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.data_dir))
print("Implicit User Feedback: {}".format(args.implicit))
progress.section("Load Raw Data")
rating_matrix, timestamp_matrix = get_yelp_df(
args.data_dir + args.data_name,
sampling=True,
top_user_num=args.top_user_num,
top_item_num=args.top_item_num)
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)
import ipdb
ipdb.set_trace()
progress.section("Save NPZ")
save_numpy(rtrain, args.data_dir, "Rtrain")
save_numpy(rvalid, args.data_dir, "Rvalid")
save_numpy(rtest, args.data_dir, "Rtest")
save_numpy(rtime, args.data_dir, "Rtime")
save_array(nonzero_index, args.data_dir, "Index")
def main(args):
progress = WorkSplitter()
progress.section("Load Raw Data")
rating_matrix = load_pandas_without_names(
path=args.path,
name=args.name,
row_name='userId',
sep='\t',
col_name='trackId',
value_name='rating',
shape=args.shape,
names=['userId', 'trackId', 'rating'])
progress.section("Split CSR Matrices")
rtrain, rvalid, rtest, nonzero_index = split_seed_randomly(
rating_matrix=rating_matrix,
ratio=args.ratio,
threshold=80,
implicit=args.implicit,
sampling=True,
percentage=0.2)
print("Done splitting Yahoo dataset")
progress.section("Save NPZ")
save_numpy(rtrain, args.path, "Rtrain")
save_numpy(rvalid, args.path, "Rvalid")
save_numpy(rtest, args.path, "Rtest")
save_array(nonzero_index, args.path, "Index")
print("Done saving data for yahoo after splitting")
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")
def main(args):
progress = WorkSplitter()
progress.section("Load Raw Data")
#rating_matrix = load_pandas(path=args.path, name=args.name, shape=args.shape)
rating_matrix = load_yahoo(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, nonzero_index = time_ordered_split(rating_matrix=rating_matrix, ratio=args.ratio, implicit=args.implicit)
rtrain, rvalid, rtest, nonzero_index = split_seed_randomly(
rating_matrix=rating_matrix, ratio=args.ratio, implicit=args.implicit)
print("Done splitting Yahoo dataset")
progress.section("Save NPZ")
save_numpy(rtrain, args.path, "Rtrain")
save_numpy(rvalid, args.path, "Rvalid")
save_numpy(rtest, args.path, "Rtest")
save_array(nonzero_index, args.path, "Index")
print("Done saving data for yahoo after splitting")