def load(self, ratings, train, validation):
self.train = train
self.validation = validation
self.num_users = movielens_extractor.get_num_users(ratings)
self.num_items = movielens_extractor.get_num_items(ratings)
self.train = train
self.validation = validation
self.mean_rating = np.mean(self.train[:, 2])
self.ratings_test = np.float64(validation[:, 2])
self.item_features = 0.1 * NormalRandom.generate_matrix(
self.num_items, self.num_features)
self.user_features = 0.1 * NormalRandom.generate_matrix(
self.num_users, self.num_features)
self.df_post_item = self.df_item + self.num_items
self.df_post_user = self.df_user + self.num_users
# num_user, num_item, ratings = build_ml_1m()
self.matrix = build_rating_matrix(self.num_users, self.num_items,
train)
self.matrix = self.matrix.T
self.counter_prob = 1
self.probe_rat_all = self.pred(self.item_features, self.user_features,
self.validation, self.mean_rating)
self.estimate()
def update_user_features(self):
self.matrix = self.matrix.T
# print('matrix', self.matrix.shape, self.matrix[0:10, 0:5])
# Gibbs sampling for user features
for user_id in range(self.num_users):
self.results_file.write('User %d\n' % (user_id + 1))
items = self.matrix[:, user_id] > 0.0
features = self.item_features[items, :]
ratings = self.matrix[items, user_id] - self.mean_rating
rating_len = len(ratings)
ratings = np.reshape(ratings, (rating_len, 1))
covar = inv(self.alpha_user +
self.beta * np.dot(features.T, features))
temp = self.beta * \
np.dot(features.T, ratings) + np.dot(
self.alpha_user, self.mu_user)
mean = np.dot(covar, temp)
lam = cholesky(covar)
temp_feature = mean + np.dot(
lam, NormalRandom.generate_matrix(self.num_features, 1))
temp_feature = np.reshape(temp_feature, (self.num_features, ))
self.user_features[user_id, :] = temp_feature
self.results_file.write(
'user_features \t (%d,%d) \t %16.16f\n' %
(self.user_features.shape[0], self.user_features.shape[1],
self.user_features[0, 0]))
def sample_wishart(sigma, dof):
'''
Returns a sample from the Wishart distn, conjugate prior for precision matrices.
'''
n = sigma.shape[0]
chol = np.linalg.cholesky(sigma).T
rnd_matrix = NormalRandom.generate_matrix(dof, n)
X = np.dot(rnd_matrix, chol)
W = np.dot(X.T, X)
return W
def udpate_item_features(self):
self.matrix = self.matrix.T
# Gibbs sampling for item features
for item_id in range(self.num_items):
self.results_file.write('Item %d\n' % (item_id + 1))
users = self.matrix[:, item_id] > 0.0
features = self.user_features[users, :]
ratings = self.matrix[users, item_id] - self.mean_rating
rating_len = len(ratings)
ratings = np.reshape(ratings, (rating_len, 1))
covar = inv(self.alpha_item +
self.beta * np.dot(features.T, features))
lam = cholesky(covar)
temp = self.beta * \
np.dot(features.T, ratings) + np.dot(
self.alpha_item, self.mu_item)
mean = np.dot(covar, temp)
temp_feature = mean + np.dot(
lam, NormalRandom.generate_matrix(self.num_features, 1))
temp_feature = np.reshape(temp_feature, (self.num_features, ))
self.item_features[item_id, :] = temp_feature
def update_user_params(self):
x_bar = np.mean(self.user_features, 0).T
x_bar = np.reshape(x_bar, (self.num_features, 1))
S_bar = np.cov(self.user_features.T)
norm_X_bar = self.mu0_user - x_bar
WI_post = inv(inv(self.WI_user) + self.num_users * S_bar + \
np.dot(norm_X_bar, norm_X_bar.T) * \
(self.num_users * self.beta_user) / (self.beta_user + self.num_users))
# Not sure why we need this...
WI_post = (WI_post + WI_post.T) / 2.0
# update alpha_user
self.alpha_user = sample_wishart(WI_post, self.df_post_user)
# update mu_item
mu_temp = (self.beta_user * self.mu0_user + self.num_users * x_bar) / \
(self.beta_user + self.num_users)
lam = cholesky(inv(
(self.beta_user + self.num_users) * self.alpha_user))
self.mu_user = mu_temp + np.dot(
lam, NormalRandom.generate_matrix(self.num_features, 1))
