this is my code on Kaggle:
from datasets import load_dataset
data = load_dataset('tsdocode/vi_alpaca_clean')
and this is the error I met:
---------------------------------------------------------------------------
ArrowInvalid Traceback (most recent call last)
File /opt/conda/lib/python3.10/site-packages/datasets/packaged_modules/json/json.py:122, in Json._generate_tables(self, files)
121 try:
--> 122 pa_table = paj.read_json(
123 io.BytesIO(batch), read_options=paj.ReadOptions(block_size=block_size)
124 )
125 break
File /opt/conda/lib/python3.10/site-packages/pyarrow/_json.pyx:259, in pyarrow._json.read_json()
File /opt/conda/lib/python3.10/site-packages/pyarrow/error.pxi:144, in pyarrow.lib.pyarrow_internal_check_status()
File /opt/conda/lib/python3.10/site-packages/pyarrow/error.pxi:100, in pyarrow.lib.check_status()
ArrowInvalid: JSON parse error: Column() changed from object to array in row 0
During handling of the above exception, another exception occurred:
AttributeError Traceback (most recent call last)
Cell In[2], line 2
1 from datasets import load_dataset
----> 2 data = load_dataset('tsdocode/vi_alpaca_clean')
File /opt/conda/lib/python3.10/site-packages/datasets/load.py:1691, in load_dataset(path, name, data_dir, data_files, split, cache_dir, features, download_config, download_mode, ignore_verifications, keep_in_memory, save_infos, revision, use_auth_token, task, streaming, **config_kwargs)
1688 try_from_hf_gcs = path not in _PACKAGED_DATASETS_MODULES
1690 # Download and prepare data
-> 1691 builder_instance.download_and_prepare(
1692 download_config=download_config,
1693 download_mode=download_mode,
1694 ignore_verifications=ignore_verifications,
1695 try_from_hf_gcs=try_from_hf_gcs,
1696 use_auth_token=use_auth_token,
1697 )
1699 # Build dataset for splits
1700 keep_in_memory = (
1701 keep_in_memory if keep_in_memory is not None else is_small_dataset(builder_instance.info.dataset_size)
1702 )
File /opt/conda/lib/python3.10/site-packages/datasets/builder.py:605, in DatasetBuilder.download_and_prepare(self, download_config, download_mode, ignore_verifications, try_from_hf_gcs, dl_manager, base_path, use_auth_token, **download_and_prepare_kwargs)
603 logger.warning("HF google storage unreachable. Downloading and preparing it from source")
604 if not downloaded_from_gcs:
--> 605 self._download_and_prepare(
606 dl_manager=dl_manager, verify_infos=verify_infos, **download_and_prepare_kwargs
607 )
608 # Sync info
609 self.info.dataset_size = sum(split.num_bytes for split in self.info.splits.values())
File /opt/conda/lib/python3.10/site-packages/datasets/builder.py:694, in DatasetBuilder._download_and_prepare(self, dl_manager, verify_infos, **prepare_split_kwargs)
690 split_dict.add(split_generator.split_info)
692 try:
693 # Prepare split will record examples associated to the split
--> 694 self._prepare_split(split_generator, **prepare_split_kwargs)
695 except OSError as e:
696 raise OSError(
697 "Cannot find data file. "
698 + (self.manual_download_instructions or "")
699 + "\nOriginal error:\n"
700 + str(e)
701 ) from None
File /opt/conda/lib/python3.10/site-packages/datasets/builder.py:1151, in ArrowBasedBuilder._prepare_split(self, split_generator)
1149 generator = self._generate_tables(**split_generator.gen_kwargs)
1150 with ArrowWriter(features=self.info.features, path=fpath) as writer:
-> 1151 for key, table in logging.tqdm(
1152 generator, unit=" tables", leave=False, disable=True # not logging.is_progress_bar_enabled()
1153 ):
1154 writer.write_table(table)
1155 num_examples, num_bytes = writer.finalize()
File /opt/conda/lib/python3.10/site-packages/tqdm/notebook.py:254, in tqdm_notebook.__iter__(self)
252 try:
253 it = super(tqdm_notebook, self).__iter__()
--> 254 for obj in it:
255 # return super(tqdm...) will not catch exception
256 yield obj
257 # NB: except ... [ as ...] breaks IPython async KeyboardInterrupt
File /opt/conda/lib/python3.10/site-packages/tqdm/std.py:1166, in tqdm.__iter__(self)
1163 # If the bar is disabled, then just walk the iterable
1164 # (note: keep this check outside the loop for performance)
1165 if self.disable:
-> 1166 for obj in iterable:
1167 yield obj
1168 return
File /opt/conda/lib/python3.10/site-packages/datasets/packaged_modules/json/json.py:150, in Json._generate_tables(self, files)
145 except json.JSONDecodeError:
146 raise e
147 raise ValueError(
148 f"Not able to read records in the JSON file at {file}. "
149 f"You should probably indicate the field of the JSON file containing your records. "
--> 150 f"This JSON file contain the following fields: {str(list(dataset.keys()))}. "
151 f"Select the correct one and provide it as `field='XXX'` to the dataset loading method. "
152 ) from None
153 # Uncomment for debugging (will print the Arrow table size and elements)
154 # logger.warning(f"pa_table: {pa_table} num rows: {pa_table.num_rows}")
155 # logger.warning('\n'.join(str(pa_table.slice(i, 1).to_pydict()) for i in range(pa_table.num_rows)))
156 yield (file_idx, batch_idx), self._cast_classlabels(pa_table)
AttributeError: 'list' object has no attribute 'keys'
It seems to me that the dataset has been downloaded
