Skip to content

Commit d5650b3

Browse files
committed
add sample
1 parent 91d6f0c commit d5650b3

File tree

1 file changed

+5
-0
lines changed

1 file changed

+5
-0
lines changed

paddlemix/datacopilot/core/dataset.py

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -122,6 +122,11 @@ def shuffle(self, seed: Optional[int]=None) -> 'MMDataset':
122122
random.shuffle(self._items)
123123
return self
124124

125+
def sample(self, k: int) -> 'MMDataset':
126+
indices = random.sample(range(len(self)), k)
127+
items = [self.items[i] for i in indices]
128+
return MMDataset(items)
129+
125130
@classmethod
126131
def from_json(cls, path: str, schema: SCHEMA=SCHEMA.MM) -> 'MMDataset':
127132
with open(path, 'r') as f:

0 commit comments

Comments
 (0)