Create a high dimensions test case and fix the build error

HISTORY.md

@@ -1,16 +1,13 @@
 ### mlpack ?.?.?
 ###### ????-??-??
-<<<<<<< HEAD
   * Enforce CMake version check for ensmallen (#2032).
 
   * Fix CMake check for Armadillo version (#2029).
 
 ### mlpack 3.2.0
 ###### 2019-09-25
-=======
   * Fix some potential infinity errors in Naive Bayes Classifier (#2022).
 
->>>>>>> a16d55f... Edit according to comments of Marcus and Ryan.
   * Fix occasionally-failing RADICAL test (#1924).
 
   * Fix gcc 9 OpenMP compilation issue (#1970).

src/mlpack/methods/naive_bayes/naive_bayes_classifier_impl.hpp

@@ -272,8 +272,9 @@ void NaiveBayesClassifier<ModelMatType>::Classify(
   // To prevent underflow in log of sum of exp of x operation (where x is a
   // small negative value), we use logsumexp(x - max(x)) + max(x).
   const double maxValue = arma::max(logLikelihoods);
-  probabilities = exp(logLikelihoods - log(arma::accu(exp(logLikelihoods -
-      maxValue))) + maxValue); // log(exp(value)) == value.
+  const double logProbX = log(arma::accu(exp(logLikelihoods - maxValue))) +
+      maxValue;
+  probabilities = exp(logLikelihoods - logProbX); // log(exp(value)) == value.
 
   arma::uword maxIndex = 0;
   logLikelihoods.max(maxIndex);
@@ -324,7 +325,7 @@ void NaiveBayesClassifier<ModelMatType>::Classify(
   LogLikelihood(data, logLikelihoods);
 
   predictionProbs.set_size(arma::size(logLikelihoods));
-  double maxValue;
+  double maxValue, logProbX;
   for (size_t j = 0; j < data.n_cols; ++j)
   {
     // The LogLikelihood() gives us the unnormalized log likelihood which is
@@ -332,8 +333,9 @@ void NaiveBayesClassifier<ModelMatType>::Classify(
     // Besides, to prevent underflow in log of sum of exp of x operation (where
     // x is a small negative value), we use logsumexp(x - max(x)) + max(x).
     maxValue = arma::max(logLikelihoods.col(j));
-    predictionProbs.col(j) = arma::exp(logLikelihoods.col(j) -
-        log(arma::accu(exp(logLikelihoods.col(j) - maxValue))) + maxValue);
+    logProbX = log(arma::accu(exp(logLikelihoods.col(j) -
+        maxValue))) + maxValue;
+    predictionProbs.col(j) = arma::exp(logLikelihoods.col(j) - logProbX);
   }
 
   // Now calculate maximum probabilities for each point.

src/mlpack/tests/data/nbc_high_dim_test_labels.csv

@@ -0,0 +1,50 @@
+3
+2
+0
+0
+0
+1
+2
+3
+3
+2
+4
+2
+1
+2
+3
+1
+2
+4
+4
+1
+3
+0
+2
+0
+0
+2
+0
+1
+3
+3
+2
+2
+2
+3
+3
+3
+3
+3
+0
+0
+4
+3
+3
+0
+3
+2
+3
+2
+1
+1

src/mlpack/tests/data/nbc_high_dim_train_labels.csv

@@ -0,0 +1,200 @@
+1
+4
+2
+2
+1
+0
+1
+0
+0
+4
+0
+4
+3
+4
+3
+2
+4
+2
+2
+2
+4
+1
+2
+1
+3
+0
+4
+1
+4
+4
+4
+0
+3
+4
+3
+1
+3
+2
+3
+0
+4
+1
+4
+1
+4
+2
+1
+4
+2
+1
+2
+0
+2
+2
+4
+2
+0
+2
+0
+3
+3
+3
+0
+2
+1
+4
+3
+1
+2
+2
+4
+0
+1
+3
+4
+4
+4
+2
+4
+2
+3
+4
+4
+3
+2
+3
+3
+4
+3
+4
+2
+4
+0
+3
+3
+1
+3
+4
+2
+1
+2
+3
+1
+3
+3
+0
+4
+0
+0
+3
+2
+1
+0
+3
+2
+1
+0
+0
+1
+0
+2
+2
+4
+2
+3
+1
+4
+4
+2
+3
+4
+0
+2
+2
+0
+4
+0
+3
+1
+4
+4
+2
+0
+0
+0
+0
+3
+4
+3
+2
+0
+4
+3
+3
+4
+0
+3
+1
+3
+4
+3
+2
+2
+4
+0
+0
+0
+0
+1
+4
+0
+3
+4
+3
+1
+4
+0
+1
+4
+3
+2
+1
+3
+2
+4
+3
+2
+0
+1
+4
+2
+0
+2
+3
+0
+0
+2
+1
+3
+1

src/mlpack/tests/nbc_test.cpp

@@ -314,4 +314,45 @@ BOOST_AUTO_TEST_CASE(SeparateTrainIndividualIncrementalTest)
   }
 }
 
+/**
+ * Check if NaiveBayesClassifier::Classify() works properly for a high
+ * dimension datasets.
+ */
+BOOST_AUTO_TEST_CASE(NaiveBayesClassifierHighDimensionsTest)
+{
+  // Set file names of dataset of training and test.
+  // The training dataset has 5 classes and each class has 1,000 dimensions.
+  const char* trainFilename = "nbc_high_dim_train.csv";
+  const char* testFilename = "nbc_high_dim_test.csv";
+  const char* trainLabelsFileName = "nbc_high_dim_train_labels.csv";
+  const char* testLabelsFilename = "nbc_high_dim_test_labels.csv";
+
+  size_t classes = 5;
+
+  // Create variables for training and assign data to them.
+  arma::mat trainData;
+  arma::Row<size_t> trainLabels;
+  data::Load(trainFilename, trainData, true);
+  data::Load(trainLabelsFileName, trainLabels, true);
+
+  // Initialize and train a NBC model.
+  NaiveBayesClassifier<> nbcTest(trainData, trainLabels, classes);
+
+  // Create variables for test and assign data to them.
+  arma::mat testData, calcProbs;
+  arma::Row<size_t> testLabels;
+  arma::Row<size_t> calcVec;
+  data::Load(testFilename, testData, true);
+  data::Load(testLabelsFilename, testLabels, true);
+
+  // Classify observations in the test dataset. To use Classify() method with
+  // a parameter for probabilities of predictions, we pass 'calcProbs' to the
+  // method.
+  nbcTest.Classify(testData, calcVec, calcProbs);
+
+  // Check the results.
+  for (size_t i = 0; i < calcVec.n_cols; i++)
+    BOOST_REQUIRE_EQUAL(calcVec(i), testLabels(i));
+}
+
 BOOST_AUTO_TEST_SUITE_END();