def apply_pca(X):
eigenvectors, eigenvalues = compute_pca(X)
# Stack first two eigenvectors
E_2 = np.column_stack((eigenvectors[0], eigenvectors[1]))
X_PCA = np.dot(X, E_2)
# Print report data
print "Largest two eigenvalues:"
print eigenvalues[0]
print eigenvalues[1]
print "\n"
print "First five rows of E_2:"
print E_2[0:5, :]
print "\n"
print "First five rows of X_PCA:"
print X_PCA[0:5, :]
return X_PCA
def apply_pca(matrix):
[EVecs, EVal] = compute_pca(matrix)
E2 = EVecs[:, :2]
X_PCA = matrix.dot(E2)
print("2 eigenvalues:", EVal[:2])
print("5 rows of E2:\n", E2[:5, :])
print("5 rows of X_PCA:\n", X_PCA[:5, :])
return X_PCA
def show_cumulative_variance():
import scipy.io
data = scipy.io.loadmat('svhn.mat')
train_data = np.array(data['train_features'])
cumsum = np.cumsum(compute_pca(train_data)[1])
x_axis = [x for x in range(len(cumsum))]
plt.plot(x_axis, cumsum, 'ro')
plt.xlabel("Principal components")
plt.ylabel("Comulative variance")
plt.show()
def PCA(NormMatrix, file2D, file3D):
transposed_matrix = NormMatrix.T
proj, pve, pcs = compute_pca(transposed_matrix,
scaled=True,
logged=False,
kernel=None,
kernel_kwargs=None,
variant='pca',
pf=1)
print '\nTransposed Matrix =', np.shape(transposed_matrix)
print '\nProj =', np.shape(proj)
print '\nPVE =', np.shape(pve)
print '\nPCS =', np.shape(pcs)
print proj
experiment = [
"Human Liver Carcinoma", "Heatshock", "UV", "Hepatocyte GF",
"Interferons", "Brain"
]
plot_pca(file2D,
proj,
pcs=(0, 1),
labels=experiment,
label_points=True,
levels=None,
colors=None,
legend=True,
s=100)
plot_pca3D(file3D,
proj,
pcs=(0, 1, 2),
labels=experiment,
label_points=True,
levels=None,
colors=None,
legend=True,
s=100)
# Reduce dimensionality of test data and center it using the training mean
T = test_x - mu
T = T.dot(EVecs)
probabilities = np.zeros((classes, test_y.shape[0]))
# Find posterior probabilities for every class
for k in range(classes):
probabilities[k, :] = gaussianClassifier(mu_hat[k, :], sigma_hat[:, :,
k], T)
# Find predicted class labels for the test data and correct it so it starts from 1
labels_predicted = np.argmax(probabilities, axis=0) + 1
confusion_matrix = MyConfusionMatrix(test_y, labels_predicted)
return confusion_matrix
EVecs, EVals = compute_pca(train_x)
confusion_matrix = trainAndTest(train_x, train_y, test_x, test_y, EVecs, 100)
scipy.io.savemat('confmat_d100.mat', {'Confusion Matrix': confusion_matrix})
classification_rate = np.diag(confusion_matrix / confusion_matrix.sum(axis=0))
for float in classification_rate:
print '{:.1%}'.format(float)
# Pretty printing for the confusion matrix using Pandas. Used only for the report.
# y_actual = pd.Index(np.arange(1,6,1), name="Actual")
# y_pred = pd.Index(np.arange(1,6,1), name="Predicted")
# df = pd.DataFrame(data = confusion_matrix.astype(int), index = y_actual, columns=y_pred)
# print df
import scipy.io
import compute_pca as cp
import numpy as np
from sklearn import decomposition
from matplotlib.mlab import PCA
data = scipy.io.loadmat('svhn.mat')
X=data['train_features']
(vec,val)=cp.compute_pca(X)
E2=vec[:,0:2]
egvals=val[0:2]
X_PCA=np.dot(X,E2)
print X.shape
print E2.shape
v1=E2[:,0]
v2=E2[:,1]
#sklearn_pca = sklearnPCA(n_components=2)
#sklearn_transf = sklearn_pca.fit_transform(X)
#print sklearn_transf
pca = decomposition.PCA(n_components=2)
pca.fit(X.T)
Y = pca.transform(X.T)
print Y[0:2,0:2]
print X_PCA[0:2,0:2]
#print np.isclose(sklearn_transf,X_PCA)
#print type(mlab_pca)
#np.savetxt("eigenvalues.out",egvals,delimiter=' , ')
#np.savetxt("xpca.out",X_PCA,delimiter=" ")
import scipy.io
import numpy as np
import compute_pca
import matplotlib.pyplot as plt
data = scipy.io.loadmat('svhn.mat')
X = data['train_features']
eigenvectors, eigenvalues = compute_pca.compute_pca(X)
cs = np.cumsum(eigenvalues)
x = range(1, 101)
y = cs
print cs
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
ax.set_title('Cumulative variance')
ax.scatter(x, y)
plt.show()