From b92a3e5a2de20914fd379bd1f804e5da2f78ec80 Mon Sep 17 00:00:00 2001
From: Marcus Edel <marcus.edel@fu-berlin.de>
Date: Mon, 18 Sep 2017 15:31:12 +0200
Subject: [PATCH] Add SPALERA optimizer test case.

---
 src/mlpack/tests/CMakeLists.txt       |  1 +
 src/mlpack/tests/spalera_sgd_test.cpp | 89 +++++++++++++++++++++++++++
 2 files changed, 90 insertions(+)
 create mode 100644 src/mlpack/tests/spalera_sgd_test.cpp

diff --git a/src/mlpack/tests/CMakeLists.txt b/src/mlpack/tests/CMakeLists.txt
index 24d3f33054..880b137fe5 100644
--- a/src/mlpack/tests/CMakeLists.txt
+++ b/src/mlpack/tests/CMakeLists.txt
@@ -106,6 +106,7 @@ add_executable(mlpack_test
   snapshot_ensembles.cpp
   softmax_regression_test.cpp
   sort_policy_test.cpp
+  spalera_sgd_test.cpp
   sparse_autoencoder_test.cpp
   sparse_coding_test.cpp
   spill_tree_test.cpp
diff --git a/src/mlpack/tests/spalera_sgd_test.cpp b/src/mlpack/tests/spalera_sgd_test.cpp
new file mode 100644
index 0000000000..c07e337054
--- /dev/null
+++ b/src/mlpack/tests/spalera_sgd_test.cpp
@@ -0,0 +1,89 @@
+/**
+ * @file spalera_sgd_test.cpp
+ * @author Marcus Edel
+ *
+ * Test file for SGD (stochastic gradient descent).
+ *
+ * mlpack is free software; you may redistribute it and/or modify it under the
+ * terms of the 3-clause BSD license.  You should have received a copy of the
+ * 3-clause BSD license along with mlpack.  If not, see
+ * http://www.opensource.org/licenses/BSD-3-Clause for more information.
+ */
+#include <mlpack/core.hpp>
+#include <mlpack/core/optimizers/spalera_sgd/spalera_sgd.hpp>
+#include <mlpack/methods/logistic_regression/logistic_regression.hpp>
+
+#include <boost/test/unit_test.hpp>
+#include "test_tools.hpp"
+
+using namespace mlpack;
+using namespace mlpack::optimization;
+using namespace mlpack::distribution;
+using namespace mlpack::regression;
+
+BOOST_AUTO_TEST_SUITE(SPALeRASGDTest);
+
+/**
+ * Run SPALeRA SGD on logistic regression and make sure the results are
+ * acceptable.
+ */
+BOOST_AUTO_TEST_CASE(LogisticRegressionTest)
+{
+  // Generate a two-Gaussian dataset.
+  GaussianDistribution g1(arma::vec("1.0 1.0 1.0"), arma::eye<arma::mat>(3, 3));
+  GaussianDistribution g2(arma::vec("9.0 9.0 9.0"), arma::eye<arma::mat>(3, 3));
+
+  arma::mat data(3, 500);
+  arma::Row<size_t> responses(500);
+  for (size_t i = 0; i < 250; ++i)
+  {
+    data.col(i) = g1.Random();
+    responses[i] = 0;
+  }
+  for (size_t i = 250; i < 500; ++i)
+  {
+    data.col(i) = g2.Random();
+    responses[i] = 1;
+  }
+
+  // Shuffle the dataset.
+  arma::uvec indices = arma::shuffle(arma::linspace<arma::uvec>(0,
+      data.n_cols - 1, data.n_cols));
+  arma::mat shuffledData(3, 500);
+  arma::Row<size_t> shuffledResponses(500);
+  for (size_t i = 0; i < data.n_cols; ++i)
+  {
+    shuffledData.col(i) = data.col(indices[i]);
+    shuffledResponses[i] = responses[indices[i]];
+  }
+
+  // Create a test set.
+  arma::mat testData(3, 500);
+  arma::Row<size_t> testResponses(500);
+  for (size_t i = 0; i < 250; ++i)
+  {
+    testData.col(i) = g1.Random();
+    testResponses[i] = 0;
+  }
+  for (size_t i = 250; i < 500; ++i)
+  {
+    testData.col(i) = g2.Random();
+    testResponses[i] = 1;
+  }
+
+  // Now run mini-batch SGD with a couple of batch sizes.
+  for (size_t batchSize = 5; batchSize < 50; batchSize += 5)
+  {
+    SPALeRASGD<> mbsgd(batchSize, 0.01, 10000, 1e-3);
+    LogisticRegression<> lr(shuffledData, shuffledResponses, mbsgd, 0.5);
+
+    // Ensure that the error is close to zero.
+    const double acc = lr.ComputeAccuracy(data, responses);
+    BOOST_REQUIRE_CLOSE(acc, 100.0, 0.3); // 0.3% error tolerance.
+
+    const double testAcc = lr.ComputeAccuracy(testData, testResponses);
+    BOOST_REQUIRE_CLOSE(testAcc, 100.0, 0.6); // 0.6% error tolerance.
+  }
+}
+
+BOOST_AUTO_TEST_SUITE_END();