path # lines of code # active days days since first update days since last update # commits # contributors first updated last updated first contributor last contributor setup.py 92 44 2831 253 56 14 2018-07-19 2025-08-09 yevgeni@uber.com 40239280+arushi297@users.noreply.github.com setup.cfg 2 1 2789 2789 1 1 2018-08-30 2018-08-30 robbieg@uber.com robbieg@uber.com petastorm/tf_utils.py 180 21 2826 1640 22 10 2018-07-24 2021-10-22 yevgeni@uber.com gregor.ehrensperger@gmx.com petastorm/pyarrow_helpers/__init__.py 1 1 2716 2716 1 1 2018-11-11 2018-11-11 yevgeni@uber.com yevgeni@uber.com petastorm/pyarrow_helpers/batching_table_queue.py 30 1 2716 2716 1 1 2018-11-11 2018-11-11 yevgeni@uber.com yevgeni@uber.com petastorm/errors.py 1 1 2571 2571 1 1 2019-04-05 2019-04-05 yevgeni@uber.com yevgeni@uber.com petastorm/fs_utils.py 106 21 2826 1728 22 16 2018-07-24 2021-07-26 yevgeni@uber.com manjuransari143@gmail.com petastorm/hdfs/namenode.py 159 12 2826 1560 15 7 2018-07-24 2022-01-10 yevgeni@uber.com selitvin@users.noreply.github.com petastorm/hdfs/__init__.py 1 1 2826 2826 1 1 2018-07-24 2018-07-24 yevgeni@uber.com yevgeni@uber.com petastorm/__init__.py 4 91 2826 121 115 15 2018-07-24 2025-12-19 yevgeni@uber.com kashish@uber.com petastorm/cache.py 9 4 2826 2701 4 2 2018-07-24 2018-11-26 yevgeni@uber.com yevgeni@uber.com petastorm/transform.py 32 8 2668 2208 10 4 2018-12-29 2020-04-02 yevgeni@uber.com weichen.xu@databricks.com petastorm/unischema.py 266 37 2826 1725 41 10 2018-07-24 2021-07-29 yevgeni@uber.com selitvin@users.noreply.github.com petastorm/reader.py 381 72 2826 170 85 25 2018-07-24 2025-10-31 yevgeni@uber.com kashish@uber.com petastorm/arrow_reader_worker.py 225 24 2692 124 29 9 2018-12-05 2025-12-16 yevgeni@uber.com kashish@uber.com petastorm/utils.py 61 14 2826 1987 15 5 2018-07-24 2020-11-09 yevgeni@uber.com selitvin@users.noreply.github.com petastorm/ngram.py 105 10 2801 1959 15 6 2018-08-18 2020-12-07 kash@uber.com 44522052+ritwikbera@users.noreply.github.com petastorm/etl/legacy.py 36 3 2809 1726 3 2 2018-08-10 2021-07-28 selitvin@users.noreply.github.com selitvin@users.noreply.github.com petastorm/etl/__init__.py 21 4 2826 2701 4 3 2018-07-24 2018-11-26 yevgeni@uber.com yevgeni@uber.com petastorm/etl/metadata_util.py 45 6 2826 2649 8 5 2018-07-24 2019-01-17 yevgeni@uber.com kimham@kth.se petastorm/etl/rowgroup_indexers.py 73 5 2826 2801 5 4 2018-07-24 2018-08-18 yevgeni@uber.com m.eremeev@uber.com petastorm/etl/petastorm_generate_metadata.py 98 15 2806 2508 18 9 2018-08-13 2019-06-07 robbieg@uber.com dimitrov@uber.com petastorm/etl/rowgroup_indexing.py 71 14 2826 1987 15 7 2018-07-24 2020-11-09 yevgeni@uber.com selitvin@users.noreply.github.com petastorm/etl/dataset_metadata.py 201 37 2826 1819 40 14 2018-07-24 2021-04-26 yevgeni@uber.com tgaddair@gmail.com petastorm/py_dict_reader_worker.py 155 15 2692 1335 15 5 2018-12-05 2022-08-23 yevgeni@uber.com 74630762+chongxiaoc@users.noreply.github.com petastorm/generator.py 15 3 2826 2789 3 3 2018-07-24 2018-08-30 yevgeni@uber.com ocheng@uber.com petastorm/reader_impl/__init__.py 1 1 2802 2802 1 1 2018-08-17 2018-08-17 yevgeni@uber.com yevgeni@uber.com petastorm/reader_impl/pytorch_shuffling_buffer.py 123 4 2192 1363 4 3 2020-04-18 2022-07-26 felipe.such@uber.com 74630762+chongxiaoc@users.noreply.github.com petastorm/reader_impl/pickle_serializer.py 6 2 2755 1487 2 2 2018-10-03 2022-03-24 yevgeni@uber.com 54285210+rbetz@users.noreply.github.com petastorm/reader_impl/shuffling_buffer.py 75 6 2802 2445 6 3 2018-08-17 2019-08-09 yevgeni@uber.com yevgeni@uber.com petastorm/reader_impl/arrow_table_serializer.py 12 2 2692 1728 2 2 2018-12-05 2021-07-26 yevgeni@uber.com selitvin@users.noreply.github.com petastorm/weighted_sampling_reader.py 48 7 2775 1964 8 4 2018-09-13 2020-12-02 yevgeni@uber.com gueguenster@gmail.com petastorm/benchmark/cli.py 63 4 2768 1987 4 2 2018-09-20 2020-11-09 yevgeni@uber.com selitvin@users.noreply.github.com petastorm/benchmark/__init__.py 1 1 2768 2768 1 1 2018-09-20 2018-09-20 yevgeni@uber.com yevgeni@uber.com petastorm/benchmark/dummy_reader.py 56 1 2192 2192 1 1 2020-04-18 2020-04-18 felipe.such@uber.com felipe.such@uber.com petastorm/benchmark/throughput.py 124 10 2768 1987 10 6 2018-09-20 2020-11-09 yevgeni@uber.com selitvin@users.noreply.github.com petastorm/spark/__init__.py 2 3 2250 2231 4 2 2020-02-20 2020-03-10 liang.zhang@databricks.com weichen.xu@databricks.com petastorm/spark/spark_dataset_converter.py 403 27 2250 1175 39 6 2020-02-20 2023-01-30 liang.zhang@databricks.com weichen.xu@databricks.com petastorm/selectors.py 46 3 2826 2541 4 3 2018-07-24 2019-05-05 yevgeni@uber.com greg.arutiunian@ge.com petastorm/codecs.py 154 19 2826 2047 21 8 2018-07-24 2020-09-10 yevgeni@uber.com dmcguire81@gmail.com petastorm/predicates.py 93 7 2826 1466 7 5 2018-07-24 2022-04-14 yevgeni@uber.com tir.karthi@gmail.com petastorm/local_disk_cache.py 43 7 2826 170 7 6 2018-07-24 2025-10-31 yevgeni@uber.com kashish@uber.com petastorm/namedtuple_gt_255_fields.py 65 1 2579 2579 1 1 2019-03-28 2019-03-28 yevgeni@uber.com yevgeni@uber.com petastorm/pytorch.py 248 23 2803 1466 23 11 2018-08-16 2022-04-14 ocheng@uberatc.com tir.karthi@gmail.com petastorm/spark_utils.py 18 6 2826 2649 6 5 2018-07-24 2019-01-17 yevgeni@uber.com kimham@kth.se petastorm/workers_pool/__init__.py 3 3 2826 2701 3 2 2018-07-24 2018-11-26 yevgeni@uber.com yevgeni@uber.com petastorm/workers_pool/exec_in_new_process_entrypoint.py 18 1 1562 1562 1 1 2022-01-08 2022-01-08 selitvin@users.noreply.github.com selitvin@users.noreply.github.com petastorm/workers_pool/process_pool.py 214 22 2826 1395 26 8 2018-07-24 2022-06-24 yevgeni@uber.com farahani.mostafa@gmail.com petastorm/workers_pool/exec_in_new_process.py 18 9 2826 1562 9 4 2018-07-24 2022-01-08 yevgeni@uber.com selitvin@users.noreply.github.com petastorm/workers_pool/thread_pool.py 150 10 2826 253 11 6 2018-07-24 2025-08-09 yevgeni@uber.com 40239280+arushi297@users.noreply.github.com petastorm/workers_pool/dummy_pool.py 38 4 2826 2752 5 2 2018-07-24 2018-10-06 yevgeni@uber.com yevgeni@uber.com petastorm/workers_pool/worker_base.py 11 1 2826 2826 1 1 2018-07-24 2018-07-24 yevgeni@uber.com yevgeni@uber.com petastorm/workers_pool/ventilator.py 87 10 2826 253 10 7 2018-07-24 2025-08-09 yevgeni@uber.com 40239280+arushi297@users.noreply.github.com petastorm/tools/copy_dataset.py 77 4 2763 2508 6 4 2018-09-25 2019-06-07 yevgeni@uber.com dimitrov@uber.com petastorm/tools/__init__.py 1 1 2763 2763 1 1 2018-09-25 2018-09-25 yevgeni@uber.com yevgeni@uber.com petastorm/tools/spark_session_cli.py 28 1 2763 2763 1 1 2018-09-25 2018-09-25 yevgeni@uber.com yevgeni@uber.com