def plotProgresskMeans(X, centroids, previous, idx, K, i, color):
"""plots the data
points with colors assigned to each centroid. With the previous
centroids, it also plots a line between the previous locations and
current locations of the centroids.
"""
# Plot the examples
plotDataPoints(X, idx)
# Plot the centroids as black x's
plt.scatter(centroids[:, 0],
centroids[:, 1],
marker='x',
s=60,
lw=3,
edgecolor='k')
# Plot the history of the centroids with lines
for j in range(len(centroids)):
plt.plot([centroids[j, 0], previous[j, 0]],
[centroids[j, 1], previous[j, 1]],
c=color)
# Title
plt.title('Iteration number %d' % i)
show()
raw_input("Program paused. Press Enter to continue...")
def displayData(X):
"""displays 2D data
stored in X in a nice grid. It returns the figure handle h and the
displayed array if requested."""
# Compute rows, cols
m, n = X.shape
example_width = round(np.sqrt(n))
example_height = (n / example_width)
# Compute number of items to display
display_rows = np.floor(np.sqrt(m))
display_cols = np.ceil(m / display_rows)
# Between images padding
pad = 1
# Setup blank display
display_array = -np.ones(
(pad + display_rows * (example_height + pad), pad + display_cols *
(example_width + pad)))
# Copy each example into a patch on the display array
curr_ex = 0
for j in np.arange(display_rows):
for i in np.arange(display_cols):
if curr_ex > m:
break
# Get the max value of the patch
max_val = np.max(np.abs(X[curr_ex, :]))
rows = [
pad + j * (example_height + pad) + x
for x in np.arange(example_height + 1)
]
cols = [
pad + i * (example_width + pad) + x
for x in np.arange(example_width + 1)
]
display_array[min(rows):max(rows),
min(cols):max(cols)] = X[curr_ex, :].reshape(
example_height, example_width) / max_val
curr_ex = curr_ex + 1
if curr_ex > m:
break
# Display Image
display_array = display_array.astype('float32')
plt.imshow(display_array.T)
plt.set_cmap('gray')
# Do not show axis
plt.axis('off')
show()
def visualizeFit(X, mu, sigma2):
"""
This visualization shows you the
probability density function of the Gaussian distribution. Each example
has a location (x1, x2) that depends on its feature values.
"""
n = np.linspace(0, 35, 71)
X1 = np.meshgrid(n, n)
Z = multivariateGaussian(
np.column_stack((X1[0].T.flatten(), X1[1].T.flatten())), mu, sigma2)
Z = Z.reshape(X1[0].shape)
plt.plot(X[:, 0], X[:, 1], 'bx')
# Do not plot if there are infinities
if not isinf(np.sum(Z)):
plt.contour(X1[0], X1[1], Z, 10.0**np.arange(-20, 0, 3).T)
show()
def plotDataPoints(X, idx):
"""plots data points in X, coloring them so that those
with the same index assignments in idx have the same color
"""
pass
# Create palette
# palette = hsv(K + 1)
# colors = palette(idx, :)
#
# # Plot the data
# c = dict(enumerate(np.eye(3)))
# colors=idx
map = plt.get_cmap("jet")
idxn = idx.astype('float') / max(idx.astype('float'))
colors = map(idxn)
plt.scatter(X[:, 0],
X[:, 1],
15,
edgecolors=colors,
marker='o',
facecolors='none',
lw=0.5)
show()
# Y is a 1682x943 matrix, containing ratings (1-5) of 1682 movies on
# 943 users
#
# R is a 1682x943 matrix, where R(i,j) = 1 if and only if user j gave a
# rating to movie i
# From the matrix, we can compute statistics like average rating.
print('Average rating for movie 1 (Toy Story): %f / 5' % np.mean(Y[0, R[0, :]]))
# We can "visualize" the ratings matrix by plotting it with imagesc
plt.figure()
plt.imshow(Y, aspect='equal', origin='upper', extent=(0, Y.shape[1], 0, Y.shape[0]/2.0))
plt.ylabel('Movies')
plt.xlabel('Users')
show()
input("Program paused. Press Enter to continue...")
## ============ Part 2: Collaborative Filtering Cost Function ===========
# You will now implement the cost function for collaborative filtering.
# To help you debug your cost function, we have included set of weights
# that we trained on that. Specifically, you should complete the code in
# cofiCostFunc.m to return J.
# Load pre-trained weights (X, Theta, num_users, num_movies, num_features)
data = scipy.io.loadmat('ex8_movieParams.mat')
X = data['X']
Theta = data['Theta']
num_users = data['num_users']
num_movies = data['num_movies']