movie_mappings = recsys_utils.read_movie_map()
user_means = np.squeeze(np.sum(np.array(training.todense()), axis=1))
user_means = np.divide(user_means,
(np.array(training.todense()) != 0).sum(1))
print('collaborative filtering for User-User:'******'float32')), metric='cosine')
print('distance calculation time:', time() - start_time_user)
predictions = predict(training, user_dist, testing, user_mappings,
movie_mappings, 10)
print('Time for User-User:'******'RMSE:', evaluation.RMSE(predictions, truth))
print('spearman rank correlation:',
evaluation.spearman_rank_correlation(predictions, truth))
print(
'top k precision:',
evaluation.top_k_precision(predictions,
testing,
user_means,
user_mappings,
k=5))
print('Total time:', time() - start_time_user)
# Item-item collaborative filtering
it_means = np.squeeze(np.sum(np.array(training.T.todense()), axis=1))
it_means = np.divide(it_means,
(np.array(training.T.todense()) != 0).sum(1))
print('collaborative filtering for Item-Item:')
start_time_item = time()
val[1]] = t2[val[0],
val[1]] - means_matrix[val[0]] - movie_matrix[val[1]]
means_matrix = np.squeeze(means_matrix)
movie_matrix = np.squeeze(movie_matrix)
user_dist = 1 - pairwise_distances(sub_mean(t), metric='cosine')
start_time_item = time()
predictions_usr = predict_baseline(training, user_dist, testing, user_map,
movie_map, 10, 'user', t2, means_matrix,
movie_matrix)
predictions_usr = np.squeeze(predictions_usr)
print('Total time for User-User:'******'RMSE:', evaluation.RMSE(predictions_usr, truth[0:10000]))
print('spearman_rank_correlation:',
evaluation.spearman_rank_correlation(predictions_usr, truth[0:10000]))
print(
'Precision on top K:',
evaluation.top_k_precision(predictions_usr, testing.head(10000),
means_matrix, user_map))
print('collaborative filtering for....')
start_time_item = time()
item_dist = 1 - pairwise_distances(sub_mean(training.T), metric='cosine')
print('Time taken to calculate distances:', time() - start_time_item)
t2 = t2.T
predictions_mov = predict_baseline(training.T, item_dist, testing, user_map,
movie_map, 10, 'item', t2, means_matrix,
movie_matrix)
predictions = np.squeeze(predictions_mov)
print('Total time for Item-item:', time() - start_time_item)
# Read data
train = np.array(recsys_utils.read_train())
test = recsys_utils.read_test_table()
truth = test['rating'].as_matrix()
user_map = recsys_utils.read_user_map()
movie_map = recsys_utils.read_movie_map()
start_time = time()
# Subtracting mean of data from train set
user_means = np.squeeze(np.sum(train, axis=1))
user_means = np.divide(user_means, (train != 0).sum(1))
for i in range(train.shape[0]):
train[i, :][train[i, :] != 0] -= user_means[i]
# Decomposition and Reconstruction of SVD
U, V_t, sigma = SVD(train, retain_energy=90, save_factorized=True)
reconstructed = np.dot(np.dot(U, sigma), V_t)
# Get predicted
pred_matrix = train + np.reshape(user_means, [len(user_means), 1])
ro = [user_map[x] for x in test['userId']]
co = [movie_map[x] for x in test['movieId']]
predicted = pred_matrix[ro, co]
total_time_svd = time() - start_time
print('RMSE:', evaluation.RMSE(np.array(predicted), truth))
print('spearman_rank_correlation',
evaluation.spearman_rank_correlation(np.array(predicted), truth))
print('Top k Precision(k=5):',
evaluation.top_k_precision(predicted, test, user_means, user_map, 5))
print('Total SVD time:', total_time_svd)
user_map = recsys_utils.read_user_map()
movie_map = recsys_utils.read_movie_map()
# User-user collaborative filtering
# user_means=np.squeeze(np.sum(np.array(train.todense()), axis=1))
user_means = np.squeeze(np.sum(np.array(train.todense()), axis=1))
user_means = np.divide(user_means, (np.array(train.todense()) != 0).sum(1))
print 'User-user collaborative filtering....'
start_time_user = time()
user_dist = 1 - pairwise_distances(subtract_mean(train.astype('float32')),
metric='cosine')
print 'Time taken to calculate distances:', time() - start_time_user
predictions = predict(train, user_dist, test, user_map, movie_map, 10)
print 'User-user-> Total time:', time() - start_time_user
print 'User-user-> RMSE:', evaluation.RMSE(predictions, truth)
print 'spearman_rank_correlation', evaluation.spearman_rank_correlation(
predictions, truth)
print 'top k precision:', evaluation.top_k_precision(predictions,
test,
user_means,
user_map,
k=5)
print 'Total time:', time() - start_time_user
# Item-item collaborative filtering
# item_means=np.squeeze(np.sum(np.array(train.T.todense()), axis=1))
item_means = np.squeeze(np.sum(np.array(train.T.todense()), axis=1))
item_means = np.divide(item_means,
(np.array(train.T.todense()) != 0).sum(1))
print 'Item-item collaborative filtering....'
start_time_item = time()
item_dist = 1 - pairwise_distances(
train=np.array(recsys_utils.read_train()) test=recsys_utils.read_test_table() truth=test['rating'].as_matrix() user_map=recsys_utils.read_user_map() movie_map=recsys_utils.read_movie_map() start_time=time() # Subtract means from train user_means=np.squeeze(np.sum(train, axis=1)) user_means=np.divide(user_means, (train!=0).sum(1)) for i in range(train.shape[0]): train[i, :][train[i, :]!=0]-=user_means[i] # SVD Decomposition and Reconstruction U, V_t, sigma=SVD(train, percent_energy_retain=100, save_factorized=True) print 'Factorization Time:', time()-start_time reconstructed=np.dot(np.dot(U, sigma), V_t) print 'RMSE(reconstruction):', evaluation.RMSE_mat(train, reconstructed) # Get Predictions pred_mat=train+np.reshape(user_means, [len(user_means), 1]) rows=[user_map[x] for x in test['userId']] cols=[movie_map[x] for x in test['movieId']] predictions=pred_mat[rows, cols] total_time_svd=time()-start_time print 'RMSE:', evaluation.RMSE(np.array(predictions), truth) print 'spearman_rank_correlation', evaluation.spearman_rank_correlation(np.array(predictions), truth) print 'Top k Precision(k=5):', evaluation.top_k_precision(predictions, test, user_means, user_map, 5) print 'Total SVD time:', total_time_svd