def create_fold_column_if_not_exist(h2o_base_table: h2o.H2OFrame,
fold_column: str,
nfolds: int = None) -> h2o.H2OFrame:
if fold_column and fold_column not in h2o_base_table.col_names:
h2o_fold_col = h2o_base_table.kfold_column(n_folds=nfolds)
h2o_fold_col.set_names([fold_column])
h2o_base_table = h2o_base_table.cbind(h2o_fold_col)
return h2o_base_table
def add_unique_row_id(h2o_base_table: h2o.H2OFrame):
num_rows = h2o_base_table.shape[0]
ids = []
for id in range(0, num_rows):
ids.append(id)
h2o_id_frame = h2o.H2OFrame(ids)
return h2o_base_table.cbind(h2o_id_frame.set_names(['row_id']))
