Add __all__ to all pylibcudf modules

rapidsai · Nov 7, 2024 · 1801379 · 1801379
1 parent bd9f6f8
commit 1801379
Show file tree

Hide file tree

Showing 91 changed files with 410 additions and 2 deletions.
diff --git a/python/pylibcudf/pylibcudf/aggregation.pyx b/python/pylibcudf/pylibcudf/aggregation.pyx
@@ -64,6 +64,40 @@ from pylibcudf.libcudf.aggregation import udf_type as UdfType  # no-cython-lint
 from .types cimport DataType
 
 
+__all__ = [
+    "Aggregation",
+    "CorrelationType",
+    "EWMHistory",
+    "Kind",
+    "RankMethod",
+    "RankPercentage",
+    "UdfType",
+    "all",
+    "any",
+    "argmax",
+    "argmin",
+    "collect_list",
+    "collect_set",
+    "correlation",
+    "count",
+    "covariance",
+    "ewma",
+    "max",
+    "mean",
+    "median",
+    "min",
+    "nth_element",
+    "nunique",
+    "product",
+    "quantile",
+    "rank",
+    "std",
+    "sum",
+    "sum_of_squares",
+    "udf",
+    "variance",
+]
+
 cdef class Aggregation:
     """A type of aggregation to perform.
 

diff --git a/python/pylibcudf/pylibcudf/binaryop.pyx b/python/pylibcudf/pylibcudf/binaryop.pyx
@@ -16,6 +16,7 @@ from .column cimport Column
 from .scalar cimport Scalar
 from .types cimport DataType
 
+__all__ = ["BinaryOperator", "binary_operation", "is_supported_operation"]
 
 cpdef Column binary_operation(
     LeftBinaryOperand lhs,

diff --git a/python/pylibcudf/pylibcudf/column.pyx b/python/pylibcudf/pylibcudf/column.pyx
@@ -17,6 +17,7 @@ from .utils cimport int_to_bitmask_ptr, int_to_void_ptr
 
 import functools
 
+__all__ = ["Column", "ListColumnView", "is_c_contiguous"]
 
 cdef class Column:
     """A container of nullable device data as a column of elements.

diff --git a/python/pylibcudf/pylibcudf/column_factories.pyx b/python/pylibcudf/pylibcudf/column_factories.pyx
@@ -17,6 +17,15 @@ from .types cimport DataType, type_id
 from .types import MaskState, TypeId
 
 
+__all__ = [
+    "make_duration_column",
+    "make_empty_column",
+    "make_fixed_point_column",
+    "make_fixed_width_column",
+    "make_numeric_column",
+    "make_timestamp_column",
+]
+
 cpdef Column make_empty_column(MakeEmptyColumnOperand type_or_id):
     """Creates an empty column of the specified type.
 

diff --git a/python/pylibcudf/pylibcudf/concatenate.pyx b/python/pylibcudf/pylibcudf/concatenate.pyx
@@ -12,6 +12,7 @@ from pylibcudf.libcudf.table.table_view cimport table_view
 from .column cimport Column
 from .table cimport Table
 
+__all__ = ["concatenate"]
 
 cpdef concatenate(list objects):
     """Concatenate columns or tables.

diff --git a/python/pylibcudf/pylibcudf/contiguous_split.pyx b/python/pylibcudf/pylibcudf/contiguous_split.pyx
@@ -20,6 +20,13 @@ from .table cimport Table
 from .utils cimport int_to_void_ptr
 
 
+__all__ = [
+    "PackedColumns",
+    "pack",
+    "unpack",
+    "unpack_from_memoryviews",
+]
+
 cdef class HostBuffer:
     """Owning host buffer that implements the buffer protocol"""
     cdef unique_ptr[vector[uint8_t]] c_obj

diff --git a/python/pylibcudf/pylibcudf/copying.pyx b/python/pylibcudf/pylibcudf/copying.pyx
@@ -36,6 +36,23 @@ from .table cimport Table
 from .utils cimport _as_vector
 
 
+__all__ = [
+    "MaskAllocationPolicy",
+    "OutOfBoundsPolicy",
+    "allocate_like",
+    "boolean_mask_scatter",
+    "copy_if_else",
+    "copy_range",
+    "copy_range_in_place",
+    "empty_like",
+    "gather",
+    "get_element",
+    "scatter",
+    "shift",
+    "slice",
+    "split",
+]
+
 cpdef Table gather(
     Table source_table,
     Column gather_map,

diff --git a/python/pylibcudf/pylibcudf/datetime.pyx b/python/pylibcudf/pylibcudf/datetime.pyx
@@ -29,6 +29,24 @@ from cython.operator cimport dereference
 
 from .column cimport Column
 
+__all__ = [
+    "DatetimeComponent",
+    "RoundingFrequency",
+    "add_calendrical_months",
+    "ceil_datetimes",
+    "day_of_year",
+    "days_in_month",
+    "extract_datetime_component",
+    "extract_microsecond_fraction",
+    "extract_millisecond_fraction",
+    "extract_nanosecond_fraction",
+    "extract_quarter",
+    "floor_datetimes",
+    "is_leap_year",
+    "last_day_of_month",
+    "round_datetimes",
+]
+
 cpdef Column extract_millisecond_fraction(
     Column input
 ):

diff --git a/python/pylibcudf/pylibcudf/experimental.pyx b/python/pylibcudf/pylibcudf/experimental.pyx
@@ -5,6 +5,8 @@ from libcpp.string cimport string
 from pylibcudf.libcudf cimport experimental as cpp_experimental
 
 
+__all__ = ["disable_prefetching", "enable_prefetching", "prefetch_debugging"]
+
 cpdef enable_prefetching(str key):
     """Turn on prefetch instructions for the given key.
 

diff --git a/python/pylibcudf/pylibcudf/expressions.pyx b/python/pylibcudf/pylibcudf/expressions.pyx
@@ -49,6 +49,16 @@ from .types cimport DataType
 # Aliases for simplicity
 ctypedef unique_ptr[libcudf_exp.expression] expression_ptr
 
+__all__ = [
+    "ASTOperator",
+    "ColumnNameReference",
+    "ColumnReference",
+    "Expression",
+    "Literal",
+    "Operation",
+    "TableReference",
+]
+
 # Define this class just to have a docstring for it
 cdef class Expression:
     """

diff --git a/python/pylibcudf/pylibcudf/filling.pyx b/python/pylibcudf/pylibcudf/filling.pyx
@@ -18,6 +18,8 @@ from .scalar cimport Scalar
 from .table cimport Table
 
 
+__all__ = ["fill", "fill_in_place", "repeat", "sequence"]
+
 cpdef Column fill(
     Column destination,
     size_type begin,

diff --git a/python/pylibcudf/pylibcudf/gpumemoryview.pyx b/python/pylibcudf/pylibcudf/gpumemoryview.pyx
@@ -1,5 +1,6 @@
 # Copyright (c) 2023-2024, NVIDIA CORPORATION.
 
+__all__ = ["gpumemoryview"]
 
 cdef class gpumemoryview:
     """Minimal representation of a memory buffer.

diff --git a/python/pylibcudf/pylibcudf/groupby.pyx b/python/pylibcudf/pylibcudf/groupby.pyx
@@ -25,6 +25,8 @@ from .types cimport null_order, null_policy, order, sorted
 from .utils cimport _as_vector
 
 
+__all__ = ["GroupBy", "GroupByRequest"]
+
 cdef class GroupByRequest:
     """A request for a groupby aggregation or scan.
 

diff --git a/python/pylibcudf/pylibcudf/hashing.pyx b/python/pylibcudf/pylibcudf/hashing.pyx
@@ -20,6 +20,19 @@ from pylibcudf.libcudf.table.table cimport table
 from .column cimport Column
 from .table cimport Table
 
+__all__ = [
+    "LIBCUDF_DEFAULT_HASH_SEED",
+    "md5",
+    "murmurhash3_x64_128",
+    "murmurhash3_x86_32",
+    "sha1",
+    "sha224",
+    "sha256",
+    "sha384",
+    "sha512",
+    "xxhash_64",
+]
+
 LIBCUDF_DEFAULT_HASH_SEED = DEFAULT_HASH_SEED
 
 cpdef Column murmurhash3_x86_32(

diff --git a/python/pylibcudf/pylibcudf/interop.pyx b/python/pylibcudf/pylibcudf/interop.pyx
@@ -38,6 +38,14 @@ from .scalar cimport Scalar
 from .table cimport Table
 from .types cimport DataType, type_id
 
+__all__ = [
+    "ColumnMetadata",
+    "from_arrow",
+    "from_dlpack",
+    "to_arrow",
+    "to_dlpack",
+]
+
 ARROW_TO_PYLIBCUDF_TYPES = {
     pa.int8(): type_id.INT8,
     pa.int16(): type_id.INT16,

diff --git a/python/pylibcudf/pylibcudf/io/__init__.py b/python/pylibcudf/pylibcudf/io/__init__.py
@@ -2,3 +2,17 @@
 
 from . import avro, csv, datasource, json, orc, parquet, timezone, types
 from .types import SinkInfo, SourceInfo, TableWithMetadata
+
+__all__ = [
+    "SinkInfo",
+    "SourceInfo",
+    "TableWithMetadata",
+    "avro",
+    "csv",
+    "datasource",
+    "json",
+    "orc",
+    "parquet",
+    "timezone",
+    "types",
+]
diff --git a/python/pylibcudf/pylibcudf/io/avro.pyx b/python/pylibcudf/pylibcudf/io/avro.pyx
@@ -10,6 +10,8 @@ from pylibcudf.libcudf.io.avro cimport (
 )
 from pylibcudf.libcudf.types cimport size_type
 
+__all__ = ["read_avro"]
+
 
 cpdef TableWithMetadata read_avro(
     SourceInfo source_info,

diff --git a/python/pylibcudf/pylibcudf/io/csv.pyx b/python/pylibcudf/pylibcudf/io/csv.pyx
@@ -19,6 +19,8 @@ from pylibcudf.libcudf.types cimport data_type, size_type
 from pylibcudf.types cimport DataType
 
 
+__all__ = ["read_csv"]
+
 cdef tuple _process_parse_dates_hex(list cols):
     cdef vector[string] str_cols
     cdef vector[int] int_cols

diff --git a/python/pylibcudf/pylibcudf/io/datasource.pyx b/python/pylibcudf/pylibcudf/io/datasource.pyx
@@ -2,6 +2,7 @@
 
 from pylibcudf.libcudf.io.datasource cimport datasource
 
+__all__ = ["Datasource"]
 
 cdef class Datasource:
     cdef datasource* get_datasource(self) except * nogil:

diff --git a/python/pylibcudf/pylibcudf/io/json.pyx b/python/pylibcudf/pylibcudf/io/json.pyx
@@ -23,6 +23,7 @@ from pylibcudf.libcudf.io.types cimport (
 from pylibcudf.libcudf.types cimport data_type, size_type
 from pylibcudf.types cimport DataType
 
+__all__ = ["chunked_read_json", "read_json", "write_json"]
 
 cdef map[string, schema_element] _generate_schema_map(list dtypes):
     cdef map[string, schema_element] schema_map

diff --git a/python/pylibcudf/pylibcudf/io/orc.pyx b/python/pylibcudf/pylibcudf/io/orc.pyx
@@ -30,6 +30,12 @@ from pylibcudf.libcudf.types cimport size_type
 from pylibcudf.types cimport DataType
 from pylibcudf.variant cimport get_if, holds_alternative
 
+__all__ = [
+    "OrcColumnStatistics",
+    "ParsedOrcStatistics",
+    "read_orc",
+    "read_parsed_orc_statistics",
+]
 
 cdef class OrcColumnStatistics:
     def __init__(self):

diff --git a/python/pylibcudf/pylibcudf/io/parquet.pyx b/python/pylibcudf/pylibcudf/io/parquet.pyx
@@ -16,6 +16,8 @@ from pylibcudf.libcudf.io.parquet cimport (
 from pylibcudf.libcudf.io.types cimport table_with_metadata
 from pylibcudf.libcudf.types cimport size_type
 
+__all__ = ["ChunkedParquetReader", "read_parquet"]
+
 
 cdef parquet_reader_options _setup_parquet_reader_options(
     SourceInfo source_info,

diff --git a/python/pylibcudf/pylibcudf/io/timezone.pyx b/python/pylibcudf/pylibcudf/io/timezone.pyx
@@ -11,6 +11,7 @@ from pylibcudf.libcudf.table.table cimport table
 
 from ..table cimport Table
 
+__all__ = ["make_timezone_transition_table"]
 
 cpdef Table make_timezone_transition_table(str tzif_dir, str timezone_name):
     """

diff --git a/python/pylibcudf/pylibcudf/io/types.pyx b/python/pylibcudf/pylibcudf/io/types.pyx
@@ -31,6 +31,17 @@ from pylibcudf.libcudf.io.types import (
     statistics_freq as StatisticsFreq, # no-cython-lint
 )
 
+__all__ = [
+    "ColumnEncoding",
+    "CompressionType",
+    "DictionaryPolicy",
+    "JSONRecoveryMode",
+    "QuoteStyle",
+    "SinkInfo",
+    "SourceInfo",
+    "StatisticsFreq",
+    "TableWithMetadata",
+]
 
 cdef class TableWithMetadata:
     """A container holding a table and its associated metadata

diff --git a/python/pylibcudf/pylibcudf/join.pyx b/python/pylibcudf/pylibcudf/join.pyx
@@ -15,6 +15,24 @@ from .column cimport Column
 from .expressions cimport Expression
 from .table cimport Table
 
+__all__ = [
+    "conditional_full_join",
+    "conditional_inner_join",
+    "conditional_left_anti_join",
+    "conditional_left_join",
+    "conditional_left_semi_join",
+    "cross_join",
+    "full_join",
+    "inner_join",
+    "left_anti_join",
+    "left_join",
+    "left_semi_join",
+    "mixed_full_join",
+    "mixed_inner_join",
+    "mixed_left_anti_join",
+    "mixed_left_join",
+    "mixed_left_semi_join",
+]
 
 cdef Column _column_from_gather_map(cpp_join.gather_map_type gather_map):
     # helper to convert a gather map to a Column

diff --git a/python/pylibcudf/pylibcudf/json.pyx b/python/pylibcudf/pylibcudf/json.pyx
@@ -10,6 +10,7 @@ from pylibcudf.libcudf.column.column cimport column
 from pylibcudf.libcudf.scalar.scalar cimport string_scalar
 from pylibcudf.scalar cimport Scalar
 
+__all__ = ["GetJsonObjectOptions", "get_json_object"]
 
 cdef class GetJsonObjectOptions:
     """Settings for ``get_json_object()``"""

diff --git a/python/pylibcudf/pylibcudf/labeling.pyx b/python/pylibcudf/pylibcudf/labeling.pyx
@@ -10,6 +10,7 @@ from pylibcudf.libcudf.labeling import inclusive as Inclusive  # no-cython-lint
 
 from .column cimport Column
 
+__all__ = ["Inclusive", "label_bins"]
 
 cpdef Column label_bins(
     Column input,

diff --git a/python/pylibcudf/pylibcudf/lists.pyx b/python/pylibcudf/pylibcudf/lists.pyx
@@ -49,6 +49,28 @@ from .column cimport Column, ListColumnView
 from .scalar cimport Scalar
 from .table cimport Table
 
+__all__ = [
+    "ConcatenateNullPolicy",
+    "DuplicateFindOption",
+    "apply_boolean_mask",
+    "concatenate_list_elements",
+    "concatenate_rows",
+    "contains",
+    "contains_nulls",
+    "count_elements",
+    "difference_distinct",
+    "distinct",
+    "explode_outer",
+    "extract_list_element",
+    "have_overlap",
+    "index_of",
+    "intersect_distinct",
+    "reverse",
+    "segmented_gather",
+    "sequences",
+    "sort_lists",
+    "union_distinct",
+]
 
 cpdef Table explode_outer(Table input, size_type explode_column_idx):
     """Explode a column of lists into rows.