[1708] | 1 | #ifndef _theplu_yat_normalizer_qquantile_normalizer_ |
---|
| 2 | #define _theplu_yat_normalizer_qquantile_normalizer_ |
---|
| 3 | |
---|
| 4 | /* |
---|
| 5 | Copyright (C) 2009 Jari Häkkinen |
---|
| 6 | |
---|
| 7 | This file is part of the yat library, http://dev.thep.lu.se/yat |
---|
| 8 | |
---|
| 9 | The yat library is free software; you can redistribute it and/or |
---|
| 10 | modify it under the terms of the GNU General Public License as |
---|
| 11 | published by the Free Software Foundation; either version 3 of the |
---|
| 12 | License, or (at your option) any later version. |
---|
| 13 | |
---|
| 14 | The yat library is distributed in the hope that it will be useful, |
---|
| 15 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
---|
| 16 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
---|
| 17 | General Public License for more details. |
---|
| 18 | |
---|
| 19 | You should have received a copy of the GNU General Public License |
---|
| 20 | along with yat. If not, see <http://www.gnu.org/licenses/>. |
---|
| 21 | */ |
---|
| 22 | |
---|
| 23 | #include "yat/utility/Vector.h" |
---|
| 24 | |
---|
| 25 | namespace theplu { |
---|
| 26 | namespace yat { |
---|
| 27 | namespace utility { |
---|
| 28 | class Matrix; |
---|
| 29 | class VectorConstView; |
---|
| 30 | } |
---|
| 31 | namespace normalizer { |
---|
| 32 | |
---|
| 33 | /** |
---|
| 34 | \brief Documentation please. |
---|
| 35 | */ |
---|
| 36 | class Partitioner |
---|
| 37 | { |
---|
| 38 | public: |
---|
| 39 | /** |
---|
| 40 | \brief Documentation please. |
---|
| 41 | */ |
---|
| 42 | Partitioner(const utility::VectorConstView& vec, unsigned int N); |
---|
| 43 | |
---|
| 44 | /** |
---|
| 45 | \brief Documentation please. |
---|
| 46 | */ |
---|
| 47 | const utility::Vector& averages(void) const; |
---|
| 48 | |
---|
| 49 | /** |
---|
| 50 | \brief Documentation please. |
---|
| 51 | */ |
---|
| 52 | const utility::Vector& index(void) const; |
---|
| 53 | |
---|
| 54 | /** |
---|
[1709] | 55 | \brief The number of parts. |
---|
[1708] | 56 | */ |
---|
| 57 | size_t size(void) const; |
---|
| 58 | |
---|
| 59 | private: |
---|
| 60 | utility::Vector average_; |
---|
| 61 | utility::Vector index_; |
---|
| 62 | }; |
---|
| 63 | |
---|
| 64 | |
---|
| 65 | /** |
---|
| 66 | \brief Perform Q-quantile normalization |
---|
| 67 | |
---|
| 68 | After a Q-quantile normalization each column has the same |
---|
| 69 | distribution of data (the Q-quantiles are the same). Also, within |
---|
| 70 | each column the rank of an element is not changed. |
---|
| 71 | |
---|
| 72 | There is currently no weighted version of qQuantileNormalizer |
---|
| 73 | |
---|
| 74 | The normalization goes like this |
---|
| 75 | |
---|
| 76 | 0. Data is not assumed to be sorted. |
---|
| 77 | |
---|
| 78 | 1. Partition the target data in N+1 parts. The ends have half |
---|
[1711] | 79 | size of the "normal" part size ( = \#targetdata/N ) |
---|
[1708] | 80 | |
---|
| 81 | 2. Calculate the arithmetic mean for each part |
---|
| 82 | |
---|
| 83 | 3. Do the same for the data to be tranformed (called source |
---|
| 84 | here). |
---|
| 85 | |
---|
| 86 | 4. For each part, calculate the difference between the target and |
---|
| 87 | the source. Now we have N differences d_i. |
---|
| 88 | |
---|
| 89 | 5. Create a cubic spline fit to this difference vector d. The |
---|
| 90 | resulting curve is used to recalculate all column values. |
---|
| 91 | |
---|
| 92 | I. For values in parts 1 through N-1 we use a cubic spline |
---|
| 93 | fit. |
---|
| 94 | |
---|
| 95 | II. For end parts 0 and N linear interpolation is used |
---|
| 96 | |
---|
| 97 | Linear interpolation simply means a translation. |
---|
| 98 | |
---|
| 99 | \since New in yat 0.5 |
---|
| 100 | */ |
---|
| 101 | class qQuantileNormalizer |
---|
| 102 | { |
---|
| 103 | public: |
---|
| 104 | /** |
---|
| 105 | \brief Documentation please. |
---|
| 106 | |
---|
[1711] | 107 | \a Q is the number of parts and must be within \f$ [2,N] \f$ |
---|
| 108 | where \f$ N \f$ is the total number of data points in the |
---|
| 109 | target. However, if \f$ N \f$ is larger than the number of points |
---|
[1708] | 110 | in the data to be normalized the behaviour of the code is |
---|
[1711] | 111 | undefined. Keep \f$ N \f$ equal to or less than the smallest |
---|
[1708] | 112 | number of data points in the target or each data set to be |
---|
| 113 | normalized with a ginven target. |
---|
| 114 | */ |
---|
| 115 | qQuantileNormalizer(const utility::VectorConstView& target, |
---|
| 116 | unsigned int Q); |
---|
| 117 | |
---|
| 118 | /** |
---|
| 119 | \brief perform the Q-quantile normalization. |
---|
| 120 | |
---|
| 121 | It is possible to normalize "in place"; it is permissible for |
---|
| 122 | \a matrix and \a result to reference the same Matrix. |
---|
| 123 | |
---|
| 124 | \note dimensions of \a matrix and \a result must match. |
---|
| 125 | */ |
---|
| 126 | void operator()(const utility::Matrix& matrix, |
---|
| 127 | utility::Matrix& result) const; |
---|
| 128 | |
---|
| 129 | private: |
---|
| 130 | Partitioner target_; |
---|
| 131 | }; |
---|
| 132 | |
---|
| 133 | }}} // end of namespace normalizer, yat and thep |
---|
| 134 | |
---|
| 135 | #endif |
---|