ModuleNotFoundError: No module named 'pkg_resources._vendor' #274
Description
Although I did install all the packages as instructed in Setup . But when I do run the cell code in Distributed Data Processing, I get the following error.
# Data ingestion
ds = ray.data.read_csv(DATASET_LOC)
ds = ds.random_shuffle(seed=1234)
ds.take(1)---------------------------------------------------------------------------
RayTaskError(ModuleNotFoundError) Traceback (most recent call last)
Cell In[40], line 2
1 # Data ingestion
----> 2 ds = ray.data.read_csv(DATASET_LOC)
3 ds = ds.random_shuffle(seed=1234)
4 ds.take(1)
File d:\madewithml\venv\lib\site-packages\ray\data\read_api.py:1208, in read_csv(paths, filesystem, parallelism, ray_remote_args, arrow_open_stream_args, meta_provider, partition_filter, partitioning, ignore_missing_paths, **arrow_csv_args)
1206 if meta_provider is None:
1207 meta_provider = get_generic_metadata_provider(CSVDatasource._FILE_EXTENSION)
-> 1208 return read_datasource(
1209 CSVDatasource(),
1210 parallelism=parallelism,
1211 paths=paths,
1212 filesystem=filesystem,
1213 ray_remote_args=ray_remote_args,
1214 open_stream_args=arrow_open_stream_args,
1215 meta_provider=meta_provider,
1216 partition_filter=partition_filter,
1217 partitioning=partitioning,
1218 ignore_missing_paths=ignore_missing_paths,
1219 **arrow_csv_args,
1220 )
File d:\madewithml\venv\lib\site-packages\ray\_private\auto_init_hook.py:24, in wrap_auto_init.<locals>.auto_init_wrapper(*args, **kwargs)
21 @wraps(fn)
22 def auto_init_wrapper(*args, **kwargs):
23 auto_init_ray()
---> 24 return fn(*args, **kwargs)
File d:\madewithml\venv\lib\site-packages\ray\data\read_api.py:371, in read_datasource(datasource, parallelism, ray_remote_args, **read_args)
363 scheduling_strategy = NodeAffinitySchedulingStrategy(
364 ray.get_runtime_context().get_node_id(),
365 soft=False,
366 )
367 get_reader = cached_remote_fn(
368 _get_reader, retry_exceptions=False, num_cpus=0
369 ).options(scheduling_strategy=scheduling_strategy)
--> 371 (requested_parallelism, min_safe_parallelism, inmemory_size, reader,) = ray.get(
372 get_reader.remote(
373 datasource,
374 ctx,
375 cur_pg,
376 parallelism,
377 local_uri,
378 _wrap_arrow_serialization_workaround(read_args),
379 )
380 )
382 # TODO(hchen/chengsu): Remove the duplicated get_read_tasks call here after
383 # removing LazyBlockList code path.
384 read_tasks = reader.get_read_tasks(requested_parallelism)
File d:\madewithml\venv\lib\site-packages\ray\_private\auto_init_hook.py:24, in wrap_auto_init.<locals>.auto_init_wrapper(*args, **kwargs)
21 @wraps(fn)
22 def auto_init_wrapper(*args, **kwargs):
23 auto_init_ray()
---> 24 return fn(*args, **kwargs)
File d:\madewithml\venv\lib\site-packages\ray\_private\client_mode_hook.py:103, in client_mode_hook.<locals>.wrapper(*args, **kwargs)
101 if func.__name__ != "init" or is_client_mode_enabled_by_default:
102 return getattr(ray, func.__name__)(*args, **kwargs)
--> 103 return func(*args, **kwargs)
File d:\madewithml\venv\lib\site-packages\ray\_private\worker.py:2547, in get(object_refs, timeout)
2545 worker.core_worker.dump_object_store_memory_usage()
2546 if isinstance(value, RayTaskError):
-> 2547 raise value.as_instanceof_cause()
2548 else:
2549 raise value
RayTaskError(ModuleNotFoundError): ray::_get_reader() (pid=17388, ip=127.0.0.1)
File "python\ray\_raylet.pyx", line 1616, in ray._raylet.execute_task
File "d:\madewithml\venv\lib\site-packages\ray\data\read_api.py", line 2348, in _get_reader
reader = ds.create_reader(**kwargs)
File "d:\madewithml\venv\lib\site-packages\ray\data\datasource\file_based_datasource.py", line 256, in create_reader
return _FileBasedDatasourceReader(self, **kwargs)
File "d:\madewithml\venv\lib\site-packages\ray\data\datasource\file_based_datasource.py", line 476, in __init__
_check_pyarrow_version()
File "d:\madewithml\venv\lib\site-packages\ray\data\_internal\util.py", line 78, in _check_pyarrow_version
from pkg_resources._vendor.packaging.version import parse as parse_version
ModuleNotFoundError: No module named 'pkg_resources._vendor'