mirror of
https://github.com/deepseek-ai/smallpond
synced 2025-06-26 18:27:45 +00:00
132 lines
4.2 KiB
ReStructuredText
132 lines
4.2 KiB
ReStructuredText
smallpond.execution.task.PandasBatchTask
|
|
========================================
|
|
|
|
.. currentmodule:: smallpond.execution.task
|
|
|
|
.. autoclass:: PandasBatchTask
|
|
|
|
|
|
.. automethod:: __init__
|
|
|
|
|
|
.. rubric:: Methods
|
|
|
|
.. autosummary::
|
|
|
|
~PandasBatchTask.__init__
|
|
~PandasBatchTask.add_elapsed_time
|
|
~PandasBatchTask.adjust_row_group_size
|
|
~PandasBatchTask.clean_complex_attrs
|
|
~PandasBatchTask.clean_output
|
|
~PandasBatchTask.cleanup
|
|
~PandasBatchTask.compute_avg_row_size
|
|
~PandasBatchTask.create_input_views
|
|
~PandasBatchTask.dump
|
|
~PandasBatchTask.dump_output
|
|
~PandasBatchTask.exec
|
|
~PandasBatchTask.exec_query
|
|
~PandasBatchTask.finalize
|
|
~PandasBatchTask.get_partition_info
|
|
~PandasBatchTask.initialize
|
|
~PandasBatchTask.inject_fault
|
|
~PandasBatchTask.merge_metrics
|
|
~PandasBatchTask.oom
|
|
~PandasBatchTask.parquet_kv_metadata_bytes
|
|
~PandasBatchTask.parquet_kv_metadata_str
|
|
~PandasBatchTask.prepare_connection
|
|
~PandasBatchTask.process
|
|
~PandasBatchTask.random_float
|
|
~PandasBatchTask.random_uint32
|
|
~PandasBatchTask.restore_input_state
|
|
~PandasBatchTask.run
|
|
~PandasBatchTask.run_on_ray
|
|
~PandasBatchTask.set_memory_limit
|
|
|
|
|
|
|
|
|
|
|
|
.. rubric:: Attributes
|
|
|
|
.. autosummary::
|
|
|
|
~PandasBatchTask.process_func
|
|
~PandasBatchTask.background_io_thread
|
|
~PandasBatchTask.streaming_batch_size
|
|
~PandasBatchTask.streaming_batch_count
|
|
~PandasBatchTask.parquet_row_group_size
|
|
~PandasBatchTask.parquet_row_group_bytes
|
|
~PandasBatchTask.parquet_dictionary_encoding
|
|
~PandasBatchTask.parquet_compression
|
|
~PandasBatchTask.parquet_compression_level
|
|
~PandasBatchTask.secs_checkpoint_interval
|
|
~PandasBatchTask.allow_speculative_exec
|
|
~PandasBatchTask.any_input_empty
|
|
~PandasBatchTask.compression_level_str
|
|
~PandasBatchTask.compression_options
|
|
~PandasBatchTask.compression_type_str
|
|
~PandasBatchTask.cpu_limit
|
|
~PandasBatchTask.cpu_overcommit_ratio
|
|
~PandasBatchTask.ctx
|
|
~PandasBatchTask.dataset
|
|
~PandasBatchTask.default_output_name
|
|
~PandasBatchTask.elapsed_time
|
|
~PandasBatchTask.enable_temp_directory
|
|
~PandasBatchTask.exception
|
|
~PandasBatchTask.exec_cq
|
|
~PandasBatchTask.exec_id
|
|
~PandasBatchTask.exec_on_scheduler
|
|
~PandasBatchTask.fail_count
|
|
~PandasBatchTask.final_output_abspath
|
|
~PandasBatchTask.finish_time
|
|
~PandasBatchTask.gpu_limit
|
|
~PandasBatchTask.id
|
|
~PandasBatchTask.input_datasets
|
|
~PandasBatchTask.input_deps
|
|
~PandasBatchTask.input_udfs
|
|
~PandasBatchTask.input_view_index
|
|
~PandasBatchTask.key
|
|
~PandasBatchTask.local_gpu
|
|
~PandasBatchTask.local_gpu_ranks
|
|
~PandasBatchTask.local_rank
|
|
~PandasBatchTask.location
|
|
~PandasBatchTask.max_batch_size
|
|
~PandasBatchTask.memory_limit
|
|
~PandasBatchTask.memory_overcommit_ratio
|
|
~PandasBatchTask.node_id
|
|
~PandasBatchTask.numa_node
|
|
~PandasBatchTask.numpy_random_gen
|
|
~PandasBatchTask.output
|
|
~PandasBatchTask.output_deps
|
|
~PandasBatchTask.output_dirname
|
|
~PandasBatchTask.output_filename
|
|
~PandasBatchTask.output_name
|
|
~PandasBatchTask.output_root
|
|
~PandasBatchTask.partition_dims
|
|
~PandasBatchTask.partition_infos
|
|
~PandasBatchTask.partition_infos_as_dict
|
|
~PandasBatchTask.perf_metrics
|
|
~PandasBatchTask.perf_profile
|
|
~PandasBatchTask.python_random_gen
|
|
~PandasBatchTask.query_udfs
|
|
~PandasBatchTask.rand_seed_float
|
|
~PandasBatchTask.rand_seed_uint32
|
|
~PandasBatchTask.random_seed_bytes
|
|
~PandasBatchTask.ray_dataset_path
|
|
~PandasBatchTask.ray_marker_path
|
|
~PandasBatchTask.retry_count
|
|
~PandasBatchTask.runtime_id
|
|
~PandasBatchTask.runtime_output_abspath
|
|
~PandasBatchTask.runtime_state
|
|
~PandasBatchTask.sched_epoch
|
|
~PandasBatchTask.self_contained_output
|
|
~PandasBatchTask.skip_when_any_input_empty
|
|
~PandasBatchTask.staging_root
|
|
~PandasBatchTask.start_time
|
|
~PandasBatchTask.status
|
|
~PandasBatchTask.temp_abspath
|
|
~PandasBatchTask.temp_output
|
|
~PandasBatchTask.udfs
|
|
~PandasBatchTask.uniform_failure_prob
|
|
|
|
|