[mlpack-git] master: rename TrainTestSplit to Split (c8a60b2)
gitdub at mlpack.org
gitdub at mlpack.org
Thu May 26 15:32:39 EDT 2016
Repository : https://github.com/mlpack/mlpack
On branch : master
Link : https://github.com/mlpack/mlpack/compare/e3a23c256f017ebb8185b15847c82f51d359cdfd...181792d99549467440b2b839f52deec75be10334
>---------------------------------------------------------------
commit c8a60b2db341eab52927bb0707dfc3976e437c8b
Author: Keon Kim <kwk236 at gmail.com>
Date: Fri May 27 04:32:39 2016 +0900
rename TrainTestSplit to Split
>---------------------------------------------------------------
c8a60b2db341eab52927bb0707dfc3976e437c8b
src/mlpack/core/data/split_data.hpp | 38 +++++++++++-----------
.../methods/preprocess/preprocess_split_main.cpp | 2 +-
src/mlpack/tests/split_data_test.cpp | 6 ++--
3 files changed, 23 insertions(+), 23 deletions(-)
diff --git a/src/mlpack/core/data/split_data.hpp b/src/mlpack/core/data/split_data.hpp
index b2af0c2..3811320 100644
--- a/src/mlpack/core/data/split_data.hpp
+++ b/src/mlpack/core/data/split_data.hpp
@@ -2,7 +2,7 @@
* @file split_data.hpp
* @author Tham Ngap Wei, Keon Kim
*
- * Defines TrainTestSplit() and LabelTrainTestSplit(), utility functions to split a dataset into a
+ * Defines Split(), a utility function to split a dataset into a
* training set and a test set.
*/
#ifndef MLPACK_CORE_UTIL_SPLIT_DATA_HPP
@@ -28,7 +28,7 @@ namespace data {
*
* // Split the dataset into a training and test set, with 30% of the data being
* // held out for the test set.
- * LabelTrainTestSplit(input, label, trainData,
+ * Split(input, label, trainData,
* testData, trainLabel, testLabel, 0.3);
* @endcode
*
@@ -41,13 +41,13 @@ namespace data {
* @param testRatio Percentage of dataset to use for test set (between 0 and 1).
*/
template<typename T, typename U>
-void LabelTrainTestSplit(const arma::Mat<T>& input,
- const arma::Row<U>& inputLabel,
- arma::Mat<T>& trainData,
- arma::Mat<T>& testData,
- arma::Row<U>& trainLabel,
- arma::Row<U>& testLabel,
- const double testRatio)
+void Split(const arma::Mat<T>& input,
+ const arma::Row<U>& inputLabel,
+ arma::Mat<T>& trainData,
+ arma::Mat<T>& testData,
+ arma::Row<U>& trainLabel,
+ arma::Row<U>& testLabel,
+ const double testRatio)
{
const size_t testSize = static_cast<size_t>(input.n_cols * testRatio);
const size_t trainSize = input.n_cols - testSize;
@@ -86,7 +86,7 @@ void LabelTrainTestSplit(const arma::Mat<T>& input,
*
* // Split the dataset into a training and test set, with 30% of the data being
* // held out for the test set.
- * TrainTestSplit(input, trainData, testData, 0.3);
+ * Split(input, trainData, testData, 0.3);
* @endcode
*
* @param input Input dataset to split.
@@ -95,7 +95,7 @@ void LabelTrainTestSplit(const arma::Mat<T>& input,
* @param testRatio Percentage of dataset to use for test set (between 0 and 1).
*/
template<typename T>
-void TrainTestSplit(const arma::Mat<T>& input,
+void Split(const arma::Mat<T>& input,
arma::Mat<T>& trainData,
arma::Mat<T>& testData,
const double testRatio)
@@ -129,7 +129,7 @@ void TrainTestSplit(const arma::Mat<T>& input,
* @code
* arma::mat input = loadData();
* arma::Row<size_t> label = loadLabel();
- * auto splitResult = LabelTrainTestSplit(input, label, 0.2);
+ * auto splitResult = Split(input, label, 0.2);
* @endcode
*
* @param input Input dataset to split.
@@ -140,16 +140,16 @@ void TrainTestSplit(const arma::Mat<T>& input,
*/
template<typename T,typename U>
std::tuple<arma::Mat<T>, arma::Mat<T>, arma::Row<U>, arma::Row<U>>
-LabelTrainTestSplit(const arma::Mat<T>& input,
- const arma::Row<U>& inputLabel,
- const double testRatio)
+Split(const arma::Mat<T>& input,
+ const arma::Row<U>& inputLabel,
+ const double testRatio)
{
arma::Mat<T> trainData;
arma::Mat<T> testData;
arma::Row<U> trainLabel;
arma::Row<U> testLabel;
- LabelTrainTestSplit(input, inputLabel, trainData, testData, trainLabel, testLabel,
+ Split(input, inputLabel, trainData, testData, trainLabel, testLabel,
testRatio);
return std::make_tuple(trainData, testData, trainLabel, testLabel);
@@ -163,7 +163,7 @@ LabelTrainTestSplit(const arma::Mat<T>& input,
*
* @code
* arma::mat input = loadData();
- * auto splitResult = TrainTestSplit(input, 0.2);
+ * auto splitResult = Split(input, 0.2);
* @endcode
*
* @param input Input dataset to split.
@@ -173,12 +173,12 @@ LabelTrainTestSplit(const arma::Mat<T>& input,
*/
template<typename T>
std::tuple<arma::Mat<T>, arma::Mat<T>>
-TrainTestSplit(const arma::Mat<T>& input,
+Split(const arma::Mat<T>& input,
const double testRatio)
{
arma::Mat<T> trainData;
arma::Mat<T> testData;
- TrainTestSplit(input, trainData, testData, testRatio);
+ Split(input, trainData, testData, testRatio);
return std::make_tuple(trainData, testData);
}
diff --git a/src/mlpack/methods/preprocess/preprocess_split_main.cpp b/src/mlpack/methods/preprocess/preprocess_split_main.cpp
index d6ffb89..dfd79cf 100644
--- a/src/mlpack/methods/preprocess/preprocess_split_main.cpp
+++ b/src/mlpack/methods/preprocess/preprocess_split_main.cpp
@@ -50,7 +50,7 @@ int main(int argc, char** argv)
arma::rowvec labels_row = labels.row(0); // extract first row
// Split Data
- const auto value = data::LabelTrainTestSplit(data, labels_row, testRatio);
+ const auto value = data::Split(data, labels_row, testRatio);
Log::Info << "Train Data Count: " << get<0>(value).n_cols << endl;
Log::Info << "Test Data Count: " << get<1>(value).n_cols << endl;
Log::Info << "Train Label Count: " << get<2>(value).n_cols << endl;
diff --git a/src/mlpack/tests/split_data_test.cpp b/src/mlpack/tests/split_data_test.cpp
index 462708e..700e31a 100644
--- a/src/mlpack/tests/split_data_test.cpp
+++ b/src/mlpack/tests/split_data_test.cpp
@@ -73,11 +73,11 @@ BOOST_AUTO_TEST_CASE(SplitDataSplitResultMat)
input.randu();
// Set the labels to the column ID, so that CompareData can compare the data
- // after LabelTrainTestSplit is called.
+ // after Split is called.
const Row<size_t> labels = arma::linspace<Row<size_t>>(0, input.n_cols - 1,
input.n_cols);
- const auto value = LabelTrainTestSplit(input, labels, 0.2);
+ const auto value = Split(input, labels, 0.2);
BOOST_REQUIRE_EQUAL(std::get<0>(value).n_cols, 8);
BOOST_REQUIRE_EQUAL(std::get<1>(value).n_cols, 2);
BOOST_REQUIRE_EQUAL(std::get<2>(value).n_cols, 8);
@@ -103,7 +103,7 @@ BOOST_AUTO_TEST_CASE(SplitDataLargerTest)
const Row<size_t> labels = arma::linspace<Row<size_t>>(0, input.n_cols - 1,
input.n_cols);
- const auto value = LabelTrainTestSplit(input, labels, 0.3);
+ const auto value = Split(input, labels, 0.3);
BOOST_REQUIRE_EQUAL(std::get<0>(value).n_cols, 497 - size_t(0.3 * 497));
BOOST_REQUIRE_EQUAL(std::get<1>(value).n_cols, size_t(0.3 * 497));
BOOST_REQUIRE_EQUAL(std::get<2>(value).n_cols, 497 - size_t(0.3 * 497));
More information about the mlpack-git
mailing list