def main (k, m="means", init_type="random"):
# Starting clustering timer
start_cluster = timeit.default_timer()
# Initialize clusters
if init_type == "random":
initial_clusters = Initialize.random_centers(k)
else:
init_type = "kplusplus"
initial_clusters = Initialize.kmeans_plusplus(k, train_images_flat,\
dist_fn=Distance.sumsq)
# Run clustering algorithm
final_responsibilities, final_clusters = Kmeans.kmeans(k,train_images_flat,
initial_clusters, distfn = Distance.sumsq, method=m)
# Find and print clustering time
end_cluster = timeit.default_timer()
clustering_time = end_cluster - start_cluster
print "Time spent clustering : ", clustering_time
# Save representative images to file.
title = m + "_" + init_type + "_cluster" + str(k)
File.save_images(k, train_images, final_responsibilities,
final_clusters, title)
###########################################################################
# Calculate Accuracy #
###########################################################################
# Calculate final accuracy for clusters
final, cluster_set = Accuracy.final_accuracy(final_responsibilities,
train_labels, train_images_flat, final_clusters)
# Now see how well we can classify the dataset
start_cluster_test = timeit.default_timer()
predictions = ClassifyClusters.classify(cluster_set, test_images_flat,
test_labels, distfn = Distance.sumsq)
finish_cluster_test = timeit.default_timer()
# find time it took to test
testing_time = finish_cluster_test - start_cluster_test
print "Time spent testing : ", testing_time
###########################################################################
# Outputs #
###########################################################################
# k, prediction level, cluster_set,
results = {"k" : k, "prediction_accuracy" : predictions[1],
"cluster_means" : cluster_set, "cluster_stats" : final,
"clustering_time" : clustering_time, "testing_time" : testing_time}
with open('./results/' + title + '/' + title + '_results.json', 'w') as outfile:
json.dump(results, outfile, cls=File.NumpyEncoder)
test_images,test_labels = File.load_mnist("testing",path=os.getcwd())
# flatten training images into 60,000 x 784 array
train_images_flat = np.array([np.ravel(img) for img in train_images])
test_images_flat = np.array([np.ravel(img) for img in test_images])
###############################################################################
# Run Scikit_learn #
###############################################################################
k = int(sys.argv[1]) # number of clusters (system argument)
# Train k means model
kmeans = KMeans(init='k-means++', n_clusters=k, n_init=10)
kmeans_fit = kmeans.fit(train_images_flat)
# Get the cluster assignments of each point of training images
kmeans_labels = kmeans_fit.labels_
kmeans_centers = kmeans_fit.cluster_centers_
# Initialize a vector of responsibilities in a one-hot-coded format.
final_responsibilities = np.zeros((len(train_images_flat),k))
# For each cluster assignment, assign the appropriate vector in the
# one-hot-coded format to a 1.
for imgnum in range(len(train_images_flat)):
final_responsibilities[imgnum][kmeans_labels[imgnum]] = 1
# Obtain predictions for each point.
Z = kmeans.predict(test_images_flat)
# Determine accuracies.
Accuracy.final_accuracy(final_responsibilities, train_labels,
train_images_flat, kmeans_centers)