Python Machine Learning Cookbook - Second Edition

How to do it...

Let's see how we can perform a kernel PCA:

1. Create a new Python file and import the following packages (the full code is given in the kpca.py file that is provided for you):

import numpy as np 
import matplotlib.pyplot as plt 
 
from sklearn.decomposition import PCA, KernelPCA 
from sklearn.datasets import make_circles 

2. Define the seed value for the random number generator. This is needed to generate data samples for analysis:

# Set the seed for random number generator 
np.random.seed(7) 

3. Generate data that is distributed in concentric circles to demonstrate how PCA doesn't work in this case:

# Generate samples 
X, y = make_circles(n_samples=500, factor=0.2, noise=0.04)

4. Perform PCA on this data:

# Perform PCA pca = PCA() ...