minhash.hpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2023-2024, NVIDIA CORPORATION.
3  *
4  * Licensed under the Apache License, Version 2.0 (the "License");
5  * you may not use this file except in compliance with the License.
6  * You may obtain a copy of the License at
7  *
8  * http://www.apache.org/licenses/LICENSE-2.0
9  *
10  * Unless required by applicable law or agreed to in writing, software
11  * distributed under the License is distributed on an "AS IS" BASIS,
12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13  * See the License for the specific language governing permissions and
14  * limitations under the License.
15  */
16 #pragma once
17 
18 #include <cudf/column/column.hpp>
19 #include <cudf/hashing.hpp>
21 #include <cudf/scalar/scalar.hpp>
23 #include <cudf/utilities/export.hpp>
25 #include <cudf/utilities/span.hpp>
26 
27 namespace CUDF_EXPORT nvtext {
56 [[deprecated]] std::unique_ptr<cudf::column> minhash(
57  cudf::strings_column_view const& input,
59  cudf::size_type width = 4,
62 
90 [[deprecated]] std::unique_ptr<cudf::column> minhash(
91  cudf::strings_column_view const& input,
93  cudf::size_type width = 4,
96 
135 std::unique_ptr<cudf::column> minhash_permuted(
136  cudf::strings_column_view const& input,
137  uint32_t seed,
140  cudf::size_type width,
143 
168 [[deprecated]] std::unique_ptr<cudf::column> minhash64(
169  cudf::strings_column_view const& input,
171  cudf::size_type width = 4,
174 
202 [[deprecated]] std::unique_ptr<cudf::column> minhash64(
203  cudf::strings_column_view const& input,
205  cudf::size_type width = 4,
208 
247 std::unique_ptr<cudf::column> minhash64_permuted(
248  cudf::strings_column_view const& input,
249  uint64_t seed,
252  cudf::size_type width,
255 
280 [[deprecated]] std::unique_ptr<cudf::column> word_minhash(
281  cudf::lists_column_view const& input,
285 
311 [[deprecated]] std::unique_ptr<cudf::column> word_minhash64(
312  cudf::lists_column_view const& input,
317 } // namespace CUDF_EXPORT nvtext
Given a column-view of lists type, an instance of this class provides a wrapper on this compound colu...
An owning class to represent a numerical value in device memory.
Definition: scalar.hpp:242
Given a column-view of strings type, an instance of this class provides a wrapper on this compound co...
Class definition for cudf::column.
rmm::cuda_stream_view const get_default_stream()
Get the current default stream.
rmm::device_async_resource_ref get_current_device_resource_ref()
Get the current device memory resource reference.
cuda::mr::async_resource_ref< cuda::mr::device_accessible > device_async_resource_ref
std::unique_ptr< cudf::column > minhash_permuted(cudf::strings_column_view const &input, uint32_t seed, cudf::device_span< uint32_t const > parameter_a, cudf::device_span< uint32_t const > parameter_b, cudf::size_type width, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Returns the minhash values for each string.
std::unique_ptr< cudf::column > word_minhash64(cudf::lists_column_view const &input, cudf::device_span< uint64_t const > seeds, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Returns the minhash values for each row of strings per seed.
std::unique_ptr< cudf::column > minhash64(cudf::strings_column_view const &input, cudf::device_span< uint64_t const > seeds, cudf::size_type width=4, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Returns the minhash values for each string per seed.
std::unique_ptr< cudf::column > word_minhash(cudf::lists_column_view const &input, cudf::device_span< uint32_t const > seeds, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Returns the minhash values for each row of strings per seed.
std::unique_ptr< cudf::column > minhash(cudf::strings_column_view const &input, cudf::device_span< uint32_t const > seeds, cudf::size_type width=4, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Returns the minhash values for each string per seed.
std::unique_ptr< cudf::column > minhash64_permuted(cudf::strings_column_view const &input, uint64_t seed, cudf::device_span< uint64_t const > parameter_a, cudf::device_span< uint64_t const > parameter_b, cudf::size_type width, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Returns the minhash values for each string.
int32_t size_type
Row index type for columns and tables.
Definition: types.hpp:95
Class definition for cudf::lists_column_view.
NVText APIs.
Class definitions for cudf::scalar.
APIs for spans.
Class definition for cudf::strings_column_view.
Device version of C++20 std::span with reduced feature set.
Definition: span.hpp:338