X.append(np.array(x[0:-1].split(' ')).astype("float64"))
X = np.asanyarray(X)
samples_file.close()
print("Read", len(X), "samples of dimension", len(X[0]))
# Plot the sampling distribution
d = len(X[0])
for i in range(d):
plt.subplot(d, 1, i + 1)
plt.hist(X[:, i], 50, density=True)
plt.suptitle("Complete distribution")
plt.show()
# Find the optimal number of clustering
mcmc.elbow_search(X, 1, 10)
ncent = int(input("Enter the number of centroids: "))
# Store the clusters, which will be candidate modes
centroids, freq = mcmc.detailed_clustering(X, ncent, U)
# Perform gradient descent on each centroid to identify the modes
print("\nSearch for the modes: ")
for i in range(ncent):
print("Gradient descent on candidate mode number", i)
if (mcmc.simple_descent(centroids[i], U, gradU)):
print("MODE FOUND: centroid number ", i)
for i in range(d):
plt.subplot(d, 1, i + 1)
plt.scatter(centroids[:, i], freq, marker="*")
plt.suptitle("Clustered distribution")
plt.show()
X.append(np.array(x[0:-1].split(' ')).astype("float64"))
X = np.asanyarray(X)
samples_file.close()
print("Read", len(X), "samples of dimension", len(X[0]))
# Find the optimal number of clustering
mcmc.elbow_search(X, 1, 20)
ncent = int(input("Enter the number of centroids: "))
# Store the clusters, which will be candidate modes
centroids, freq = mcmc.detailed_clustering(X, ncent, ban_U)
freq = freq / 100.
# Perform gradient descent on each centroid to identify the modes
print("\nSearch for the modes: ")
for i in range(ncent):
print("Gradient descent on candidate mode number", i)
if (mcmc.simple_descent(centroids[i], ban_U, ban_gradU, eta=0.001)):
print("MODE FOUND: centroid number ", i)
# Plot the sampling empirical distribution
d = len(X[0])
for i in range(d):
plt.subplot(d, 1, i + 1)
plt.hist(X[:, i], 100, density=True, color='steelblue')
plt.grid(True)
plt.suptitle("Complete distribution")
plt.show()
for i in range(d):
plt.subplot(d, 1, i + 1)
plt.scatter(centroids[:, i], freq, marker="*", color='green')
plt.grid(True)