This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def matrix_factorization_quux( | |
D, P, Q, steps=5000, alpha=0.0002, beta=0.02): | |
K = P.shape[1] | |
P = np.copy(P) | |
Q = np.copy(Q) | |
for step in xrange(steps): | |
for i in xrange(len(D)): | |
for j in xrange(len(D[i])): | |
if not getmask(D)[i, j]: | |
eij = D[i, j] - np.dot(P[i, :], Q[:, j]) | |
for k in xrange(K): | |
P[i, k] = P[i, k] + alpha * (2 * eij * Q[k, j] - beta * P[i, k]) | |
Q[k, j] = Q[k, j] + alpha * (2 * eij * P[i, k] - beta * Q[k, j]) | |
return P, Q | |
if __name__ == '__main__': | |
D = np.array([[5, 3, -1, 1], | |
[4, -1, -1, 1], | |
[1, 1, -1, 5], | |
[1, -1, -1, 4], | |
[-1, 1, 5, 5]]) | |
D = ma.masked_array(D, mask=D==-1) | |
m, n = D.shape | |
K = 2 | |
P = np.random.rand(m, K) | |
Q = np.random.rand(K, n) | |
np.set_printoptions(formatter={'all': lambda x: str(x).rjust(2)}) | |
print 'Ratings Matrix\n', D, '\n' | |
np.set_printoptions(precision = 2, formatter=None) | |
P_theano_bgd, Q_theano_bgd = matrix_factorization_bgd(D, P, Q) | |
print 'Theano Batch Gradient Descent\n',\ | |
np.dot(P_theano_bgd, Q_theano_bgd), '\n' | |
P_theano_sgd, Q_theano_sgd = matrix_factorization_sgd(D, P, Q) | |
print 'Theano Stochastic Gradient Descent\n',\ | |
np.dot(P_theano_sgd, Q_theano_sgd), '\n' | |
P_quux, Q_quux = matrix_factorization_quux(D, P, Q) | |
print 'quuxlabs\n', np.dot(P_quux, Q_quux), '\n' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment