
Feature scaling decrease the time to find support vectors for SVMs
Euclidean distances are sensitive to feature magnitude.
PCA require the features to be centered at 0.
compute data
The machine learning models affected by the feature scale are:
Linear and Logistic Regression
Neural Networks
Support Vector Machines
KNN
Kmeans clustering
Principal Component Analysis (PCA)