API Reference
- fugue
- fugue.bag
- fugue.collections
- fugue.collections.partition
BagPartitionCursor
DatasetPartitionCursor
PartitionCursor
PartitionSpec
PartitionSpec.algo
PartitionSpec.empty
PartitionSpec.get_cursor()
PartitionSpec.get_key_schema()
PartitionSpec.get_num_partitions()
PartitionSpec.get_partitioner()
PartitionSpec.get_sorts()
PartitionSpec.jsondict
PartitionSpec.num_partitions
PartitionSpec.partition_by
PartitionSpec.presort
PartitionSpec.presort_expr
parse_presort_exp()
- fugue.collections.sql
- fugue.collections.yielded
- fugue.collections.partition
- fugue.column
- fugue.column.expressions
- fugue.column.functions
- fugue.column.sql
SQLExpressionGenerator
SelectColumns
SelectColumns.agg_funcs
SelectColumns.all_cols
SelectColumns.assert_all_with_names()
SelectColumns.assert_no_agg()
SelectColumns.assert_no_wildcard()
SelectColumns.group_keys
SelectColumns.has_agg
SelectColumns.has_literals
SelectColumns.is_distinct
SelectColumns.literals
SelectColumns.non_agg_funcs
SelectColumns.replace_wildcard()
SelectColumns.simple
SelectColumns.simple_cols
- fugue.dataframe
- fugue.dataframe.api
- fugue.dataframe.array_dataframe
- fugue.dataframe.arrow_dataframe
ArrowDataFrame
ArrowDataFrame.alter_columns()
ArrowDataFrame.as_array()
ArrowDataFrame.as_array_iterable()
ArrowDataFrame.as_arrow()
ArrowDataFrame.as_dict_iterable()
ArrowDataFrame.as_dicts()
ArrowDataFrame.as_pandas()
ArrowDataFrame.count()
ArrowDataFrame.empty
ArrowDataFrame.head()
ArrowDataFrame.native
ArrowDataFrame.native_as_df()
ArrowDataFrame.peek_array()
ArrowDataFrame.peek_dict()
ArrowDataFrame.rename()
- fugue.dataframe.dataframe
DataFrame
DataFrame.alter_columns()
DataFrame.as_array()
DataFrame.as_array_iterable()
DataFrame.as_arrow()
DataFrame.as_dict_iterable()
DataFrame.as_dicts()
DataFrame.as_local()
DataFrame.as_local_bounded()
DataFrame.as_pandas()
DataFrame.columns
DataFrame.drop()
DataFrame.get_info_str()
DataFrame.head()
DataFrame.native_as_df()
DataFrame.peek_array()
DataFrame.peek_dict()
DataFrame.rename()
DataFrame.schema
DataFrame.schema_discovered
DataFrameDisplay
LocalBoundedDataFrame
LocalDataFrame
LocalUnboundedDataFrame
YieldedDataFrame
as_fugue_df()
- fugue.dataframe.dataframe_iterable_dataframe
IterableArrowDataFrame
IterablePandasDataFrame
LocalDataFrameIterableDataFrame
LocalDataFrameIterableDataFrame.alter_columns()
LocalDataFrameIterableDataFrame.as_array()
LocalDataFrameIterableDataFrame.as_array_iterable()
LocalDataFrameIterableDataFrame.as_arrow()
LocalDataFrameIterableDataFrame.as_local_bounded()
LocalDataFrameIterableDataFrame.as_pandas()
LocalDataFrameIterableDataFrame.empty
LocalDataFrameIterableDataFrame.head()
LocalDataFrameIterableDataFrame.native
LocalDataFrameIterableDataFrame.peek_array()
LocalDataFrameIterableDataFrame.rename()
- fugue.dataframe.dataframes
- fugue.dataframe.function_wrapper
- fugue.dataframe.iterable_dataframe
- fugue.dataframe.pandas_dataframe
PandasDataFrame
PandasDataFrame.alter_columns()
PandasDataFrame.as_array()
PandasDataFrame.as_array_iterable()
PandasDataFrame.as_arrow()
PandasDataFrame.as_dict_iterable()
PandasDataFrame.as_dicts()
PandasDataFrame.as_pandas()
PandasDataFrame.count()
PandasDataFrame.empty
PandasDataFrame.head()
PandasDataFrame.native
PandasDataFrame.native_as_df()
PandasDataFrame.peek_array()
PandasDataFrame.rename()
- fugue.dataframe.utils
- fugue.dataset
- fugue.execution
- fugue.execution.api
aggregate()
anti_join()
assign()
broadcast()
clear_global_engine()
cross_join()
distinct()
dropna()
engine_context()
fillna()
filter()
full_outer_join()
get_context_engine()
get_current_conf()
get_current_parallelism()
inner_join()
intersect()
join()
left_outer_join()
load()
persist()
repartition()
right_outer_join()
run_engine_function()
sample()
save()
select()
semi_join()
set_global_engine()
subtract()
take()
union()
- fugue.execution.execution_engine
EngineFacet
ExecutionEngine
ExecutionEngine.aggregate()
ExecutionEngine.as_context()
ExecutionEngine.assign()
ExecutionEngine.broadcast()
ExecutionEngine.comap()
ExecutionEngine.conf
ExecutionEngine.convert_yield_dataframe()
ExecutionEngine.create_default_map_engine()
ExecutionEngine.create_default_sql_engine()
ExecutionEngine.distinct()
ExecutionEngine.dropna()
ExecutionEngine.fillna()
ExecutionEngine.filter()
ExecutionEngine.get_current_parallelism()
ExecutionEngine.in_context
ExecutionEngine.intersect()
ExecutionEngine.is_global
ExecutionEngine.join()
ExecutionEngine.load_df()
ExecutionEngine.load_yielded()
ExecutionEngine.map_engine
ExecutionEngine.on_enter_context()
ExecutionEngine.on_exit_context()
ExecutionEngine.persist()
ExecutionEngine.repartition()
ExecutionEngine.sample()
ExecutionEngine.save_df()
ExecutionEngine.select()
ExecutionEngine.set_global()
ExecutionEngine.set_sql_engine()
ExecutionEngine.sql_engine
ExecutionEngine.stop()
ExecutionEngine.stop_engine()
ExecutionEngine.subtract()
ExecutionEngine.take()
ExecutionEngine.union()
ExecutionEngine.zip()
ExecutionEngineParam
FugueEngineBase
MapEngine
SQLEngine
- fugue.execution.factory
- fugue.execution.native_execution_engine
NativeExecutionEngine
NativeExecutionEngine.broadcast()
NativeExecutionEngine.create_default_map_engine()
NativeExecutionEngine.create_default_sql_engine()
NativeExecutionEngine.distinct()
NativeExecutionEngine.dropna()
NativeExecutionEngine.fillna()
NativeExecutionEngine.get_current_parallelism()
NativeExecutionEngine.intersect()
NativeExecutionEngine.is_distributed
NativeExecutionEngine.join()
NativeExecutionEngine.load_df()
NativeExecutionEngine.log
NativeExecutionEngine.persist()
NativeExecutionEngine.pl_utils
NativeExecutionEngine.repartition()
NativeExecutionEngine.sample()
NativeExecutionEngine.save_df()
NativeExecutionEngine.subtract()
NativeExecutionEngine.take()
NativeExecutionEngine.to_df()
NativeExecutionEngine.union()
PandasMapEngine
QPDPandasEngine
- fugue.execution.api
- fugue.extensions
- fugue.extensions.creator
- fugue.extensions.outputter
- fugue.extensions.processor
- fugue.extensions.transformer
- fugue.extensions.context
ExtensionContext
ExtensionContext.callback
ExtensionContext.cursor
ExtensionContext.execution_engine
ExtensionContext.has_callback
ExtensionContext.key_schema
ExtensionContext.output_schema
ExtensionContext.params
ExtensionContext.partition_spec
ExtensionContext.rpc_server
ExtensionContext.validate_on_compile()
ExtensionContext.validate_on_runtime()
ExtensionContext.validation_rules
ExtensionContext.workflow_conf
- fugue.rpc
- fugue.sql
- fugue.workflow
- fugue.workflow.api
- fugue.workflow.input
- fugue.workflow.module
- fugue.workflow.workflow
FugueWorkflow
FugueWorkflow.add()
FugueWorkflow.assert_eq()
FugueWorkflow.assert_not_eq()
FugueWorkflow.conf
FugueWorkflow.create()
FugueWorkflow.create_data()
FugueWorkflow.df()
FugueWorkflow.get_result()
FugueWorkflow.intersect()
FugueWorkflow.join()
FugueWorkflow.last_df
FugueWorkflow.load()
FugueWorkflow.out_transform()
FugueWorkflow.output()
FugueWorkflow.process()
FugueWorkflow.run()
FugueWorkflow.select()
FugueWorkflow.set_op()
FugueWorkflow.show()
FugueWorkflow.spec_uuid()
FugueWorkflow.subtract()
FugueWorkflow.transform()
FugueWorkflow.union()
FugueWorkflow.yields
FugueWorkflow.zip()
FugueWorkflowResult
WorkflowDataFrame
WorkflowDataFrame.aggregate()
WorkflowDataFrame.alter_columns()
WorkflowDataFrame.anti_join()
WorkflowDataFrame.as_array()
WorkflowDataFrame.as_array_iterable()
WorkflowDataFrame.as_local()
WorkflowDataFrame.as_local_bounded()
WorkflowDataFrame.assert_eq()
WorkflowDataFrame.assert_not_eq()
WorkflowDataFrame.assign()
WorkflowDataFrame.broadcast()
WorkflowDataFrame.checkpoint()
WorkflowDataFrame.compute()
WorkflowDataFrame.count()
WorkflowDataFrame.cross_join()
WorkflowDataFrame.deterministic_checkpoint()
WorkflowDataFrame.distinct()
WorkflowDataFrame.drop()
WorkflowDataFrame.dropna()
WorkflowDataFrame.empty
WorkflowDataFrame.fillna()
WorkflowDataFrame.filter()
WorkflowDataFrame.full_outer_join()
WorkflowDataFrame.head()
WorkflowDataFrame.inner_join()
WorkflowDataFrame.intersect()
WorkflowDataFrame.is_bounded
WorkflowDataFrame.is_local
WorkflowDataFrame.join()
WorkflowDataFrame.left_anti_join()
WorkflowDataFrame.left_outer_join()
WorkflowDataFrame.left_semi_join()
WorkflowDataFrame.name
WorkflowDataFrame.native
WorkflowDataFrame.native_as_df()
WorkflowDataFrame.num_partitions
WorkflowDataFrame.out_transform()
WorkflowDataFrame.output()
WorkflowDataFrame.partition()
WorkflowDataFrame.partition_by()
WorkflowDataFrame.partition_spec
WorkflowDataFrame.peek_array()
WorkflowDataFrame.per_partition_by()
WorkflowDataFrame.per_row()
WorkflowDataFrame.persist()
WorkflowDataFrame.process()
WorkflowDataFrame.rename()
WorkflowDataFrame.result
WorkflowDataFrame.right_outer_join()
WorkflowDataFrame.sample()
WorkflowDataFrame.save()
WorkflowDataFrame.save_and_use()
WorkflowDataFrame.schema
WorkflowDataFrame.select()
WorkflowDataFrame.semi_join()
WorkflowDataFrame.show()
WorkflowDataFrame.spec_uuid()
WorkflowDataFrame.strong_checkpoint()
WorkflowDataFrame.subtract()
WorkflowDataFrame.take()
WorkflowDataFrame.transform()
WorkflowDataFrame.union()
WorkflowDataFrame.weak_checkpoint()
WorkflowDataFrame.workflow
WorkflowDataFrame.yield_dataframe_as()
WorkflowDataFrame.yield_file_as()
WorkflowDataFrame.yield_table_as()
WorkflowDataFrame.zip()
WorkflowDataFrames
- fugue.api
- fugue.constants
- fugue.dev
- fugue.exceptions
FugueBug
FugueDataFrameError
FugueDataFrameInitError
FugueDataFrameOperationError
FugueDatasetEmptyError
FugueError
FugueInterfacelessError
FugueInvalidOperation
FuguePluginsRegistrationError
FugueSQLError
FugueSQLRuntimeError
FugueSQLSyntaxError
FugueWorkflowCompileError
FugueWorkflowCompileValidationError
FugueWorkflowError
FugueWorkflowRuntimeError
FugueWorkflowRuntimeValidationError
- fugue.plugins
- fugue.registry
- fugue_sql
- fugue_duckdb
- fugue_duckdb.dask
DuckDaskExecutionEngine
DuckDaskExecutionEngine.broadcast()
DuckDaskExecutionEngine.convert_yield_dataframe()
DuckDaskExecutionEngine.create_default_map_engine()
DuckDaskExecutionEngine.dask_client
DuckDaskExecutionEngine.get_current_parallelism()
DuckDaskExecutionEngine.persist()
DuckDaskExecutionEngine.repartition()
DuckDaskExecutionEngine.save_df()
DuckDaskExecutionEngine.to_df()
- fugue_duckdb.dataframe
DuckDataFrame
DuckDataFrame.alias
DuckDataFrame.alter_columns()
DuckDataFrame.as_array()
DuckDataFrame.as_array_iterable()
DuckDataFrame.as_arrow()
DuckDataFrame.as_dict_iterable()
DuckDataFrame.as_dicts()
DuckDataFrame.as_local_bounded()
DuckDataFrame.as_pandas()
DuckDataFrame.count()
DuckDataFrame.empty
DuckDataFrame.head()
DuckDataFrame.native
DuckDataFrame.native_as_df()
DuckDataFrame.peek_array()
DuckDataFrame.rename()
- fugue_duckdb.execution_engine
DuckDBEngine
DuckExecutionEngine
DuckExecutionEngine.broadcast()
DuckExecutionEngine.connection
DuckExecutionEngine.convert_yield_dataframe()
DuckExecutionEngine.create_default_map_engine()
DuckExecutionEngine.create_default_sql_engine()
DuckExecutionEngine.distinct()
DuckExecutionEngine.dropna()
DuckExecutionEngine.fillna()
DuckExecutionEngine.get_current_parallelism()
DuckExecutionEngine.intersect()
DuckExecutionEngine.is_distributed
DuckExecutionEngine.join()
DuckExecutionEngine.load_df()
DuckExecutionEngine.log
DuckExecutionEngine.persist()
DuckExecutionEngine.repartition()
DuckExecutionEngine.sample()
DuckExecutionEngine.save_df()
DuckExecutionEngine.stop_engine()
DuckExecutionEngine.subtract()
DuckExecutionEngine.take()
DuckExecutionEngine.to_df()
DuckExecutionEngine.union()
- fugue_duckdb.ibis_engine
- fugue_duckdb.registry
- fugue_duckdb.dask
- fugue_spark
- fugue_spark.dataframe
SparkDataFrame
SparkDataFrame.alias
SparkDataFrame.alter_columns()
SparkDataFrame.as_array()
SparkDataFrame.as_array_iterable()
SparkDataFrame.as_arrow()
SparkDataFrame.as_dict_iterable()
SparkDataFrame.as_dicts()
SparkDataFrame.as_local_bounded()
SparkDataFrame.as_pandas()
SparkDataFrame.count()
SparkDataFrame.empty
SparkDataFrame.head()
SparkDataFrame.is_bounded
SparkDataFrame.is_local
SparkDataFrame.native
SparkDataFrame.native_as_df()
SparkDataFrame.num_partitions
SparkDataFrame.peek_array()
SparkDataFrame.rename()
- fugue_spark.execution_engine
SparkExecutionEngine
SparkExecutionEngine.broadcast()
SparkExecutionEngine.create_default_map_engine()
SparkExecutionEngine.create_default_sql_engine()
SparkExecutionEngine.distinct()
SparkExecutionEngine.dropna()
SparkExecutionEngine.fillna()
SparkExecutionEngine.get_current_parallelism()
SparkExecutionEngine.intersect()
SparkExecutionEngine.is_distributed
SparkExecutionEngine.is_spark_connect
SparkExecutionEngine.join()
SparkExecutionEngine.load_df()
SparkExecutionEngine.log
SparkExecutionEngine.persist()
SparkExecutionEngine.repartition()
SparkExecutionEngine.sample()
SparkExecutionEngine.save_df()
SparkExecutionEngine.spark_session
SparkExecutionEngine.subtract()
SparkExecutionEngine.take()
SparkExecutionEngine.to_df()
SparkExecutionEngine.union()
SparkMapEngine
SparkSQLEngine
- fugue_spark.ibis_engine
- fugue_spark.registry
- fugue_spark.dataframe
- fugue_dask
- fugue_dask.dataframe
DaskDataFrame
DaskDataFrame.alter_columns()
DaskDataFrame.as_array()
DaskDataFrame.as_array_iterable()
DaskDataFrame.as_arrow()
DaskDataFrame.as_dict_iterable()
DaskDataFrame.as_dicts()
DaskDataFrame.as_local_bounded()
DaskDataFrame.as_pandas()
DaskDataFrame.count()
DaskDataFrame.empty
DaskDataFrame.head()
DaskDataFrame.is_bounded
DaskDataFrame.is_local
DaskDataFrame.native
DaskDataFrame.native_as_df()
DaskDataFrame.num_partitions
DaskDataFrame.peek_array()
DaskDataFrame.persist()
DaskDataFrame.rename()
- fugue_dask.execution_engine
DaskExecutionEngine
DaskExecutionEngine.broadcast()
DaskExecutionEngine.create_default_map_engine()
DaskExecutionEngine.create_default_sql_engine()
DaskExecutionEngine.dask_client
DaskExecutionEngine.distinct()
DaskExecutionEngine.dropna()
DaskExecutionEngine.fillna()
DaskExecutionEngine.get_current_parallelism()
DaskExecutionEngine.intersect()
DaskExecutionEngine.is_distributed
DaskExecutionEngine.join()
DaskExecutionEngine.load_df()
DaskExecutionEngine.log
DaskExecutionEngine.persist()
DaskExecutionEngine.pl_utils
DaskExecutionEngine.repartition()
DaskExecutionEngine.sample()
DaskExecutionEngine.save_df()
DaskExecutionEngine.subtract()
DaskExecutionEngine.take()
DaskExecutionEngine.to_df()
DaskExecutionEngine.union()
DaskMapEngine
DaskSQLEngine
to_dask_engine_df()
- fugue_dask.ibis_engine
- fugue_dask.registry
- fugue_dask.dataframe
- fugue_ray
- fugue_ray.dataframe
RayDataFrame
RayDataFrame.alter_columns()
RayDataFrame.as_array()
RayDataFrame.as_array_iterable()
RayDataFrame.as_arrow()
RayDataFrame.as_dict_iterable()
RayDataFrame.as_dicts()
RayDataFrame.as_local_bounded()
RayDataFrame.as_pandas()
RayDataFrame.count()
RayDataFrame.empty
RayDataFrame.head()
RayDataFrame.is_bounded
RayDataFrame.is_local
RayDataFrame.native
RayDataFrame.native_as_df()
RayDataFrame.num_partitions
RayDataFrame.peek_array()
RayDataFrame.persist()
RayDataFrame.rename()
- fugue_ray.execution_engine
RayExecutionEngine
RayExecutionEngine.broadcast()
RayExecutionEngine.convert_yield_dataframe()
RayExecutionEngine.create_default_map_engine()
RayExecutionEngine.get_current_parallelism()
RayExecutionEngine.is_distributed
RayExecutionEngine.load_df()
RayExecutionEngine.persist()
RayExecutionEngine.repartition()
RayExecutionEngine.save_df()
RayExecutionEngine.to_df()
RayExecutionEngine.union()
RayMapEngine
- fugue_ray.registry
- fugue_ray.dataframe
- fugue_ibis
- fugue_ibis.execution
- fugue_ibis.dataframe
IbisDataFrame
IbisDataFrame.alter_columns()
IbisDataFrame.as_array()
IbisDataFrame.as_array_iterable()
IbisDataFrame.as_arrow()
IbisDataFrame.as_dict_iterable()
IbisDataFrame.as_dicts()
IbisDataFrame.as_local_bounded()
IbisDataFrame.as_pandas()
IbisDataFrame.columns
IbisDataFrame.count()
IbisDataFrame.empty
IbisDataFrame.head()
IbisDataFrame.is_bounded
IbisDataFrame.is_local
IbisDataFrame.native
IbisDataFrame.native_as_df()
IbisDataFrame.num_partitions
IbisDataFrame.peek_array()
IbisDataFrame.rename()
IbisDataFrame.to_sql()
- fugue_ibis.execution_engine
IbisExecutionEngine
IbisExecutionEngine.broadcast()
IbisExecutionEngine.create_default_map_engine()
IbisExecutionEngine.create_non_ibis_execution_engine()
IbisExecutionEngine.distinct()
IbisExecutionEngine.dropna()
IbisExecutionEngine.fillna()
IbisExecutionEngine.get_current_parallelism()
IbisExecutionEngine.ibis_sql_engine
IbisExecutionEngine.intersect()
IbisExecutionEngine.is_non_ibis()
IbisExecutionEngine.join()
IbisExecutionEngine.log
IbisExecutionEngine.non_ibis_engine
IbisExecutionEngine.persist()
IbisExecutionEngine.repartition()
IbisExecutionEngine.sample()
IbisExecutionEngine.subtract()
IbisExecutionEngine.take()
IbisExecutionEngine.to_df()
IbisExecutionEngine.union()
IbisMapEngine
IbisSQLEngine
IbisSQLEngine.backend
IbisSQLEngine.distinct()
IbisSQLEngine.dropna()
IbisSQLEngine.encode_column_name()
IbisSQLEngine.fillna()
IbisSQLEngine.get_temp_table_name()
IbisSQLEngine.intersect()
IbisSQLEngine.join()
IbisSQLEngine.load_table()
IbisSQLEngine.persist()
IbisSQLEngine.query_to_table()
IbisSQLEngine.sample()
IbisSQLEngine.save_table()
IbisSQLEngine.select()
IbisSQLEngine.subtract()
IbisSQLEngine.table_exists()
IbisSQLEngine.take()
IbisSQLEngine.union()
- fugue_ibis.extensions