def main(args):
progress = WorkSplitter()
raw = pd.read_csv(args.path + args.name,
names=['user', 'item', 'rating', 'timestamp'])
raw['userID'] = pd.factorize(raw.user)[0]
raw['itemID'] = pd.factorize(raw.item)[0]
progress.section("Load Raw Data")
rating_matrix = getSparseMatrix(raw,
row_name='userID',
col_name='itemID',
value_name='rating')
timestamp_matrix = getSparseMatrix(raw,
row_name='userID',
col_name='itemID',
value_name='timestamp')
progress.section("Split CSR Matrices")
rtrain, rvalid, rtest, nonzero_index, rtime = time_ordered_split(
rating_matrix=rating_matrix,
timestamp_matrix=timestamp_matrix,
ratio=args.ratio,
implicit=args.implicit)
progress.section("Save NPZ")
save_numpy(rtrain, args.path, "Rtrain")
save_numpy(rvalid, args.path, "Rvalid")
save_numpy(rtest, args.path, "Rtest")
save_numpy(rtime, args.path, "Rtime")
save_array(nonzero_index, args.path, "Index")
def main(args):
progress = WorkSplitter()
progress.section("Load Raw Data")
rating_matrix = load_pandas(row_name='userId',
col_name='itemId',
value_name=None,
path=args.path,
name=args.name,
shape=args.shape)
timestamp_matrix = load_pandas(row_name='userId',
col_name='itemId',
value_name='Timestamp',
path=args.path,
name=args.name,
shape=args.shape)
progress.section("Split CSR Matrices")
rtrain, rvalid, rtest, nonzero_index, rtime = time_ordered_split(
rating_matrix=rating_matrix,
timestamp_matrix=timestamp_matrix,
ratio=args.ratio,
implicit=args.implicit,
sampling=True,
percentage=0.2)
progress.section("Save NPZ")
save_numpy(rtrain, args.path, "Rtrain")
save_numpy(rvalid, args.path, "Rvalid")
save_numpy(rtest, args.path, "Rtest")
save_numpy(rtime, args.path, "Rtime")
save_array(nonzero_index, args.path, "Index")
def main(args):
progress = WorkSplitter()
progress.section("Parameter Setting")
print("Data Path: {}".format(args.path))
print("Validation: {}".format(args.validation))
print("Implicit: {}".format(args.implicit))
progress.section("Load Raw Data")
rating_matrix = load_pandas(path=args.path,
name=args.name,
shape=args.shape)
timestamp_matrix = load_pandas(path=args.path,
value_name='timestamp',
name=args.name,
shape=args.shape)
progress.section("Split CSR Matrices")
rtrain, rvalid, rtest, _, _, rtime = split_user_randomly(
rating_matrix=rating_matrix,
timestamp_matrix=timestamp_matrix,
ratio=args.split_user_ratio,
implicit=args.implicit)
if args.validation:
rtrain, rvalid, _, _, _ = time_ordered_split(
rating_matrix=rtrain,
timestamp_matrix=rtime,
ratio=args.split_train_valid_ratio,
implicit=False,
remove_empty=False)
ractive, rtest, _, _, _ = time_ordered_split(
rating_matrix=rtest,
timestamp_matrix=rtime,
ratio=args.split_active_test_ratio,
implicit=False,
remove_empty=False)
progress.section("Save NPZ")
save_numpy(rtrain, args.path, "Rtrain")
save_numpy(rvalid, args.path, "Rvalid")
save_numpy(ractive, args.path, "Ractive")
save_numpy(rtest, args.path, "Rtest")
save_numpy(rtime, args.path, "Rtime")
def main(args):
progress = WorkSplitter()
progress.section("Load Raw Data")
rating_matrix, timestamp_matrix = load_netflix(path=args.folder, shape=args.shape)
progress.section("Split CSR Matrices")
rtrain, rvalid, rtest, nonzero_index, rtime = time_ordered_split(rating_matrix=rating_matrix,
timestamp_matrix=timestamp_matrix,
ratio=args.ratio, implicit=args.implicit)
progress.section("Save NPZ")
save_numpy(rtrain, args.path, "Rtrain")
save_numpy(rvalid, args.path, "Rvalid")
save_numpy(rtest, args.path, "Rtest")
save_numpy(rtime, args.path, "Rtime")
save_array(nonzero_index, args.path, "Index")