def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
# Initialize values
m, n = X.shape
K = initial_centroids.shape[0]
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros((m, 1))
# Run K-Means
for i in range(max_iters):
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
plotProgresskMeans(X, centroids, previous_centroids, idx, K, i + 1)
previous_centroids = centroids
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
plt.show()
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
# RUNKMEANS runs the K - Means algorithm on data matrix X, where each row of X
# is a single example
# [centroids, idx] = RUNKMEANS(X, initial_centroids, max_iters, ...
# plot_progress) runs the K - Means algorithm on data matrix X, where each
# row of X is a single example.It uses initial_centroids used as the
# initial centroids.max_iters specifies the total number of interactions
# of K - Means to execute.plot_progress is a true / false flag that
# indicates if the function should also plot its progress as the
# learning happens.This is set to false by default.runkMeans returns
# centroids, a Kxn matrix of the computed centroids and idx, a m x 1
# vector of centroid assignments(i.e.each entry in range[1..K])
# Initialize values
m, n = np.shape(X)
K = np.size(initial_centroids, 0)
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros((m, 1))
# Run K - Means
for i in range(max_iters):
print('K-Means iteration #', i, ' out of ', max_iters)
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
plotProgresskMeans(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
"""runs the K-Means algorithm on data matrix X, where each
row of X is a single example. It uses initial_centroids used as the
initial centroids. max_iters specifies the total number of interactions
of K-Means to execute. plot_progress is a true/false flag that
indicates if the function should also plot its progress as the
learning happens. This is set to false by default. runkMeans returns
centroids, a Kxn matrix of the computed centroids and idx, a m x 1
vector of centroid assignments (i.e. each entry in range [1..K])
"""
# Plot the data if we are plotting progress
if plot_progress:
fig = plt.figure()
ax = plt.gca()
# Initialize values
m, n = X.shape
K = len(initial_centroids)
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros(m)
c = itertools.cycle('012')
rgb = np.eye(3)
# Run K-Means
for i in range(max_iters):
# Output progress
print('K-Means iteration %d/%d...' % (i, max_iters))
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
color = rgb[int(next(c))]
plotProgresskMeans(X, np.array(centroids),
np.array(previous_centroids), idx, K, i, color,
ax)
previous_centroids = centroids
show()
fig.canvas.draw()
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
# Hold off if we are plotting progress
if plot_progress:
pass
# hold off
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
#RUNKMEANS runs the K-Means algorithm on data matrix X, where each row of X
#is a single example
# centroids, idx = RUNKMEANS(X, initial_centroids, max_iters, plot_progress=false)
# runs the K-Means algorithm on data matrix X, where each
# row of X is a single example. It uses initial_centroids used as the
# initial centroids. max_iters specifies the total number of interactions
# of K-Means to execute. plot_progress is a True/False flag that
# indicates if the function should also plot its progress as the
# learning happens. This is set to False by default. runkMeans returns
# centroids, a K x n matrix of the computed centroids and idx, a vector of
# size m of centroid assignments (i.e. each entry in range [1..K])
#
# Plot the data if we are plotting progress
if plot_progress:
fig = figure()
hold(True)
# Initialize values
m, n = shape(X)
K = size(initial_centroids, 0)
centroids = initial_centroids
previous_centroids = centroids
idx = zeros(m)
# Run K-Means
for i in range(max_iters):
# Output progress
print 'K-Means iteration %d/%d...' % (i+1, max_iters)
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
plotProgresskMeans(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids
fig.show()
print 'Press enter to continue.'
raw_input()
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
# Hold off if we are plotting progress
if plot_progress:
hold(True)
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
#RUNKMEANS runs the K-Means algorithm on data matrix X, where each row of X
#is a single example
# [centroids, idx] = RUNKMEANS(X, initial_centroids, max_iters, ...
# plot_progress) runs the K-Means algorithm on data matrix X, where each
# row of X is a single example. It uses initial_centroids used as the
# initial centroids. max_iters specifies the total number of interactions
# of K-Means to execute. plot_progress is a true/false flag that
# indicates if the function should also plot its progress as the
# learning happens. This is set to false by default. runkMeans returns
# centroids, a Kxn matrix of the computed centroids and idx, a m x 1
# vector of centroid assignments (i.e. each entry in range [1..K])
#
# Initialize values
m, n = X.shape
K = initial_centroids.shape[0]
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros((m, 1))
# if plotting, set up the space for interactive graphs
# http://stackoverflow.com/a/4098938/583834
# http://matplotlib.org/faq/usage_faq.html#what-is-interactive-mode
if plot_progress:
plt.close()
plt.ion()
# Run K-Means
for i in range(max_iters):
# Output progress
sys.stdout.write('\rK-Means iteration {:d}/{:d}...'.format(i+1, max_iters))
sys.stdout.flush()
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
plotProgresskMeans(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids
input('Program paused. Press <Enter> to continue...')
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
# Hold off if we are plotting progress
print('\n')
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
#RUNKMEANS runs the K-Means algorithm on data matrix X, where each row of X
#is a single example
# centroids, idx = RUNKMEANS(X, initial_centroids, max_iters, plot_progress=false)
# runs the K-Means algorithm on data matrix X, where each
# row of X is a single example. It uses initial_centroids used as the
# initial centroids. max_iters specifies the total number of interactions
# of K-Means to execute. plot_progress is a True/False flag that
# indicates if the function should also plot its progress as the
# learning happens. This is set to False by default. runkMeans returns
# centroids, a K x n matrix of the computed centroids and idx, a vector of
# size m of centroid assignments (i.e. each entry in range [1..K])
#
# Plot the data if we are plotting progress
if plot_progress:
fig = figure()
hold(True)
# Initialize values
m, n = shape(X)
K = size(initial_centroids, 0)
centroids = initial_centroids
previous_centroids = centroids
idx = zeros(m)
# Run K-Means
for i in range(max_iters):
# Output progress
print 'K-Means iteration %d/%d...' % (i + 1, max_iters)
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
plotProgresskMeans(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids
fig.show()
print 'Press enter to continue.'
raw_input()
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
# Hold off if we are plotting progress
if plot_progress:
hold(True)
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
"""runs the K-Means algorithm on data matrix X, where each
row of X is a single example. It uses initial_centroids used as the
initial centroids. max_iters specifies the total number of interactions
of K-Means to execute. plot_progress is a true/false flag that
indicates if the function should also plot its progress as the
learning happens. This is set to false by default. runkMeans returns
centroids, a Kxn matrix of the computed centroids and idx, a m x 1
vector of centroid assignments (i.e. each entry in range [1..K])
"""
# Plot the data if we are plotting progress
if plot_progress:
plt.figure()
# Initialize values
m, n = X.shape
K = len(initial_centroids)
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros(m)
c = itertools.cycle('012')
rgb = np.eye(3)
# Run K-Means
for i in range(max_iters):
# Output progress
print 'K-Means iteration %d/%d...' % (i, max_iters)
# For each example in X, assign it to the closest centroid
_, idx = findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
color = rgb[int(next(c))]
plotProgresskMeans(X, np.array(centroids),
np.array(previous_centroids), idx, K, i, color)
previous_centroids = centroids
# raw_input("Press Enter to continue...")
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
# Hold off if we are plotting progress
if plot_progress:
pass
# hold off
return centroids, idx
def runkMeans(name, X, initial_centroids, max_iters, plot_progress=False):
#RUNKMEANS runs the K-Means algorithm on data matrix X, where each row of X
#is a single example
# [centroids, idx] = RUNKMEANS(X, initial_centroids, max_iters, ...
# plot_progress) runs the K-Means algorithm on data matrix X, where each
# row of X is a single example. It uses initial_centroids used as the
# initial centroids. max_iters specifies the total number of interactions
# of K-Means to execute. plot_progress is a true/false flag that
# indicates if the function should also plot its progress as the
# learning happens. This is set to false by default. runkMeans returns
# centroids, a Kxn matrix of the computed centroids and idx, a m x 1
# vector of centroid assignments (i.e. each entry in range [1..K])
#
# Initialize values
m, n = X.shape
K = initial_centroids.shape[0]
centroids = initial_centroids
previous_centroids = []
idx = None
idx_history = []
# Run K-Means
for i in range(max_iters):
# Output progress
print('K-Means iteration %d/%d...' % (i, max_iters))
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
idx_history.append(idx)
previous_centroids.append(centroids)
# Optionally, plot progress here
if plot_progress:
fig = plt.figure()
plotProgresskMeans(X, centroids, previous_centroids, idx_history, K, i)
plt.savefig('figure%s.%03d.png' % (name, i))
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
#end
#end
return (centroids, idx)
def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
'''
[centroids, idx] = RUNKMEANS(X, initial_centroids, max_iters, ...
plot_progress) runs the K-Means algorithm on data matrix X, where each
row of X is a single example. It uses initial_centroids used as the
initial centroids. max_iters specifies the total number of interactions
of K-Means to execute. plot_progress is a true/false flag that
indicates if the function should also plot its progress as the
learning happens. This is set to false by default. runkMeans returns
centroids, a Kxn matrix of the computed centroids and idx, a m x 1
vector of centroid assignments (i.e. each entry in range [1..K])
'''
import numpy as np
from findClosestCentroids import findClosestCentroids
from plotProgresskMeans import plotProgresskMeans
from computeCentroids import computeCentroids
import matplotlib.pyplot as plt
# Initialize values
m, _ = np.shape(X)
K = np.size(initial_centroids, 0)
centroids = initial_centroids
acc_centroids = centroids
idx = np.zeros((m, 1))
# Run K-Means
for i in range(max_iters):
# Output progress
print('K-Means iteration %d/%d...\n' % (i, max_iters))
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
plotProgresskMeans(X, acc_centroids, idx, K, i)
plt.show()
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
acc_centroids = np.append(acc_centroids, centroids, axis=0)
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
# Initialize values
m, n = X.shape
K = initial_centroids.shape[0]
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros((m, 1))
# Run K-Means
for i in range(1, max_iters + 1):
print('K-Means iteration %d/%d' % (i, max_iters))
idx = findClosestCentroids(X, centroids)
if plot_progress:
plotProgresskMeans(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids
centroids = computeCentroids(X, idx, K)
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress=None):
# Set default value for plot progress
if plot_progress == None:
plot_progress = False
# Plot the data if we are plotting progress
if plot_progress:
plt.figure()
# Initialize values
m = X.shape[0]
n = X.shape[1]
K = initial_centroids.shape[0]
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros(m)
idx = idx.astype(int)
# Run K-Means
for i in range(max_iters):
# Output progress
print('K-Means iteration %d/%d...\n' % (i, max_iters))
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
# For each example in X, assign it to the closest centroid
if plot_progress:
plotProgresskMeans(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids.copy()
input('Press enter to continue.\n')
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress = False):
# RUNKMEANS runs the K - Means algorithm on data matrix X, where each row of X
# is a single example
# [centroids, idx] = RUNKMEANS(X, initial_centroids, max_iters, ...
# plot_progress) runs the K - Means algorithm on data matrix X, where each
# row of X is a single example.It uses initial_centroids used as the
# initial centroids.max_iters specifies the total number of interactions
# of K - Means to execute.plot_progress is a true / false flag that
# indicates if the function should also plot its progress as the
# learning happens.This is set to false by default.runkMeans returns
# centroids, a Kxn matrix of the computed centroids and idx, a m x 1
# vector of centroid assignments(i.e.each entry in range[1..K])
# Initialize values
m, n = np.shape(X)
K = np.size(initial_centroids, 0)
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros((m, 1))
# Run K - Means
for i in range(max_iters):
print('K-Means iteration #', i,' out of ', max_iters)
# For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
plotProgresskMeans(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids
# Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K)
return centroids, idx
def runkMeans(X, initial_centroids, max_iters, plot_progress=False):
#RUNKMEANS runs the K-Means algorithm on data matrix X, where each row of X
#is a single example
# [centroids, idx] = RUNKMEANS(X, initial_centroids, max_iters, ...
# plot_progress) runs the K-Means algorithm on data matrix X, where each
# row of X is a single example. It uses initial_centroids used as the
# initial centroids. max_iters specifies the total number of interactions
# of K-Means to execute. plot_progress is a true/false flag that
# indicates if the function should also plot its progress as the
# learning happens. This is set to false by default. runkMeans returns
# centroids, a Kxn matrix of the computed centroids and idx, a m x 1
# vector of centroid assignments (i.e. each entry in range [1..K])
#
# Set default value for plot progress
# (commented out due to pythonic default parameter assignment above)
# if not plot_progress:
# plot_progress = False
# Plot the data if we are plotting progress
# if plot_progress:
# plt.hold(True)
# Initialize values
m, n = X.shape
K = initial_centroids.shape[0]
centroids = initial_centroids
previous_centroids = centroids
idx = np.zeros((m, 1))
# if plotting, set up the space for interactive graphs
# http://stackoverflow.com/a/4098938/583834
# http://matplotlib.org/faq/usage_faq.html#what-is-interactive-mode
if plot_progress:
plt.close()
plt.ion()
# Run K-Means
for i in xrange(max_iters):
# Output progress
sys.stdout.write('\rK-Means iteration {:d}/{:d}...'.format(i+1, max_iters))
sys.stdout.flush()
# For each example in X, assign it to the closest centroid
idx = fcc.findClosestCentroids(X, centroids)
# Optionally, plot progress here
if plot_progress:
ppkm.plotProgresskMeans(X, centroids, previous_centroids, idx, K, i)
previous_centroids = centroids
raw_input('Press enter to continue.')
# Given the memberships, compute new centroids
centroids = cc.computeCentroids(X, idx, K)
# Hold off if we are plotting progress
print('\n')
# if plot_progress:
# plt.hold(False)
return centroids, idx
