Changeset 1142 for trunk/yat/classifier

Timestamp:

Feb 25, 2008, 3:32:35 PM (13 years ago)

Author:

Markus Ringnér

Message:

Refs #335, fixed for NCC, working on KNN

Location:

trunk/yat/classifier

Files:

• KNN.h (modified) (7 diffs)
• KNN_ReciprocalDistance.h (modified) (1 diff)
• KNN_ReciprocalRank.h (modified) (1 diff)
• KNN_Uniform.cc (modified) (1 diff)
• KNN_Uniform.h (modified) (1 diff)
• NCC.h (modified) (3 diffs)

trunk/yat/classifier/KNN.h

@@ -85 +85 @@
 
     ///
-    /// @brief sets the number of neighbors, k.
-    ///
-    void k(u_int);
+    /// @brief sets the number of neighbors, k. If the number of
+    /// training samples set is smaller than \a k_in, k is set to the number of
+    /// training samples.
+    ///
+    void k(u_int k_in);
 
 
@@ -144 +146 @@
     : SupervisedClassifier(target), data_(data),k_(3)
   {
+    utility::yat_assert<std::runtime_error>
+      (data.columns()==target.size(),
+       "KNN::KNN called with different sizes of target and data");
+    // k has to be at most the number of training samples.
+    if(data_.columns()>k_) 
+      k_=data_.columns();
   }
 
@@ -152 +160 @@
     : SupervisedClassifier(target), data_(data),k_(3)
   {
+    utility::yat_assert<std::runtime_error>
+      (data.columns()==target.size(),
+       "KNN::KNN called with different sizes of target and data");
+    if(data_.columns()>k_) 
+      k_=data_.columns();
   }
   
@@ -232 +245 @@
         (*distances)(i,j) = distance_(training1.begin(), training1.end(), 
                                       test1.begin());
-        utility::yat_assert<std::runtime_error>(!std::isnan((*distances)(i,j)));
       }
     }
@@ -255 +267 @@
   {
     k_=k;
+    if(k_>data_.columns())
+      k_=data_.columns();
   }
 
@@ -295 +309 @@
                                                  utility::Matrix& prediction) const
   {   
-    utility::yat_assert<std::runtime_error>(data_.rows()==test.rows());
+    utility::yat_assert<std::runtime_error>(data_.rows()==test.rows(),"KNN::predict different number of rows in training and test data");
 
     utility::Matrix* distances=calculate_distances(test);
@@ -308 +322 @@
     }
     delete distances;
+
+    // classes for which there are no training samples should be set
+    // to nan in the predictions
+    for(size_t c=0;c<target_.nof_classes(); c++) 
+      if(!target_.size(c)) 
+        for(size_t j=0;j<prediction.columns();j++)
+          prediction(c,j)=std::numeric_limits<double>::quiet_NaN();
   }
 

trunk/yat/classifier/KNN_ReciprocalDistance.h

@@ -3 +3 @@
 
 // $Id$
+
+/*
+  Copyright (C) 2008 Markus Ringnér
+
+  This file is part of the yat library, http://trac.thep.lu.se/yat
+
+  The yat library is free software; you can redistribute it and/or
+  modify it under the terms of the GNU General Public License as
+  published by the Free Software Foundation; either version 2 of the
+  License, or (at your option) any later version.
+
+  The yat library is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+  General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+  02111-1307, USA.
+*/
+
 
 #include <vector>

trunk/yat/classifier/KNN_ReciprocalRank.h

@@ -3 +3 @@
 
 // $Id$
+
+/*
+  Copyright (C) 2008 Markus Ringnér
+
+  This file is part of the yat library, http://trac.thep.lu.se/yat
+
+  The yat library is free software; you can redistribute it and/or
+  modify it under the terms of the GNU General Public License as
+  published by the Free Software Foundation; either version 2 of the
+  License, or (at your option) any later version.
+
+  The yat library is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+  General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+  02111-1307, USA.
+*/
 
 

trunk/yat/classifier/KNN_Uniform.cc

@@ -18 +18 @@
                                utility::VectorMutable& prediction) const
   {           
-    std::vector<size_t>::size_type k=k_sorted.size();
-    for(size_t j=0;j<k;j++) 
+    for(size_t j=0;j<k_sorted.size();j++) 
       prediction(target(k_sorted[j]))+=1.0;           
   }

trunk/yat/classifier/KNN_Uniform.h

@@ -3 +3 @@
 
 // $Id$
+
+/*
+  Copyright (C) 2008 Markus Ringnér
+
+  This file is part of the yat library, http://trac.thep.lu.se/yat
+
+  The yat library is free software; you can redistribute it and/or
+  modify it under the terms of the GNU General Public License as
+  published by the Free Software Foundation; either version 2 of the
+  License, or (at your option) any later version.
+
+  The yat library is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+  General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+  02111-1307, USA.
+*/
+
 
 #include <vector>

trunk/yat/classifier/NCC.h

@@ -198 +198 @@
           if(class_averager[c].sum_w()==0) {
             centroids_nan_=true;
-            (*centroids_)(i,c) = std::numeric_limits<double>::quiet_NaN();
           }
-          else {
-            (*centroids_)(i,c) = class_averager[c].mean();
-          }
+          (*centroids_)(i,c) = class_averager[c].mean();
         }
       }
@@ -262 +259 @@
                                          utility::Matrix& prediction) const
   {
-    MatrixLookup unweighted_centroids(*centroids_);
-    for(size_t j=0; j<test.columns();j++) {       
-      DataLookup1D in(test,j,false);
-      for(size_t k=0; k<centroids_->columns();k++) {
-        DataLookup1D centroid(unweighted_centroids,k,false);            
-        utility::yat_assert<std::runtime_error>(in.size()==centroid.size());
-        prediction(k,j) = distance_(in.begin(), in.end(), centroid.begin());
-      }
-    }
-  }
-
+    MatrixLookup centroids(*centroids_);
+    for(size_t j=0; j<test.columns();j++)
+      for(size_t k=0; k<centroids_->columns();k++) 
+        prediction(k,j) = distance_(test.begin_column(j), test.end_column(j), 
+                                    centroids.begin_column(k));
+  }
+  
   template <typename Distance>
   void NCC<Distance>::predict_weighted(const MatrixLookupWeighted& test, 
@@ -278 +271 @@
   {
     MatrixLookupWeighted weighted_centroids(*centroids_);
-    for(size_t j=0; j<test.columns();j++) {       
-      DataLookupWeighted1D in(test,j,false);
-      for(size_t k=0; k<centroids_->columns();k++) {
-        DataLookupWeighted1D centroid(weighted_centroids,k,false);
-        utility::yat_assert<std::runtime_error>(in.size()==centroid.size());
-        prediction(k,j) = distance_(in.begin(), in.end(), centroid.begin());
-      }
-    }
+    for(size_t j=0; j<test.columns();j++) 
+      for(size_t k=0; k<centroids_->columns();k++)
+        prediction(k,j) = distance_(test.begin_column(j), test.end_column(j), 
+                                    weighted_centroids.begin_column(k));
   }