1 /** 2 * Copyright 2019-2021 Huawei Technologies Co., Ltd 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 17 #ifndef MINDSPORE_CCSRC_MINDDATA_MINDRECORD_INCLUDE_SHARD_PK_SAMPLE_H_ 18 #define MINDSPORE_CCSRC_MINDDATA_MINDRECORD_INCLUDE_SHARD_PK_SAMPLE_H_ 19 20 #include <memory> 21 #include <string> 22 #include <utility> 23 #include <vector> 24 #include "minddata/mindrecord/include/shard_operator.h" 25 #include "minddata/mindrecord/include/shard_shuffle.h" 26 #include "minddata/mindrecord/include/shard_category.h" 27 28 namespace mindspore { 29 namespace mindrecord { 30 class MINDRECORD_API ShardPkSample : public ShardCategory { 31 public: 32 ShardPkSample(const std::string &category_field, int64_t num_elements, int64_t num_samples); 33 34 ShardPkSample(const std::string &category_field, int64_t num_elements, int64_t num_categories, int64_t num_samples); 35 36 ShardPkSample(const std::string &category_field, int64_t num_elements, int64_t num_categories, uint32_t seed, 37 int64_t num_samples); 38 ~ShardPkSample()39 ~ShardPkSample() override{}; 40 41 Status SufExecute(ShardTaskList &tasks) override; 42 GetNumSamples()43 int64_t GetNumSamples() const { return num_samples_; } 44 45 private: 46 bool shuffle_; 47 std::shared_ptr<ShardShuffle> shuffle_op_; 48 int64_t num_samples_; 49 }; 50 } // namespace mindrecord 51 } // namespace mindspore 52 53 #endif // MINDSPORE_CCSRC_MINDDATA_MINDRECORD_INCLUDE_SHARD_PK_SAMPLE_H_ 54