Supervised data compression via LDA

Linear Discriminant Analysis (LDA) can be used as a technique for feature extraction to increase the computational effciency and reduce the degree of over-ftting due to the curse of dimensionality in nonregularized models.

1.1 Computing the scatter matrices

np.set_printoptions(precision=4)

mean_vecs = []
for label in range(1, 4):
    mean_vecs.append(np.mean(X_train_std[y_train == label], axis=0))

1.2  The covariance matrix is a normalized version of the scatter matrix

d = 13  # number of features
S_W = np.zeros((d, d))
for label, mv in zip(range(1, 4), mean_vecs):
    class_scatter = np.zeros((d, d))  # scatter matrix for each class
    for row in X_train_std[y_train == label]:
        row, mv = row.reshape(d, 1), mv.reshape(d, 1)  # make column vectors
        class_scatter += (row - mv).dot((row - mv).T)
    S_W += class_scatter                          # sum class scatter matrices

d = 13  # number of features
S_W = np.zeros((d, d))
for label, mv in zip(range(1, 4), mean_vecs):
    class_scatter = np.cov(X_train_std[y_train == label].T)
    S_W += class_scatter

1.3  compute the between-class scatter matrix 

mean_overall = np.mean(X_train_std, axis=0)
d = 13  # number of features
S_B = np.zeros((d, d))
for i, mean_vec in enumerate(mean_vecs):
    n = X_train[y_train == i + 1, :].shape[0]
    mean_vec = mean_vec.reshape(d, 1)  # make column vector
    mean_overall = mean_overall.reshape(d, 1)  # make column vector
    S_B += n * (mean_vec - mean_overall).dot((mean_vec - mean_overall).T)

2.1 Selecting linear discriminants for the new feature subspace

eigen_vals, eigen_vecs = np.linalg.eig(np.linalg.inv(S_W).dot(S_B))

# Make a list of (eigenvalue, eigenvector) tuples
eigen_pairs = [(np.abs(eigen_vals[i]), eigen_vecs[:, i])
               for i in range(len(eigen_vals))]

# Sort the (eigenvalue, eigenvector) tuples from high to low
eigen_pairs = sorted(eigen_pairs, key=lambda k: k[0], reverse=True)

2.2 C all the content of the class-discriminatory information  discriminability

tot = sum(eigen_vals.real)
discr = [(i / tot) for i in sorted(eigen_vals.real, reverse=True)]
cum_discr = np.cumsum(discr)

2.3 Show

plt.bar(range(1, 14), discr, alpha=0.5, align='center',
        label='individual "discriminability"')
plt.step(range(1, 14), cum_discr, where='mid',
         label='cumulative "discriminability"')
plt.ylabel('"discriminability" ratio')
plt.xlabel('Linear Discriminants')
plt.ylim([-0.1, 1.1])
plt.legend(loc='best')
plt.show()

3. Projecting samples onto the new feature space

w = np.hstack((eigen_pairs[0][1][:, np.newaxis].real,
              eigen_pairs[1][1][:, np.newaxis].real))
X_train_lda = X_train_std.dot(w)
colors = ['r', 'b', 'g']
markers = ['s', 'x', 'o']

for l, c, m in zip(np.unique(y_train), colors, markers):
    plt.scatter(X_train_lda[y_train == l, 0] * (-1),
                X_train_lda[y_train == l, 1] * (-1),
                c=c, label=l, marker=m)

plt.xlabel('LD 1')
plt.ylabel('LD 2')
plt.legend(loc='lower right')
plt.show()

4. LDA via scikit-learn

lda = LDA(n_components=2)
X_train_lda = lda.fit_transform(X_train_std, y_train)

lr = LogisticRegression()
lr = lr.fit(X_train_lda, y_train)

plot_decision_regions(X_train_lda, y_train, classifier=lr)
plt.xlabel('LD 1')
plt.ylabel('LD 2')
plt.legend(loc='lower left')
# plt.tight_layout()
# plt.savefig('./images/lda3.png', dpi=300)
plt.show()

4.1 By lowering the regularization strength, we could probably shift the decision boundaries so that the logistic regression models classify all samples in the training  dataset correctly.

X_test_lda = lda.transform(X_test_std)

plot_decision_regions(X_test_lda, y_test, classifier=lr)
plt.xlabel('LD 1')
plt.ylabel('LD 2')
plt.legend(loc='lower left')
plt.show()

Reference: 《Python Machine Learning》