)
print("\tsaving preprocessed aux path - %s" % aux_path)
print("\tsaving preprocessed data path - %s" % data_path)
print("\trating data path - %s" % path_rating)
print("\tdocument data path - %s" % path_itemtext)
print("\tprofile data path - %s" % path_usertext)
print ("\tmin_rating: %d\n\tmax_length_document: %d\n\tmax_df: %.1f\n\tvocab_size: %d\n\tsplit_ratio: %.1f" \
% (min_rating, max_length, max_df, vocab_size, split_ratio))
print(
"==========================================================================================="
)
R, D_all = data_factory.preprocess_ext(path_rating, path_itemtext,
path_usertext, min_rating,
max_length, max_df, vocab_size)
data_factory.save(aux_path, R, D_all)
data_factory.generate_train_valid_test_file_from_R(data_path, R,
split_ratio)
else:
res_dir = args.res_dir
emb_dim = args.emb_dim
pretrain_w2v = args.pretrain_w2v
dimension = args.dimension
lambda_u = args.lambda_u
lambda_v = args.lambda_v
max_iter = args.max_iter
num_kernel_per_ws = args.num_kernel_per_ws
give_weight = args.give_weight
threshold_doclen = args.threshold_length_document
threshold_sentlen = args.threshold_length_sentence
binary_rating = args.binary_rating
max_df = args.max_df
vocab_size = args.vocab_size
split_ratio = args.split_ratio
print "=================================Preprocess Option Setting================================="
print "\tsaving preprocessed aux path - %s" % aux_path
print "\tsaving preprocessed data path - %s" % data_path
print "\trating data path - %s" % path_rating
print "\tdocument data path - %s" % path_itemtext
print "\tmin_rating: %d\n\tmax_length_document: %d\n\tmax_df: %.1f\n\tvocab_size: %d\n\tsplit_ratio: %.1f" \
% (min_rating, max_length, max_df, vocab_size, split_ratio)
print "==========================================================================================="
R, D_all = data_factory.preprocess(
path_rating, path_itemtext, min_rating, max_length, max_df, vocab_size)
data_factory.save(aux_path, R, D_all)
data_factory.generate_train_valid_test_file_from_R(
data_path, R, split_ratio)
else:
res_dir = args.res_dir
emb_dim = args.emb_dim
pretrain_w2v = args.pretrain_w2v
dimension = args.dimension
lambda_u = args.lambda_u
lambda_v = args.lambda_v
max_iter = args.max_iter
num_kernel_per_ws = args.num_kernel_per_ws
give_item_weight = args.give_item_weight
if res_dir is None:
sys.exit("Argument missing - res_dir is required")
print "=================================Preprocess Option Setting================================="
print "\tsaving preprocessed aux path - %s" % aux_path
print "\tsaving preprocessed data path - %s" % data_path
print "\trating data path - %s" % path_rating
print "\tdocument data path - %s" % path_itemtext
print "\tmin_rating: %d\n\tmax_length_document: %d\n\tmax_df: %.1f\n\tvocab_size: %d\n\tsplit_ratio: %.1f" \
% (min_rating, max_length, max_df, vocab_size, split_ratio)
print "\tnumber of new itmes: %d" % new_item
print "==========================================================================================="
if new_item:
print "Under construction"
R_old, R_new, D_old, D_new = data_factory.preprocess_newitem(
path_rating, path_itemtext, min_rating, max_length, max_df,
vocab_size, new_item)
data_factory.save(aux_path, R_old, D_old, True, R_new, D_new)
data_factory.generate_train_valid_test_file_from_R(
data_path, R_old, split_ratio, R_new)
else:
R, D_all = data_factory.preprocess(path_rating, path_itemtext,
min_rating, max_length, max_df,
vocab_size)
data_factory.save(aux_path, R, D_all)
data_factory.generate_train_valid_test_file_from_R(
data_path, R, split_ratio)
else:
res_dir = args.res_dir
emb_dim = args.emb_dim
pretrain_w2v = args.pretrain_w2v
dimension = args.dimension
data_factory = Data_Factory()
if do_preprocess:
path_rating = args.raw_rating_data_path
min_rating = args.min_rating
split_ratio = args.split_ratio
print "=================================Preprocess Option Setting================================="
print "\tsaving preprocessed aux path - %s" % aux_path
print "\tsaving preprocessed data path - %s" % data_path
print "\trating data path - %s" % path_rating
print "\tmin_rating: %d\n\t split_ratio: %.1f" % (min_rating, split_ratio)
print "==========================================================================================="
R = data_factory.preprocess(path_rating, min_rating)
data_factory.save(aux_path, R)
data_factory.generate_train_valid_test_file_from_R(data_path, R,
split_ratio)
else:
methods = args.flag
dimension = args.dimension
lambda_u = args.lambda_u
lambda_v = args.lambda_v
lambda_p = args.lambda_p
lambda_q = args.lambda_q
max_iter = args.max_iter
momentum_flag = args.momentum_flag
if lambda_u is None:
sys.exit("Argument missing - lambda_u is required")