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
numa_node_count
(self)
smallpond/execution/task.py:257
Method
numpy_random_gen
(self)
smallpond/execution/task.py:841
Method
oneline_query
(self)
smallpond/logical/node.py:1139
Method
oneline_query
(self)
smallpond/execution/task.py:2610
Method
output
(self)
smallpond/execution/task.py:780
Method
output_dir
(self)
tests/test_fabric.py:75
Method
output_dirname
(self)
smallpond/execution/task.py:735
Method
output_filename
(self)
smallpond/execution/task.py:730
Method
output_root_abspath
(self)
tests/test_fabric.py:79
Function
overall_stats
( ctx, inp, sql_per_part, sql_on_merged, output_name, output_dir=None, cpu_limit=2
smallpond/utility.py:15
Method
parse_partition_key
(key: str)
smallpond/logical/dataset.py:873
Function
parse_url
( runtime_ctx: RuntimeContext, input_tables: List[arrow.Table] )
tests/test_execution.py:194
Method
partition
(self, runtime_ctx: RuntimeContext, dataset: DataSet)
smallpond/logical/node.py:1437
Method
partition
(self, runtime_ctx: RuntimeContext, dataset: DataSet)
smallpond/logical/node.py:1459
Method
partition
(self, batch_index: int, input_dataset: ParquetDataSet)
smallpond/execution/task.py:3031
Method
partition
(self, batch_index: int, input_dataset: ParquetDataSet)
smallpond/execution/task.py:3198
Method
partition
(self, runtime_ctx: RuntimeContext, dataset: DataSet)
tests/test_partition.py:33
Method
partition_by_files
( self, npartition: int, random_shuffle: bool = False )
smallpond/logical/dataset.py:798
Method
partition_dims
(self)
smallpond/execution/task.py:704
Method
partition_infos
(self)
smallpond/execution/task.py:673
Method
partition_infos_as_dict
(self)
smallpond/execution/task.py:677
Method
partition_query
(self)
smallpond/execution/task.py:3010
Method
pending_nontrivial_tasks
(self)
smallpond/execution/scheduler.py:491
Method
physical_cpu_count
(self)
smallpond/execution/task.py:266
Method
pristine_attrs_dict
(task: Task)
smallpond/execution/scheduler.py:807
Method
process
( self, runtime_ctx: RuntimeContext, input_datasets: List[DataSet], output_pat
smallpond/contrib/warc.py:57
Method
process
( self, runtime_ctx: RuntimeContext, input_readers: List[arrow.RecordBatchReader] )
smallpond/contrib/warc.py:125
Method
process
( self, runtime_ctx: RuntimeContext, input_datasets: List[DataSet], output_pat
smallpond/contrib/log_dataset.py:16
Method
process
( self, runtime_ctx: RuntimeContext, input_tables: List[arrow.Table] )
smallpond/contrib/copy_table.py:11
Method
process
( self, runtime_ctx: RuntimeContext, input_readers: List[arrow.RecordBatchReader] )
smallpond/contrib/copy_table.py:19
Method
process
Put user-defined code here. Parameters ---------- runtime_ctx The runtime context, which defines a few g
smallpond/logical/node.py:550
Method
process
Put user-defined code here. Parameters ---------- runtime_ctx The runtime context, which defines a few g
smallpond/logical/node.py:711
Method
process
Put user-defined code here. Parameters ---------- runtime_ctx The runtime context, which defines a few g
smallpond/logical/node.py:893
Method
process
( self, runtime_ctx: RuntimeContext, input_tables: List[arrow.Table] )
smallpond/logical/node.py:921
Method
process
( self, runtime_ctx: RuntimeContext, input_dfs: List[pd.DataFrame] )
smallpond/logical/node.py:935
Method
process
( self, runtime_ctx: RuntimeContext, input_dfs: List[pd.DataFrame] )
smallpond/logical/node.py:949
Method
process
( self, runtime_ctx: RuntimeContext, input_datasets: List[DataSet], output_pat
tests/test_scheduler.py:31
Method
process
( self, runtime_ctx: RuntimeContext, input_datasets: List[DataSet], output_pat
tests/test_execution.py:66
Method
process
( self, runtime_ctx: RuntimeContext, input_datasets: List[DataSet], output_pat
tests/test_execution.py:92
Method
process
( self, runtime_ctx: RuntimeContext, input_tables: List[arrow.Table] )
tests/test_execution.py:108
Method
process
( self, runtime_ctx: RuntimeContext, input_readers: List[arrow.RecordBatchReader] )
tests/test_execution.py:120
Method
process
( self, runtime_ctx: RuntimeContext, input_tables: List[arrow.Table] )
examples/sort_mock_urls.py:23
Method
process_work
(item: WorkItem, cq: WorkQueue)
smallpond/execution/executor.py:135
Method
progress
(self)
smallpond/execution/scheduler.py:455
Method
python_random_gen
(self)
smallpond/execution/task.py:849
Method
rand_seed_float
(self)
smallpond/execution/task.py:1210
Method
rand_seed_uint32
(self)
smallpond/execution/task.py:1214
Method
random_seed_bytes
(self)
smallpond/execution/task.py:835
Function
ray_address
A global Ray instance for all tests
tests/conftest.py:10
Method
ray_dataset_path
The path of a pickle file that contains the output dataset of the task. If this file exists, the task is considered finished.
smallpond/execution/task.py:824
Method
ray_log_path
(self)
smallpond/execution/task.py:245
Method
ray_marker_path
The path of an empty file that is used to determine if the task has been started. Only used by the ray executor.
smallpond/execution/task.py:814
Method
read_json
Create a DataFrame from JSON files.
smallpond/dataframe.py:64
Method
read_parquet_file
(path)
tests/test_fabric.py:270
Function
read_parquet_files_into_table
( paths_or_ranges: Union[List[str], List[RowRange]], columns: List[str] = None, filesystem: fsspec
smallpond/io/arrow.py:296
Method
recompute
Always recompute the data regardless of whether it's already computed. Examples -------- Modify the code as follows
smallpond/dataframe.py:303
Method
remote_executors
(self)
smallpond/execution/scheduler.py:522
Method
reset
NOTE: all row ranges will be cleared. DO NOT call this if you want to keep partial files.
smallpond/logical/dataset.py:629
Method
resolve_row_range
(path: str)
smallpond/logical/dataset.py:654
Method
resolved_paths
An ordered list of absolute paths of files. File patterns are expanded to absolute paths. Example:: >>> DataSet(['da
smallpond/logical/dataset.py:190
Method
resolved_row_ranges
Return row ranges for each parquet file.
smallpond/logical/dataset.py:645
Method
resource_low
(self)
smallpond/execution/scheduler.py:123
Function
return_fake_gpus
(count: int = 8)
tests/test_execution.py:223
Method
run
(self)
smallpond/execution/task.py:485
Method
run
(self)
smallpond/execution/task.py:1373
Method
run
(self)
smallpond/execution/task.py:1397
Method
run
(self)
smallpond/execution/task.py:1442
Method
run
(self)
smallpond/execution/task.py:1594
Method
run
(self)
smallpond/execution/task.py:1630
Method
run
(self)
smallpond/execution/task.py:1663
Method
run
(self)
smallpond/execution/task.py:1712
Method
run
(self)
smallpond/execution/task.py:1759
Method
run
(self)
smallpond/execution/task.py:1801
Method
run
(self)
smallpond/execution/task.py:1884
Method
run
(self)
smallpond/execution/task.py:1978
Method
run
(self)
smallpond/execution/task.py:2265
Method
run
(self)
smallpond/execution/task.py:2624
Method
run
(self)
smallpond/execution/task.py:2969
Method
run
(self)
smallpond/execution/task.py:3316
Method
run
(self)
smallpond/execution/task.py:3388
Method
run
(self)
smallpond/execution/task.py:3506
Method
run
(self)
smallpond/execution/executor.py:154
Method
run
(self)
smallpond/execution/scheduler.py:307
Method
run
(self)
smallpond/execution/workqueue.py:218
Method
run_executor
(runtime_ctx: RuntimeContext, exec_id: str, numa_node_id=None)
smallpond/execution/driver.py:335
Function
run_scheduler
( runtime_ctx: RuntimeContext, scheduler: Scheduler, queue: queue.Queue )
tests/test_fabric.py:30
Method
run_test_plan
( npartitions: int, data_partition_column: str, engine_type: str,
tests/test_partition.py:311
Method
running_works
(self)
smallpond/execution/scheduler.py:465
Method
runtime_ctx
(self)
smallpond/session.py:245
Method
runtime_ctx_path
(self)
smallpond/execution/task.py:233
Method
runtime_id
(self)
smallpond/execution/task.py:722
Method
runtime_output_abspath
Output data will be produced in this directory at runtime. When the task is finished, this directory will be atomically moved to `fi
smallpond/execution/task.py:767
Method
runtime_output_abspath
(self)
smallpond/execution/task.py:3382
Method
sched_state_path
(self)
smallpond/execution/task.py:253
Method
secs_executor_probe_timeout
(self)
smallpond/execution/task.py:297
Method
self_contained_output
Whether the output of this node is not dependent on any input nodes.
smallpond/execution/task.py:784
Method
self_contained_output
(self)
smallpond/execution/task.py:1388
Method
self_contained_output
(self)
smallpond/execution/task.py:1433
Method
self_contained_output
(self)
smallpond/execution/task.py:1624
Method
self_contained_output
(self)
smallpond/execution/task.py:1709
← previous
next →
701–800 of 992, ranked by callers