[mlpack-git] master, mlpack-1.0.x: IsDistinct() improved. (94be125)

[gitdub at big.cc.gt.atl.ga.us]

Repository : https://github.com/mlpack/mlpack

On branches: master,mlpack-1.0.x
Link       : https://github.com/mlpack/mlpack/compare/904762495c039e345beba14c1142fd719b3bd50e...f94823c800ad6f7266995c700b1b630d5ffdcf40

>---------------------------------------------------------------

commit 94be1252d8d6ed80145b1d894ba7e228df111cbc
Author: Udit Saxena <saxena.udit at gmail.com>
Date:   Wed Jul 9 20:15:45 2014 +0000

    IsDistinct() improved.


>---------------------------------------------------------------

94be1252d8d6ed80145b1d894ba7e228df111cbc
 src/mlpack/methods/decision_stump/decision_stump.hpp   |  2 +-
 .../methods/decision_stump/decision_stump_impl.hpp     | 15 ++++++++-------
 src/mlpack/tests/decision_stump_test.cpp               | 18 ------------------
 3 files changed, 9 insertions(+), 26 deletions(-)

diff --git a/src/mlpack/methods/decision_stump/decision_stump.hpp b/src/mlpack/methods/decision_stump/decision_stump.hpp
index 2e57d05..fb4d6c9 100644
--- a/src/mlpack/methods/decision_stump/decision_stump.hpp
+++ b/src/mlpack/methods/decision_stump/decision_stump.hpp
@@ -123,7 +123,7 @@ class DecisionStump
    *
    * @param featureRow The attribute which is checked for identical values.
    */
-  template <typename rType> int isDistinct(const arma::Row<rType>& featureRow);
+  template <typename rType> int IsDistinct(const arma::Row<rType>& featureRow);
 
   /**
    * Calculate the entropy of the given attribute.
diff --git a/src/mlpack/methods/decision_stump/decision_stump_impl.hpp b/src/mlpack/methods/decision_stump/decision_stump_impl.hpp
index cfe4388..7300521 100644
--- a/src/mlpack/methods/decision_stump/decision_stump_impl.hpp
+++ b/src/mlpack/methods/decision_stump/decision_stump_impl.hpp
@@ -44,13 +44,13 @@ DecisionStump<MatType>::DecisionStump(const MatType& data,
   for (int i = 0; i < data.n_rows; i++)
   {
     // Go through each attribute of the data.
-    if (isDistinct<double>(data.row(i)))
+    if (IsDistinct<double>(data.row(i)))
     {
       // For each attribute with non-identical values, treat it as a potential
       // splitting attribute and calculate entropy if split on it.
       entropy = SetupSplitAttribute(data.row(i), labels);
 
-      Log::Debug << "Entropy for attribute " << i << " is " << entropy << ".\n";
+      // Log::Debug << "Entropy for attribute " << i << " is " << entropy << ".\n";
       gain = rootEntropy - entropy;
       // Find the attribute with the best entropy so that the gain is
       // maximized.
@@ -351,12 +351,13 @@ rType DecisionStump<MatType>::CountMostFreq(const arma::Row<rType>& subCols)
  */
 template <typename MatType>
 template <typename rType>
-int DecisionStump<MatType>::isDistinct(const arma::Row<rType>& featureRow)
+int DecisionStump<MatType>::IsDistinct(const arma::Row<rType>& featureRow)
 {
-  if (featureRow.max() - featureRow.min() > 0)
-    return 1;
-  else
-    return 0;
+  rType val = featureRow(0);
+  for (size_t i = 1; i < featureRow.n_elem; ++i)
+    if (val != featureRow(i))
+      return 1;
+  return 0;
 }
 
 /**
diff --git a/src/mlpack/tests/decision_stump_test.cpp b/src/mlpack/tests/decision_stump_test.cpp
index a56dff8..dec4f2c 100644
--- a/src/mlpack/tests/decision_stump_test.cpp
+++ b/src/mlpack/tests/decision_stump_test.cpp
@@ -307,22 +307,4 @@ BOOST_AUTO_TEST_CASE(DimensionSelectionTest)
   }
 }
 
-BOOST_AUTO_TEST_CASE(TempAttributeSplit)
-{
-  const size_t numClasses = 2;
-  const size_t inpBucketSize = 3;
-
-  mat trainingData;
-  trainingData << 1 << 1 << 1 << 2 << 2 << 2 << endr
-               << 0.5  << 0.6  << 0.7  << 0.4  << 0.3  << 0.5 << endr;
-
-  Mat<size_t> labelsIn;
-  labelsIn << 0 << 0 << 0 << 0 << 1 << 1 << 1;
-
-  DecisionStump<> ds(trainingData, labelsIn.row(0), numClasses, inpBucketSize);
-
-  // Row<size_t> predictedLabels(testingData.n_cols);
-  // ds.Classify(testingData, predictedLabels);
-  BOOST_CHECK_EQUAL(ds.SplitAttribute(), 0);
-}
 BOOST_AUTO_TEST_SUITE_END();