u_features, v_features, adj_train, train_labels, train_u_indices, train_v_indices, \
val_labels, val_u_indices, val_v_indices, test_labels, \
test_u_indices, test_v_indices, class_values = create_trainvaltest_split(DATASET, DATASEED, TESTING,
datasplit_path, SPLITFROMFILE,
VERBOSE)
num_users, num_items = adj_train.shape
num_side_features = 0
# feature loading
if not FEATURES:
u_features = sp.identity(num_users, format='csr')
v_features = sp.identity(num_items, format='csr')
u_features, v_features = preprocess_user_item_features(
u_features, v_features)
elif FEATURES and u_features is not None and v_features is not None:
# use features as side information and node_id's as node input features
print("Normalizing feature vectors...")
# liy - u_features 是个神马东西？user本身有age,zipcode ，occupation三个属性呢
# liy u_features 有23个属性，应该是把zipcode和occupation给one-hot离散化了
# liy -- 这个东西是对一个tuple的归一化，如果一个向量变成one-hot之后多个点都是1，这些点的权重也会减小
# 这个东西并不是对于一个属性的归一化，比如年龄神马的，不知道为什么要做这个操作，貌似是对属性稠密点和稀疏点做的一个归一化
u_features_side = normalize_features(u_features)
v_features_side = normalize_features(v_features)
#liy - 为什么要做这个hstack操作?
u_features_side, v_features_side = preprocess_user_item_features(
val_labels, val_u_indices, val_v_indices, test_labels, \
test_u_indices, test_v_indices, class_values = create_trainvaltest_split(DATASET, DATASEED, TESTING,
datasplit_path, SPLITFROMFILE, VERBOSE)
# num_mini_batch = np.int(np.ceil(train_labels.shape[0]/float(BATCHSIZE)))
num_mini_batch = train_labels.shape[0] // BATCHSIZE
print('num mini batch = ', num_mini_batch)
num_users, num_items = adj_train.shape
# feature loading
if not FEATURES:
u_features = sp.identity(num_users, format='csr')
v_features = sp.identity(num_items, format='csr')
u_features, v_features = preprocess_user_item_features(
u_features, v_features)
else:
raise ValueError('Features are not supported in this implementation.')
# global normalization
support = []
support_t = []
adj_train_int = sp.csr_matrix(adj_train, dtype=np.int32)
for i in range(NUMCLASSES):
# build individual binary rating matrices (supports) for each rating
support_unnormalized = sp.csr_matrix(adj_train_int == i + 1,
dtype=np.float32)
support_unnormalized_transpose = support_unnormalized.T
support.append(support_unnormalized)
support_t.append(support_unnormalized_transpose)
