import numpy
import pylab
from unsupervised.kmeans import KMeans
if __name__ == "__main__":
numpy.random.seed(1)
X = numpy.vstack((numpy.random.randn(10000, 2)*0.3,
numpy.random.randn(10000, 2)*0.3 + numpy.ones(2)))
estimator = KMeans(2, 200, 10)
estimator.fit(X)
print estimator.C_
print estimator.v
Y = estimator.predict(X)
print Y
pylab.plot(X[:, 0], X[:, 1], "o")
pylab.plot([estimator.C_[0, 0]], [estimator.C_[0, 1]], "o")
pylab.plot([estimator.C_[1, 0]], [estimator.C_[1, 1]], "o")
pylab.show()
if __name__ == "__main__":
numpy.random.seed(0)
train_images, T = load_mnist("training", 60000)
test_images, T2 = load_mnist("testing", 10000)
print "Dataset loaded"
train_cluster = train_images[:10000]
train_classifier = train_images
label_classifier = T
n_filters = 196
estimator = KMeans(n_filters=n_filters, batch_size=1000, n_iterations=10)
estimator.fit(train_cluster)
X = estimator.predict(train_classifier)
X2 = estimator.predict(test_images)
X_mean = X.mean(axis=0)
X_std = X.std(axis=0) + 1e-8
X = scale_features(X, X_mean, X_std)
X2 = scale_features(X2, X_mean, X_std)
print "Transformed datasets"
test_classifier(X, label_classifier, X2, T2)
pylab.figure()
pylab.subplots_adjust(wspace=0.0, hspace=0.0)
n_cells = numpy.min((int(numpy.sqrt(n_filters)), 10))
for i in range(n_cells**2):
pylab.subplot(n_cells, n_cells, i + 1)
pylab.imshow(estimator.C_[i].reshape(28, 28),
data = numpy.fmax(numpy.fmin(data, pstd), -pstd) / pstd
data = (data + 1) * 0.4 + 0.1;
return data
images = normalize_data(images)
patch_width = 8
n_filters = 25
n_samples, n_rows, n_cols = images.shape
n_features = n_rows * n_cols
patches = [extract_patches_2d(images[i], (patch_width, patch_width),
max_patches=1000, random_state=i)
for i in range(n_samples)]
patches = numpy.array(patches).reshape(-1, patch_width * patch_width)
print("Dataset consists of %d samples" % n_samples)
estimator = KMeans(n_filters=n_filters, batch_size=1000, n_iterations=200)
estimator.fit(patches)
print estimator.predict(patches)
pylab.figure()
for i in range(estimator.C_.shape[0]):
rows = max(int(numpy.sqrt(n_filters)), 2)
cols = max(int(numpy.sqrt(n_filters)), 2)
pylab.subplot(rows, cols, i + 1)
pylab.imshow(estimator.C_[i].reshape(patch_width, patch_width),
cmap=pylab.cm.gray, interpolation="nearest")
pylab.xticks(())
pylab.yticks(())
pylab.show()
# Clustering
kmeans = KMeans(k=n_centers, iterations=max_iterations, random_state=random_state, track_history=True)
kmeans.fit(X)
# Extract centroids
centroids = kmeans.history_centroids
# Create decision boundary data
h = .1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
area_data = np.c_[xx.ravel(), yy.ravel()]
# Prepare predictions
predicted_labels = []
predicted_area = []
for iteration in range(max_iterations):
kmeans.centroids = centroids[iteration]
area = np.array(kmeans.predict(area_data))
area = area.reshape(xx.shape)
predicted_labels.append(kmeans.predict(X))
predicted_area.append(area)
# Plotting and showing the animation.
fig, ax = plt.subplots(figsize=(15, 6), dpi=80)
animation = FuncAnimation(fig, update, frames=max_iterations, interval=800, repeat=False)
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.show()
