Added Confusionmatrix function

src/mlpack/core.hpp

@@ -88,6 +88,7 @@
 #include <mlpack/core/dists/laplace_distribution.hpp>
 #include <mlpack/core/dists/gamma_distribution.hpp>
 #include <mlpack/core/dists/diagonal_gaussian_distribution.hpp>
+#include <mlpack/core/data/confusion_matrix.hpp>
 
 // mlpack::backtrace only for linux
 #ifdef HAS_BFD_DL

src/mlpack/core/data/CMakeLists.txt

@@ -24,6 +24,7 @@ set(SOURCES
   split_data.hpp
   imputer.hpp
   binarize.hpp
+  confusion_matrix.hpp
 )
 
 # add directory name to sources

src/mlpack/core/data/confusion_matrix.hpp

@@ -0,0 +1,53 @@
+/**
+ * @file confusion_matrix_impl.hpp
+ * @author Jeffin Sam
+ *
+ * Compute confusion matrix to evaluate the accuracy of a classification.
+ * The function works only for discrete data/categorical data.
+ *
+ * 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.
+ */
+#ifndef MLPACK_CORE_DATA_CONFUSION_MATRIX_HPP
+#define MLPACK_CORE_DATA_CONFUSION_MATRIX_HPP
+
+#include <mlpack/prereqs.hpp>
+
+namespace mlpack {
+namespace data {
+
+/**
+ * A confusion matrix is a summary of prediction results on a classification
+ * problem.The number of correct and incorrect predictions are summarized
+ * with count values and broken down by each class.
+ * for example for 2 classes the function will be
+ * confusionmatrix(predictors, responses, output, 2)
+ * output matrix will be of size 2 * 2
+ *
+ *         0     1
+ *    0    TP    FN
+ *    1    FP    TN
+ *
+ * Confusion matrix for two labels will look like above.
+ * Row is the predicted values and column are actual values.
+ *
+ * @param predictors Vector of data points.
+ * @param responses The measured data for each point in X.
+ * @param output Matrix which is represented as confusion matrix.
+ * @param countlables No of classes
+ *
+ */
+template<typename eT>
+void ConfusionMatrix(const arma::Row<size_t> predictors,
+                     const arma::Row<size_t> responses,
+                     arma::Mat<eT>& output,
+                     const size_t countlabels);
+} // namespace data
+} // namespace mlpack
+
+// Include implementation.
+#include "confusion_matrix_impl.hpp"
+
+#endif

src/mlpack/core/data/confusion_matrix_impl.hpp

@@ -0,0 +1,59 @@
+/**
+ * @file confusion_matrix_impl.hpp
+ * @author Jeffin Sam
+ *
+ * Compute confusion matrix to evaluate the accuracy of a classification.
+ * The function works only for discrete data/categorical data.
+ *
+ * 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.
+ */
+#ifndef MLPACK_CORE_DATA_CONFUSION_MATRIX_IMPL_HPP
+#define MLPACK_CORE_DATA_CONFUSION_MATRIX_IMPL_HPP
+
+// In case it hasn't been included yet.
+#include "confusion_matrix.hpp"
+
+namespace mlpack {
+namespace data {
+
+/**
+ * A confusion matrix is a summary of prediction results on a classification
+ * problem.The number of correct and incorrect predictions are summarized
+ * with count values and broken down by each class.
+ * for example for 2 classes the function will be
+ * confusionmatrix(predictors, responses, output, 2)
+ * output matrix will be of size 2 * 2
+ *
+ *         0     1
+ *    0    TP    FN
+ *    1    FP    TN
+ *
+ * Confusion matrix for two labels will look like above.
+ * Row is the predicted values and column are actual values.
+ *
+ * @param predictors Vector of data points.
+ * @param responses The measured data for each point in X.
+ * @param output Matrix which is represented as confusion matrix.
+ * @param countlables No of classes
+ *
+ */
+template<typename eT>
+void ConfusionMatrix(const arma::Row<size_t> predictors,
+                     const arma::Row<size_t> responses,
+                     arma::Mat<eT>& output,
+                     const size_t countlabels)
+{
+  // Loop over the actual labels and predicted labels and add the count
+  output = arma::zeros<arma::Mat<eT> >(countlabels, countlabels);
+  for (size_t i = 0; i < predictors.n_elem; ++i)
+  {
+    output.at(predictors[i], responses[i])++;
+  }
+}
+} // namespace data
+} // namespace mlpack
+
+#endif

src/mlpack/tests/cv_test.cpp

@@ -31,7 +31,7 @@
 #include <mlpack/methods/logistic_regression/logistic_regression.hpp>
 #include <mlpack/methods/naive_bayes/naive_bayes_classifier.hpp>
 #include <mlpack/methods/softmax_regression/softmax_regression.hpp>
-
+#include <mlpack/core/data/confusion_matrix.hpp>
 #include <ensmallen.hpp>
 
 #include <boost/test/unit_test.hpp>
@@ -43,6 +43,7 @@ using namespace mlpack::cv;
 using namespace mlpack::naive_bayes;
 using namespace mlpack::regression;
 using namespace mlpack::tree;
+using namespace mlpack::data;
 
 BOOST_AUTO_TEST_SUITE(CVTest);
 
@@ -73,6 +74,25 @@ BOOST_AUTO_TEST_CASE(BinaryClassificationMetricsTest)
   BOOST_REQUIRE_CLOSE(F1<Binary>::Evaluate(lr, data, labels), f1, 1e-5);
 }
 
+/**
+ * Test for confusion matrix.
+ */
+BOOST_AUTO_TEST_CASE(ConfusionMatrixTest)
+{
+  // Labels that will be considered as "ground truth".
+  arma::Row<size_t> labels("0 0 1 0 0  1 0 1 0 1");
+
+  // Predicted labels.
+  arma::Row<size_t> predictedLabels("0 0 0 0 0  1 1 1 1 1");
+  // Confusion matrix.
+  arma::Mat<int> output;
+  data::ConfusionMatrix(predictedLabels, labels, output, 2);
+  BOOST_REQUIRE_EQUAL(output(0, 0), 4);
+  BOOST_REQUIRE_EQUAL(output(0, 1), 1);
+  BOOST_REQUIRE_EQUAL(output(1, 0), 2);
+  BOOST_REQUIRE_EQUAL(output(1, 1), 3);
+}
+
 /**
  * Test metrics for multiclass classification.
  */