Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/deepseek-ai/smallpond
/ functions
Functions
992 in github.com/deepseek-ai/smallpond
⨍
Functions
992
◇
Types & classes
154
↳
Endpoints
2
Method
test_pandas_task
(self)
tests/test_execution.py:354
Function
test_parquet
(sp: Session)
tests/test_dataframe.py:38
Method
test_parquet_batch_reader
(self)
tests/test_arrow.py:90
Method
test_parquet_file_created_by_pandas
(self)
tests/test_dataset.py:19
Method
test_partial_process_func
(self)
tests/test_execution.py:852
Function
test_partial_sql
(sp: Session)
tests/test_dataframe.py:153
Function
test_partition_by
(sp: Session)
tests/test_dataframe.py:112
Method
test_partition_by_files
(self)
tests/test_dataset.py:75
Function
test_partition_by_hash
(sp: Session)
tests/test_dataframe.py:128
Function
test_partition_by_key_out_of_range
(sp: Session)
tests/test_dataframe.py:118
Method
test_partition_by_rows
(self)
tests/test_dataset.py:93
Method
test_partition_dims_not_compatible
(self)
tests/test_logical.py:52
Method
test_partition_info_in_sql_query
User can refer to the partition info in the SQL query.
tests/test_partition.py:643
Method
test_paths_with_char_ranges
(self)
tests/test_dataset.py:118
Method
test_pickle_runtime_ctx
(self)
tests/test_filesystem.py:11
Method
test_pickle_trace
(self)
tests/test_filesystem.py:18
Method
test_projection_task
(self)
tests/test_execution.py:451
Method
test_python_node_with_process_method
(self)
tests/test_execution.py:593
Function
test_random_shuffle
(sp: Session)
tests/test_dataframe.py:95
Method
test_read_write_deltalake
(self)
tests/test_deltalake.py:14
Method
test_resolved_many_paths
(self)
tests/test_dataset.py:111
Method
test_run_on_remote_executors
(self)
tests/test_driver.py:33
Method
test_shuffle_data
(self)
tests/test_plan.py:44
Method
test_shuffle_mock_urls
(self)
tests/test_plan.py:34
Function
test_shutdown_cleanup
(sp: Session)
tests/test_session.py:6
Function
test_shutdown_no_cleanup_on_failure
(sp: Session)
tests/test_session.py:32
Method
test_sort_mock_urls
(self)
tests/test_plan.py:15
Method
test_sort_mock_urls_external_output_path
(self)
tests/test_plan.py:25
Function
test_sort_mock_urls_v2
(sp: Session)
tests/test_plan.py:67
Method
test_speculative_scheduling
(self)
tests/test_scheduler.py:149
Method
test_split_into_cols
(self, data: st.data)
tests/test_common.py:43
Method
test_split_into_cols_bench
(self)
tests/test_common.py:68
Method
test_split_into_rows
(self, data: st.data)
tests/test_common.py:32
Method
test_split_into_rows_bench
(self)
tests/test_common.py:61
Method
test_sql_batched_processing
(self)
tests/test_execution.py:691
Method
test_sql_engine_oom
(self)
tests/test_execution.py:605
Method
test_standalone_mode
(self)
tests/test_scheduler.py:105
Method
test_standalone_mode
(self)
tests/test_driver.py:26
Method
test_stop_executor_on_failure
(self)
tests/test_scheduler.py:167
Method
test_table_to_batches
(self)
tests/test_arrow.py:114
Function
test_take
(sp: Session)
tests/test_dataframe.py:43
Method
test_task_crash_as_oom
(self)
tests/test_execution.py:651
Method
test_temp_outputs_in_final_results
(self)
tests/test_execution.py:732
Method
test_to_arrow_table_batch_reader
(self)
tests/test_dataset.py:128
Function
test_unpicklable_task_exception
(sp: Session)
tests/test_dataframe.py:188
Method
test_urls_sort_benchmark
(self)
tests/test_bench.py:27
Method
test_user_defined_partition
(self)
tests/test_partition.py:575
Method
test_user_partitioned_data_source
(self)
tests/test_partition.py:605
Method
test_variable_length_input_datasets
(self)
tests/test_execution.py:402
Method
to_arrow_table
( self, max_workers=16, filesystem: fsspec.AbstractFileSystem = None, conn: du
smallpond/logical/dataset.py:1037
Method
to_batch_reader
( self, batch_size=DEFAULT_BATCH_SIZE, filesystem: fsspec.AbstractFileSystem = None,
smallpond/logical/dataset.py:430
Method
to_batch_reader
( self, batch_size=DEFAULT_BATCH_SIZE, filesystem: fsspec.AbstractFileSystem = None,
smallpond/logical/dataset.py:1045
Method
to_batch_reader
( self, batch_size=DEFAULT_BATCH_SIZE, filesystem: fsspec.AbstractFileSystem = None,
smallpond/logical/dataset.py:1083
Method
to_duckdb_type
(self)
smallpond/logical/udf.py:111
Method
to_duckdb_type
(self)
smallpond/logical/udf.py:125
Method
to_duckdb_type
(self)
smallpond/logical/udf.py:140
Method
to_duckdb_type
(self)
smallpond/logical/udf.py:152
Method
to_pandas
(self)
smallpond/logical/dataset.py:1072
Method
to_str
(node: Node, depth: int = 0)
smallpond/logical/node.py:2098
Method
to_str
(task: Task, depth: int = 0)
smallpond/execution/task.py:3527
Method
total_memory
(self)
smallpond/execution/task.py:280
Function
udf
A decorator to define a Python UDF. Examples -------- ``` @udf(params=[UDFType.INTEGER, UDFType.INTEGER], return_type=UDFType.IN
smallpond/logical/udf.py:246
Method
udfs
(self)
smallpond/logical/dataset.py:123
Method
udfs
(self)
smallpond/logical/dataset.py:400
Method
udfs
(self)
smallpond/execution/task.py:1224
Method
uniform_failure_prob
(self)
smallpond/execution/task.py:863
Method
union_by_name
Whether to unify the columns of different files by name.
smallpond/logical/dataset.py:116
Function
urls_sort_benchmark_v2
( sp: Session, input_paths: List[str], output_path: str, num_data_partitions: int, num_has
benchmarks/urls_sort_benchmark.py:73
Method
usable_cpu_count
(self)
smallpond/execution/task.py:289
Method
usable_gpu_count
(self)
smallpond/execution/task.py:310
Method
usable_memory_size
(self)
smallpond/execution/task.py:293
Function
validate_records
( runtime_ctx: RuntimeContext, input_datasets: List[DataSet], output_path: str )
benchmarks/gray_sort_benchmark.py:167
Function
validate_summary
( runtime_ctx: RuntimeContext, input_datasets: List[DataSet], output_path: str )
benchmarks/gray_sort_benchmark.py:188
Method
visit_arrow_compute_node
(self, node: ArrowComputeNode, depth: int)
smallpond/logical/planner.py:306
Method
visit_arrow_stream_node
(self, node: ArrowStreamNode, depth: int)
smallpond/logical/planner.py:312
Method
visit_consolidate_node
(self, node: ConsolidateNode, depth: int)
smallpond/logical/planner.py:148
Method
visit_data_sink_node
(self, node: DataSinkNode, depth: int)
smallpond/logical/planner.py:126
Method
visit_data_source_node
(self, node: DataSourceNode, depth: int)
smallpond/logical/planner.py:122
Method
visit_limit_node
(self, node: LimitNode, depth: int)
smallpond/logical/planner.py:333
Method
visit_partition_node
(self, node: PartitionNode, depth: int)
smallpond/logical/planner.py:177
Method
visit_projection_node
(self, node: ProjectionNode, depth: int)
smallpond/logical/planner.py:324
Method
visit_python_script_node
(self, node: PythonScriptNode, depth: int)
smallpond/logical/planner.py:300
Method
visit_query_engine_node
(self, node: SqlEngineNode, depth: int)
smallpond/logical/planner.py:318
Method
visit_query_engine_node
(self, node: SqlEngineNode, depth: int)
smallpond/logical/optimizer.py:33
Method
visit_root_node
(self, node: RootNode, depth: int)
smallpond/logical/planner.py:132
Method
visit_union_node
(self, node: UnionNode, depth: int)
smallpond/logical/planner.py:138
Method
working
(self)
smallpond/execution/scheduler.py:127
Method
working_executors
(self)
smallpond/execution/scheduler.py:536
Method
wrapper
(self: Node, *args, **kwargs)
smallpond/logical/node.py:260
Method
write_buffer_size
(self)
smallpond/execution/task.py:2818
Method
write_partition_data
( conn: duckdb.DuckDBPyConnection, partition_batch: List[Tuple[int, str]] )
smallpond/execution/task.py:3121
Method
write_partition_data
( partition_batch: List[Tuple[int, polars.DataFrame]], )
smallpond/execution/task.py:3231
← previous
901–992 of 992, ranked by callers