[python] Principal Component Analysis (PCA) in Python

Another Python PCA using numpy. The same idea as @doug but that one didn't run.

from numpy import array, dot, mean, std, empty, argsort
from numpy.linalg import eigh, solve
from numpy.random import randn
from matplotlib.pyplot import subplots, show

def cov(X):
    """
    Covariance matrix
    note: specifically for mean-centered data
    note: numpy's `cov` uses N-1 as normalization
    """
    return dot(X.T, X) / X.shape[0]
    # N = data.shape[1]
    # C = empty((N, N))
    # for j in range(N):
    #   C[j, j] = mean(data[:, j] * data[:, j])
    #   for k in range(j + 1, N):
    #       C[j, k] = C[k, j] = mean(data[:, j] * data[:, k])
    # return C

def pca(data, pc_count = None):
    """
    Principal component analysis using eigenvalues
    note: this mean-centers and auto-scales the data (in-place)
    """
    data -= mean(data, 0)
    data /= std(data, 0)
    C = cov(data)
    E, V = eigh(C)
    key = argsort(E)[::-1][:pc_count]
    E, V = E[key], V[:, key]
    U = dot(data, V)  # used to be dot(V.T, data.T).T
    return U, E, V

""" test data """
data = array([randn(8) for k in range(150)])
data[:50, 2:4] += 5
data[50:, 2:5] += 5

""" visualize """
trans = pca(data, 3)[0]
fig, (ax1, ax2) = subplots(1, 2)
ax1.scatter(data[:50, 0], data[:50, 1], c = 'r')
ax1.scatter(data[50:, 0], data[50:, 1], c = 'b')
ax2.scatter(trans[:50, 0], trans[:50, 1], c = 'r')
ax2.scatter(trans[50:, 0], trans[50:, 1], c = 'b')
show()

Which yields the same thing as the much shorter

from sklearn.decomposition import PCA

def pca2(data, pc_count = None):
    return PCA(n_components = 4).fit_transform(data)

As I understand it, using eigenvalues (first way) is better for high-dimensional data and fewer samples, whereas using Singular value decomposition is better if you have more samples than dimensions.