Intel® oneAPI Data Analytics Library Developer Guide and Reference
ID
772611
Date
7/13/2023
Public
A newer version of this document is available. Customers should click here to go to the newest version.
Visible to Intel only — GUID: GUID-14F33A73-0CA2-4C7B-944F-73CB4D3A9DEF
basic_statistics_dense_batch.cpp
column_accessor_homogen.cpp
cor_dense_batch.cpp
cov_dense_batch.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
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
pca_cor_dense_batch.cpp
pca_precomputed_cor_dense_batch.cpp
pca_precomputed_cov_dense_batch.cpp
rbf_kernel_dense_batch.cpp
svm_two_class_thunder_dense_batch.cpp
basic_statistics_dense_batch.cpp
column_accessor_homogen.cpp
connected_components_batch.cpp
cor_dense_batch.cpp
cov_dense_batch.cpp
csr_accessor.cpp
dbscan_brute_force_batch.cpp
df_cls_dense_batch.cpp
df_reg_dense_batch.cpp
directed_graph.cpp
graph_service_functions.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
logloss_dense_batch.cpp
louvain_batch.cpp
pca_dense_batch.cpp
pca_precomputed_dense_batch.cpp
polynomial_kernel_dense_batch.cpp
rbf_kernel_dense_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
Mathematical Notations
Mathematical Notations
Correlation and Variance-Covariance Matrices
Mathematical Notations
Principal Components Analysis Transform
Singular Value Decomposition
Association Rules
Mathematical Notations
Mathematical Notations
Cholesky Decomposition
QR Decomposition
Outlier Detection
Distance Matrix
Distributions
Engines
Moments of Low Order
Mathematical Notations
Quality Metrics
Sorting
Normalization
Mathematical Notations
Visible to Intel only — GUID: GUID-14F33A73-0CA2-4C7B-944F-73CB4D3A9DEF
df_reg_hist_batch_random.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.
*******************************************************************************/
#ifndef ONEDAL_DATA_PARALLEL
#define ONEDAL_DATA_PARALLEL
#endif
#include "oneapi/dal/algo/decision_forest.hpp"
#include "oneapi/dal/io/csv.hpp"
#include "example_util/utils.hpp"
#include "oneapi/dal/exceptions.hpp"
namespace dal = oneapi::dal;
namespace df = dal::decision_forest;
void run(sycl::queue& q) {
const auto train_data_file_name = get_data_path("df_regression_train_data.csv");
const auto train_response_file_name = get_data_path("df_regression_train_label.csv");
const auto test_data_file_name = get_data_path("df_regression_test_data.csv");
const auto test_response_file_name = get_data_path("df_regression_test_label.csv");
const auto x_train = dal::read<dal::table>(q, dal::csv::data_source{ train_data_file_name });
const auto y_train =
dal::read<dal::table>(q, dal::csv::data_source{ train_response_file_name });
const auto x_test = dal::read<dal::table>(q, dal::csv::data_source{ test_data_file_name });
const auto y_test = dal::read<dal::table>(q, dal::csv::data_source{ test_response_file_name });
const auto df_desc =
df::descriptor<float, df::method::hist, df::task::regression>{}
.set_tree_count(200)
.set_features_per_node(10)
.set_splitter_mode(df::splitter_mode::random)
.set_variable_importance_mode(df::variable_importance_mode::mdi)
.set_min_observations_in_leaf_node(5)
.set_error_metric_mode(df::error_metric_mode::out_of_bag_error |
df::error_metric_mode::out_of_bag_error_per_observation);
try {
const auto result_train = dal::train(q, df_desc, x_train, y_train);
std::cout << "Variable importance results:\n"
<< result_train.get_var_importance() << std::endl;
std::cout << "OOB error: " << result_train.get_oob_err() << std::endl;
std::cout << "OOB error per observation:\n"
<< result_train.get_oob_err_per_observation() << std::endl;
const auto result_infer = dal::infer(q, df_desc, result_train.get_model(), x_test);
std::cout << "Prediction results:\n" << result_infer.get_responses() << std::endl;
std::cout << "Ground truth:\n" << y_test << std::endl;
}
catch (dal::unimplemented& e) {
std::cout << " " << e.what() << std::endl;
return;
}
}
int main(int argc, char const* argv[]) {
for (auto d : list_devices()) {
std::cout << "Running on " << d.get_platform().get_info<sycl::info::platform::name>()
<< ", " << d.get_info<sycl::info::device::name>() << std::endl
<< std::endl;
auto q = sycl::queue{ d };
run(q);
}
return 0;
}