def bi_item_rating_pred(item_pair, train_mtx, pair_path, k, option):
pair = pred_set.pred_pair(pair_path)
item_sim_mtx = []
pred_list = []
if option == 1 or option == 2:
item_sim_mtx = movie_sim.item_dot_sim(train_mtx)
if option == 3 or option == 4:
item_zero_vec = np.where(~train_mtx.any(axis=1))[0]
train_mtx[[item_zero_vec], 0] = 0.001
item_sim_mtx = movie_sim.item_cos_sim(train_mtx)
for row in pair:
pred_rating = 0
movie_id = row[0]
user_id = row[1]
key = item_pair[movie_id]
item_sim_list = item_sim_mtx[key]
# top k+1 nearest neighbors
item_knn_list = np.argsort(item_sim_list)[::-1][0: k]
if option == 1 or option == 3:
pred_rating = np.sum(np.take(train_mtx[:, user_id], item_knn_list.tolist())) / float(k) + 3
if option == 2 or option == 4:
item_knn_sim = item_sim_list[item_knn_list]
if np.sum(item_knn_sim) != 0:
weight = item_knn_sim / np.sum(item_knn_sim)
pred_rating = np.sum(np.multiply(np.take(train_mtx[:, user_id], item_knn_list.tolist()), weight)) + 3
else:
pred_rating = 3.0
pred_list.append(pred_rating)
# output the result
pred_result.file_writer(pred_list)
return pred_list
def pcc_item_rating_pred(pair_path, k, option):
pair = pred_set.pred_pair(pair_path)
train_mtx = rating_matrix.matrix_transfer(2)
item_zero_vec = np.where(~train_mtx.any(axis=0))[0]
# add a bias to the all zero column vectors
train_mtx[:, [item_zero_vec]] = 0.001
pcc_mtx = np.transpose(train_mtx)
# user rating standardization
pcc_mtx = pcc_mtx - np.sum(pcc_mtx, axis=0) / len(pcc_mtx)
pcc_mtx /= np.linalg.norm(pcc_mtx, axis=0)
pcc_mtx = np.transpose(pcc_mtx)
item_sim_mtx = []
pred_list = []
if option == 1 or option == 2:
item_sim_mtx = movie_sim.item_dot_sim(pcc_mtx)
if option == 3 or option == 4:
train_mtx[:, [item_zero_vec]] = 0.001
item_sim_mtx = movie_sim.item_cos_sim(pcc_mtx)
for row in pair:
pred_rating = 0
movie_id = row[0]
user_id = row[1]
item_sim_list = item_sim_mtx[movie_id]
# top k+1 nearest neighbors
item_knn_list = np.argsort(item_sim_list)[::-1][0:k + 1]
if movie_id in item_knn_list:
position = np.where(item_knn_list == movie_id)
item_knn_list = np.delete(item_knn_list, position)
else:
item_knn_list = np.delete(item_knn_list, len(item_knn_list) - 1)
if option == 1 or option == 3:
pred_rating = np.sum(
np.take(train_mtx[:, user_id],
item_knn_list.tolist())) / float(k) + 3
if option == 2 or option == 4:
item_knn_sim = item_sim_list[item_knn_list]
if np.sum(item_knn_sim) != 0:
weight = item_knn_sim / np.sum(item_knn_sim)
pred_rating = np.sum(
np.multiply(
np.take(train_mtx[:, user_id], item_knn_list.tolist()),
weight)) + 3
else:
pred_rating = 3.0
pred_list.append(pred_rating)
# output the result
pred_result.file_writer(pred_list)
return pred_list
def pcc_item_rating_pred(pair_path, k, option):
pair = pred_set.pred_pair(pair_path)
train_mtx = rating_matrix.matrix_transfer(2)
item_zero_vec = np.where(~train_mtx.any(axis=0))[0]
# add a bias to the all zero column vectors
train_mtx[:, [item_zero_vec]] = 0.001
pcc_mtx = np.transpose(train_mtx)
# user rating standardization
pcc_mtx = pcc_mtx - np.sum(pcc_mtx, axis=0) / len(pcc_mtx)
pcc_mtx /= np.linalg.norm(pcc_mtx, axis=0)
pcc_mtx = np.transpose(pcc_mtx)
item_sim_mtx = []
pred_list = []
if option == 1 or option == 2:
item_sim_mtx = movie_sim.item_dot_sim(pcc_mtx)
if option == 3 or option == 4:
train_mtx[:, [item_zero_vec]] = 0.001
item_sim_mtx = movie_sim.item_cos_sim(pcc_mtx)
for row in pair:
pred_rating = 0
movie_id = row[0]
user_id = row[1]
item_sim_list = item_sim_mtx[movie_id]
# top k+1 nearest neighbors
item_knn_list = np.argsort(item_sim_list)[::-1][0: k+1]
if movie_id in item_knn_list:
position = np.where(item_knn_list == movie_id)
item_knn_list = np.delete(item_knn_list, position)
else:
item_knn_list = np.delete(item_knn_list, len(item_knn_list) - 1)
if option == 1 or option == 3:
pred_rating = np.sum(np.take(train_mtx[:, user_id], item_knn_list.tolist())) / float(k) + 3
if option == 2 or option == 4:
item_knn_sim = item_sim_list[item_knn_list]
if np.sum(item_knn_sim) != 0:
weight = item_knn_sim / np.sum(item_knn_sim)
pred_rating = np.sum(np.multiply(np.take(train_mtx[:, user_id], item_knn_list.tolist()), weight)) + 3
else:
pred_rating = 3.0
pred_list.append(pred_rating)
# output the result
pred_result.file_writer(pred_list)
return pred_list
def item_rating_pred(pair_path, k, option):
pair = pred_set.pred_pair(pair_path)
train_mtx = rating_matrix.matrix_transfer(2)
item_zero_vec = np.where(~train_mtx.any(axis=0))[0]
item_sim_mtx = []
pred_list = []
if option == 1 or option == 2:
item_sim_mtx = movie_sim.item_dot_sim(train_mtx)
if option == 3 or option == 4:
train_mtx[:, [item_zero_vec]] = 0.001
item_sim_mtx = movie_sim.item_cos_sim(train_mtx)
for row in pair:
pred_rating = 0
movie_id = row[0]
user_id = row[1]
item_sim_list = item_sim_mtx[movie_id]
# top k+1 nearest neighbors
item_knn_list = np.argsort(item_sim_list)[::-1][0:k + 1]
if movie_id in item_knn_list:
position = np.where(item_knn_list == movie_id)
item_knn_list = np.delete(item_knn_list, position)
else:
item_knn_list = np.delete(item_knn_list, len(item_knn_list) - 1)
if option == 1 or option == 3:
pred_rating = np.sum(
np.take(train_mtx[:, user_id],
item_knn_list.tolist())) / float(k) + 3
if option == 2 or option == 4:
item_knn_sim = item_sim_list[item_knn_list]
if np.sum(item_knn_sim) != 0:
weight = item_knn_sim / np.sum(item_knn_sim)
pred_rating = np.sum(
np.multiply(
np.take(train_mtx[:, user_id], item_knn_list.tolist()),
weight)) + 3
else:
pred_rating = np.sum(train_mtx[movie_id, :]) / np.size(
np.nonzero(train_mtx[movie_id, :])) + 3
pred_list.append(pred_rating)
# output the result
pred_result.file_writer(pred_list)
return pred_list
def item_rating_pred(pair_path, k, option):
pair = pred_set.pred_pair(pair_path)
train_mtx = rating_matrix.matrix_transfer(2)
item_zero_vec = np.where(~train_mtx.any(axis=0))[0]
item_sim_mtx = []
pred_list = []
if option == 1 or option == 2:
item_sim_mtx = movie_sim.item_dot_sim(train_mtx)
if option == 3 or option == 4:
train_mtx[:, [item_zero_vec]] = 0.001
item_sim_mtx = movie_sim.item_cos_sim(train_mtx)
for row in pair:
pred_rating = 0
movie_id = row[0]
user_id = row[1]
item_sim_list = item_sim_mtx[movie_id]
# top k+1 nearest neighbors
item_knn_list = np.argsort(item_sim_list)[::-1][0: k+1]
if movie_id in item_knn_list:
position = np.where(item_knn_list == movie_id)
item_knn_list = np.delete(item_knn_list, position)
else:
item_knn_list = np.delete(item_knn_list, len(item_knn_list) - 1)
if option == 1 or option == 3:
pred_rating = np.sum(np.take(train_mtx[:, user_id], item_knn_list.tolist())) / float(k) + 3
if option == 2 or option == 4:
item_knn_sim = item_sim_list[item_knn_list]
if np.sum(item_knn_sim) != 0:
weight = item_knn_sim / np.sum(item_knn_sim)
pred_rating = np.sum(np.multiply(np.take(train_mtx[:, user_id], item_knn_list.tolist()), weight)) + 3
else:
pred_rating = np.sum(train_mtx[movie_id, :]) / np.size(np.nonzero(train_mtx[movie_id, :])) + 3
pred_list.append(pred_rating)
# output the result
pred_result.file_writer(pred_list)
return pred_list