How do I use PCA with NumPy?

How do I use PCA with NumPy?

To use PCA with NumPy, you can follow these steps: standardize your data, compute the covariance matrix, and then find the eigenvalues and eigenvectors.

Can you show me a code example?

Sure! Here's a simple example:

import numpy as np
from sklearn.decomposition import PCA

# Sample data
X = np.array([[2.5, 2.4],
              [0.5, 0.7],
              [2.2, 2.9],
              [1.9, 2.2],
              [3.1, 3.0],
              [2.3, 3.1],
              [2, 1.6],
              [1, 1.1],
              [1.5, 1.6],
              [1.1, 0.9]])

# Standardizing the data
X_meaned = X - np.mean(X , axis = 0)

# PCA
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_meaned)
print(X_pca)

What does n_components do in PCA?

n_components specifies the number of principal components to keep. It reduces the dimensionality of the data while preserving as much variance as possible.