Standardization

Python'da Machine Learning için Ön İşleme

James Chapman

Curriculum Manager, DataCamp

What is standardization?

Standardization: transform continuous data to appear normally distributed

scikit-learn models assume normally distributed data
Using non-normal training data can introduce bias
Log normalization and feature scaling in this course
Applied to continuous numerical data

When to standardize: linear distances

Model in linear space

Examples:

k-Nearest Neighbors (kNN)
Linear regression
K-Means Clustering

A knn example.

When to standardize: high variance

Model in linear space

Examples:

k-Nearest Neighbors (kNN)
Linear regression
K-Means Clustering

Dataset features have high variance

A knn example.

When to standardize: different scales

Features are on different scales

Example:

Predicting house prices using no. bedrooms and last sale price

Linearity assumptions

Let's practice!

Python'da Machine Learning için Ön İşleme

Preparing Video For Download...