Hands-On Image Processing with Python

Dimension reduction and visualization with PCA

In this section, we will use the scikit-learn's digits dataset that contains 1,797 images (each of 8 x 8 pixels) of handwritten digits. Each row represents an image in the data matrix. Let's first load and display the first 25 digits from the dataset with the following code block:

import numpy as npimport matplotlib.pylab as plt from sklearn.datasets import load_digits from sklearn.preprocessing import StandardScalerfrom sklearn.decomposition import PCAfrom sklearn.pipeline import Pipelinedigits = load_digits() #print(digits.keys())print(digits.data.shape)j = 1np.random.seed(1)fig = plt.figure(figsize=(3,3)) fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05) for i ...