Changeset 1718

Timestamp:

Jan 14, 2009, 4:42:57 PM (14 years ago)

Author:

Jari Häkkinen

Message:

Addresses #425. Improved docs. Fixed a bug in the normalization.

Location:

trunk/yat/normalizer

Files:

• qQuantileNormalizer.cc (modified) (4 diffs)
• qQuantileNormalizer.h (modified) (3 diffs)

trunk/yat/normalizer/qQuantileNormalizer.cc

@@ -82 +82 @@
     : target_(Partitioner(target,Q))
   {
+    assert(Q>2); // required by cspline fit
   }
 
@@ -110 +111 @@
       for (size_t row=start; row<end; ++row) {
         size_t srow=sorted_index[column][row];
-        result(srow,column) = matrix(srow,column) + diff(0);
+        result(srow,column) = matrix(srow,column) - diff(0);
       }
 
@@ -119 +120 @@
       for (size_t row=start; row<=end; ++row) {
         size_t srow=sorted_index[column][row];
-        result(srow,column) = matrix(srow,column) + cspline.evaluate(row) ;
+        result(srow,column) = matrix(srow,column) - cspline.evaluate(row) ;
       }
 
@@ -128 +129 @@
       for (size_t row=start; row<end; ++row) {
         size_t srow=sorted_index[column][row];
-        result(srow,column) = matrix(srow,column) + diff(diff.size()-1);
+        result(srow,column) = matrix(srow,column) - diff(diff.size()-1);
       }
     }

trunk/yat/normalizer/qQuantileNormalizer.h

@@ -43 +43 @@
      The normalization goes like this
      - Data is not assumed to be sorted.
-     - Partition the target data in N parts.
+     - Partition the target data in N parts. N must be 3 larger
+       because of requirements from the underlying cspline fit
      - Calculate the arithmetic mean for each part, the mean is
        assigned to the mid point of each part.
@@ -67 +68 @@
        \brief Documentation please.
 
-       \a Q is the number of parts and must be within \f$ [2,N] \f$
+       \a Q is the number of parts and must be within \f$ [3,N] \f$
        where \f$ N \f$ is the total number of data points in the
        target. However, if \f$ N \f$ is larger than the number of points
@@ -73 +74 @@
        undefined. Keep \f$ N \f$ equal to or less than the smallest
        number of data points in the target or each data set to be
-       normalized against a ginven target.
+       normalized against a ginven target. The lower bound of three is
+       due to restrictions in the cspline fit utilized in the
+       normalization.
     */
     qQuantileNormalizer(const utility::VectorBase& target, unsigned int Q);