stream_compaction.hpp

Go to the documentation of this file.

/*
 * SPDX-FileCopyrightText: Copyright (c) 2019-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: Apache-2.0
 */
 
#pragma once
 
#include <cudf/column/column_view.hpp>
#include <cudf/column/scalar_column_view.hpp>
#include <cudf/types.hpp>
#include <cudf/utilities/default_stream.hpp>
#include <cudf/utilities/export.hpp>
#include <cudf/utilities/memory_resource.hpp>
 
#include <memory>
#include <optional>
#include <variant>
#include <vector>
 
namespace CUDF_EXPORT cudf {
namespace ast {
struct expression;
}
 
std::unique_ptr<table> drop_nulls(
  table_view const& input,
  std::vector<size_type> const& keys,
  cudf::size_type keep_threshold,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<table> drop_nulls(
  table_view const& input,
  std::vector<size_type> const& keys,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<table> drop_nans(
  table_view const& input,
  std::vector<size_type> const& keys,
  cudf::size_type keep_threshold,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<table> drop_nans(
  table_view const& input,
  std::vector<size_type> const& keys,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<table> apply_retention_mask(
  table_view const& input,
  column_view const& retention_mask,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
[[deprecated("Use apply_retention_mask() instead")]] std::unique_ptr<table> apply_boolean_mask(
  table_view const& input,
  column_view const& boolean_mask,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<table> apply_deletion_mask(
  table_view const& input,
  column_view const& deletion_mask,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
enum class duplicate_keep_option {
  KEEP_ANY = 0,  
  KEEP_FIRST,    
  KEEP_LAST,     
  KEEP_NONE      
};
 
std::unique_ptr<table> unique(
  table_view const& input,
  std::vector<size_type> const& keys,
  duplicate_keep_option keep,
  null_equality nulls_equal         = null_equality::EQUAL,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<table> distinct(
  table_view const& input,
  std::vector<size_type> const& keys,
  duplicate_keep_option keep        = duplicate_keep_option::KEEP_ANY,
  null_equality nulls_equal         = null_equality::EQUAL,
  nan_equality nans_equal           = nan_equality::ALL_EQUAL,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<column> distinct_indices(
  table_view const& input,
  duplicate_keep_option keep        = duplicate_keep_option::KEEP_ANY,
  null_equality nulls_equal         = null_equality::EQUAL,
  nan_equality nans_equal           = nan_equality::ALL_EQUAL,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<table> stable_distinct(
  table_view const& input,
  std::vector<size_type> const& keys,
  duplicate_keep_option keep        = duplicate_keep_option::KEEP_ANY,
  null_equality nulls_equal         = null_equality::EQUAL,
  nan_equality nans_equal           = nan_equality::ALL_EQUAL,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
[[deprecated("Use filter_extended instead")]] std::vector<std::unique_ptr<column>> filter(
  std::vector<column_view> const& predicate_columns,
  std::string const& predicate_udf,
  std::vector<column_view> const& filter_columns,
  bool is_ptx,
  std::optional<void*> user_data           = std::nullopt,
  null_aware is_null_aware                 = null_aware::NO,
  output_nullability predicate_nullability = output_nullability::PRESERVE,
  cuda::stream_ref stream                  = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr        = cudf::get_current_device_resource_ref());
 
using filter_input = std::variant<column_view, scalar_column_view>;
 
std::vector<std::unique_ptr<column>> filter_extended(
  std::span<std::variant<column_view, scalar_column_view> const> predicate_inputs,
  std::string const& predicate_udf,
  std::vector<column_view> const& filter_columns,
  cudf::udf_source_type source_type,
  std::optional<void*> user_data           = std::nullopt,
  null_aware is_null_aware                 = null_aware::NO,
  output_nullability predicate_nullability = output_nullability::PRESERVE,
  cuda::stream_ref stream                  = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr        = cudf::get_current_device_resource_ref());
 
std::unique_ptr<table> filter(
  table_view const& predicate_table,
  ast::expression const& predicate_expr,
  table_view const& filter_table,
  cuda::stream_ref stream           = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
}  // namespace CUDF_EXPORT cudf