Visible to Intel only — GUID: GUID-2BF5E395-4E95-4089-922F-96C1E546180F
basic_statistics_dense_batch.cpp
basic_statistics_dense_online.cpp
column_accessor_homogen.cpp
cor_dense_batch.cpp
cor_dense_online.cpp
cov_dense_batch.cpp
cov_dense_biased_batch.cpp
cov_dense_biased_online.cpp
cov_dense_online.cpp
csr_accessor.cpp
csr_table.cpp
dbscan_brute_force_batch.cpp
df_cls_hist_batch.cpp
df_cls_hist_batch_random.cpp
df_cls_traverse_model.cpp
df_reg_hist_batch.cpp
df_reg_hist_batch_random.cpp
df_reg_traverse_model.cpp
heterogen_table.cpp
homogen_table.cpp
kmeans_init_dense.cpp
kmeans_lloyd_dense_batch.cpp
knn_cls_brute_force_dense_batch.cpp
knn_reg_brute_force_dense_batch.cpp
knn_search_brute_force_dense_batch.cpp
linear_kernel_dense_batch.cpp
linear_regression_dense_batch.cpp
linear_regression_dense_online.cpp
logistic_regression_dense_batch.cpp
pca_cor_dense_batch.cpp
pca_cor_dense_online.cpp
pca_cov_dense_batch.cpp
pca_cov_dense_online.cpp
pca_precomputed_cor_dense_batch.cpp
pca_precomputed_cov_dense_batch.cpp
pca_svd_dense_batch.cpp
rbf_kernel_dense_batch.cpp
read_batch.cpp
svm_two_class_thunder_dense_batch.cpp
basic_statistics_dense_batch.cpp
basic_statistics_dense_online.cpp
column_accessor_homogen.cpp
connected_components_batch.cpp
cor_dense_batch.cpp
cor_dense_online.cpp
cov_dense_batch.cpp
cov_dense_biased_batch.cpp
cov_dense_biased_online.cpp
cov_dense_online.cpp
csr_accessor.cpp
csr_table.cpp
dbscan_brute_force_batch.cpp
df_cls_dense_batch.cpp
df_reg_dense_batch.cpp
directed_graph.cpp
graph_service_functions.cpp
heterogen_table.cpp
homogen_table.cpp
jaccard_batch.cpp
jaccard_batch_app.cpp
kmeans_init_dense.cpp
kmeans_lloyd_dense_batch.cpp
knn_cls_brute_force_dense_batch.cpp
knn_cls_kd_tree_dense_batch.cpp
knn_search_brute_force_dense_batch.cpp
linear_kernel_dense_batch.cpp
linear_regression_dense_batch.cpp
linear_regression_dense_online.cpp
logloss_dense_batch.cpp
louvain_batch.cpp
pca_cor_dense_batch.cpp
pca_cor_dense_online.cpp
pca_cov_dense_batch.cpp
pca_cov_dense_online.cpp
pca_precomputed_dense_batch.cpp
pca_svd_dense_batch.cpp
pca_svd_dense_online.cpp
polynomial_kernel_dense_batch.cpp
rbf_kernel_dense_batch.cpp
read_batch.cpp
shortest_paths_batch.cpp
sigmoid_kernel_dense_batch.cpp
subgraph_isomorphism_batch.cpp
svm_multi_class_thunder_csr_batch.cpp
svm_multi_class_thunder_dense_batch.cpp
svm_nu_cls_thunder_csr_batch.cpp
svm_nu_cls_thunder_dense_batch.cpp
svm_nu_reg_thunder_csr_batch.cpp
svm_nu_reg_thunder_dense_batch.cpp
svm_reg_thunder_csr_batch.cpp
svm_reg_thunder_dense_batch.cpp
svm_two_class_smo_csr_batch.cpp
svm_two_class_smo_dense_batch.cpp
svm_two_class_thunder_csr_batch.cpp
svm_two_class_thunder_dense_batch.cpp
triangle_counting_batch.cpp
K-Means Clustering
Density-Based Spatial Clustering of Applications with Noise
Correlation and Variance-Covariance Matrices
Principal Component Analysis
Principal Components Analysis Transform
Singular Value Decomposition
Association Rules
Kernel Functions
Expectation-Maximization
Cholesky Decomposition
QR Decomposition
Outlier Detection
Distance Matrix
Distributions
Engines
Moments of Low Order
Quantile
Quality Metrics
Sorting
Normalization
Optimization Solvers
Decision Forest
Decision Trees
Gradient Boosted Trees
Stump
Linear and Ridge Regressions
LASSO and Elastic Net Regressions
k-Nearest Neighbors (kNN) Classifier
Implicit Alternating Least Squares
Logistic Regression
Naïve Bayes Classifier
Support Vector Machine Classifier
Multi-class Classifier
Boosting
Visible to Intel only — GUID: GUID-2BF5E395-4E95-4089-922F-96C1E546180F
csr_table.cpp
/*******************************************************************************
* Copyright 2023 Intel Corporation
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*******************************************************************************/
#include <memory>
#include <numeric>
#include <iostream>
#include <algorithm>
#include "example_util/utils.hpp"
#include "oneapi/dal/table/csr.hpp"
#include "oneapi/dal/table/common.hpp"
#include "oneapi/dal/table/csr_accessor.hpp"
// Generate offsets expecting the table
// to have various amounts of data
// in each row
template <typename Index = std::int64_t>
dal::array<Index> generate_offsets(std::int64_t row_count, std::int64_t column_count) {
const std::int64_t offset_count = row_count + 1l;
Index* const raw_data = new Index[offset_count];
for (std::int64_t row = 0l; row < offset_count; ++row) {
raw_data[row] = static_cast<Index>(row);
}
std::partial_sum(raw_data, raw_data + offset_count, raw_data);
return dal::array<Index>(raw_data,
offset_count, //
[](Index* const ptr) -> void {
delete[] ptr;
});
}
// Generate indices knowing, from the `offsets` array,
// how many elements should be in each row
template <typename Index = std::int64_t>
dal::array<Index> generate_indices(std::int64_t column_count, const dal::array<Index>& offsets) {
const std::int64_t offset_count = offsets.get_count();
const std::int64_t row_count = offset_count - 1l;
const std::int64_t element_count = offsets[row_count];
Index* const raw_data = new Index[element_count];
for (std::int64_t row = 0l; row < row_count; ++row) {
const std::int64_t first = offsets[row];
const std::int64_t last = offsets[row + 1l];
const std::int64_t count = last - first;
for (std::int64_t col = 0l; col < count; ++col) {
const std::int64_t column = column_count - col - 1l;
raw_data[first + col] = static_cast<Index>(column);
}
std::sort(raw_data + first, raw_data + last);
}
return dal::array<Index>(raw_data,
element_count, //
[](Index* const ptr) -> void {
delete[] ptr;
});
}
// Generate data for the table in a deterministic way
template <typename Type = float, typename Index = std::int64_t>
dal::array<Type> generate_data(const dal::array<Index>& offsets) {
const std::int64_t offset_count = offsets.get_count();
const std::int64_t element_count = offsets[offset_count - 1];
Type* const raw_data = new Type[element_count];
for (std::int64_t i = 0l; i < element_count; ++i) {
raw_data[i] = static_cast<Type>(element_count - i);
}
return dal::array<Type>(raw_data,
element_count, //
[](Type* const ptr) -> void {
delete[] ptr;
});
}
int main(int argc, char** argv) {
constexpr std::int64_t row_count = 4;
constexpr std::int64_t column_count = 10;
// Generate data on the host
auto offsets = generate_offsets(row_count, column_count);
auto indices = generate_indices(column_count, offsets);
auto data = generate_data(offsets);
// Wrap previously generated data
dal::csr_table test_table = dal::csr_table::wrap(data, //
indices,
offsets,
column_count,
dal::sparse_indexing::zero_based);
// Sanity checks for the table shape
std::cout << "Number of rows in table: " << test_table.get_row_count() << '\n';
std::cout << "Number of columns in table: " << test_table.get_column_count() << '\n';
// Check the type of abstract table
const bool is_csr = test_table.get_kind() == dal::csr_table::kind();
std::cout << "Is CSR table: " << is_csr << '\n';
// Extract CSR slice of data on the host
dal::csr_accessor<const double> accessor{ test_table };
auto [slice_data, slice_indices, slice_offsets] = accessor.pull({ 1, 3 });
// Print components of slice: data, indices, offsets
std::cout << "Slice of elements (compressed): " << slice_data << '\n';
std::cout << "Slice of indices (compressed): " << slice_indices << '\n';
std::cout << "Slice of offsets: " << slice_offsets << std::endl;
return 0;
}