Skip to content

Commit

Permalink
Remove prints
Browse files Browse the repository at this point in the history
  • Loading branch information
XiaohanZhangCMU committed May 24, 2024
1 parent 7e3fcfb commit de033d3
Show file tree
Hide file tree
Showing 3 changed files with 1 addition and 6 deletions.
2 changes: 0 additions & 2 deletions streaming/base/dataset.py
Original file line number Diff line number Diff line change
Expand Up @@ -519,8 +519,6 @@ def __init__(self,

# Build the shard index (for partitioning and mapping samples to shards).
self.samples_per_shard = np.array([shard.samples for shard in self.shards], np.int64)
print('I am here 5.1, samples_per_shard = ')
print(self.samples_per_shard)
self.sample_offset_per_shard = self.samples_per_shard.cumsum() - self.samples_per_shard
self.spanner = Spanner(self.samples_per_shard)

Expand Down
2 changes: 0 additions & 2 deletions streaming/base/stream.py
Original file line number Diff line number Diff line change
Expand Up @@ -567,8 +567,6 @@ def get_shards(self, world: World, allow_unsafe_types: bool) -> List[Reader]:
from streaming.base.converters import infer_dataframe_schema

w = WorkspaceClient()
##cluster_id = "0201-234512-tcp9nfat" # e2-dogfood
#cluster_id = "0523-224100-tid6mais" # db-force-one

sparkSession = DatabricksSession.builder.remote(
host=w.config.host,
Expand Down
3 changes: 1 addition & 2 deletions tests/test_streaming_remote.py
Original file line number Diff line number Diff line change
Expand Up @@ -79,8 +79,7 @@ def get_dataset(name: str,
local = d['local']
remote = d['remote']
kwargs = {**d['kwargs'], **other_kwargs}
dataset = d['class'](d['cluster_id'],
local=local,
dataset = d['class'](local=local,
remote=remote,
split=split,
shuffle=shuffle,
Expand Down

0 comments on commit de033d3

Please sign in to comment.