[mlpack-git] master: Add command line parameter to calculate the effective error. (9a8a9eb)

[gitdub at mlpack.org]

Repository : https://github.com/mlpack/mlpack
On branch  : master
Link       : https://github.com/mlpack/mlpack/compare/0f4b25acd6aaa14294c044874ba6cc0751712baa...0a19d07bd39e6223991976474bc79671ba8aa0f0

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

commit 9a8a9eb789f5a423faad41314314db22f7f59aa2
Author: MarcosPividori <marcos.pividori at gmail.com>
Date:   Thu Aug 11 16:06:28 2016 -0300

    Add command line parameter to calculate the effective error.


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

9a8a9eb789f5a423faad41314314db22f7f59aa2
 src/mlpack/methods/neighbor_search/knn_main.cpp | 26 +++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/src/mlpack/methods/neighbor_search/knn_main.cpp b/src/mlpack/methods/neighbor_search/knn_main.cpp
index 97db49d..0505687 100644
--- a/src/mlpack/methods/neighbor_search/knn_main.cpp
+++ b/src/mlpack/methods/neighbor_search/knn_main.cpp
@@ -82,6 +82,9 @@ PARAM_FLAG("single_mode", "If true, single-tree search is used (as opposed to "
     "dual-tree search).", "S");
 PARAM_DOUBLE_IN("epsilon", "If specified, will do approximate nearest neighbor "
     "search with given relative error.", "e", 0);
+PARAM_STRING_IN("effective_error", "If specified, will compare the results "
+    "against the provided distances file, and will print the average relative "
+    "error.", "E", "");
 
 // Convenience typedef.
 typedef NSModel<NearestNeighborSort> KNNModel;
@@ -292,6 +295,29 @@ int main(int argc, char *argv[])
       data::Save(CLI::GetParam<string>("neighbors_file"), neighbors);
     if (CLI::HasParam("distances_file"))
       data::Save(CLI::GetParam<string>("distances_file"), distances);
+
+    // Calculate the effective error, if desired.
+    if (CLI::HasParam("effective_error"))
+    {
+      const string exactFile = CLI::GetParam<string>("effective_error");
+      arma::mat distancesExact;
+      data::Load(exactFile, distancesExact, true);
+
+      if (distancesExact.n_elem != distances.n_elem)
+        Log::Fatal << "The effective error file must have the same number of "
+          << "values than the set of distances being queried!" << endl;
+
+      double effectiveError = 0;
+      for (size_t i = 0; i < distances.n_elem; i++)
+      {
+        if (distancesExact(i) != 0 && distances(i) != DBL_MAX)
+          effectiveError += (distances(i) - distancesExact(i)) /
+              distancesExact(i);
+      }
+      effectiveError /= distances.n_elem;
+
+      Log::Info << "Effective error: " << effectiveError << endl;
+    }
   }
 
   if (CLI::HasParam("output_model_file"))