source: trunk/yat/utility/utility.cc @ 1304

Last change on this file since 1304 was 1304, checked in by Peter, 13 years ago

quantile normalization closes #288

  • Property svn:eol-style set to native
  • Property svn:keywords set to Id
File size: 3.2 KB
Line 
1// $Id: utility.cc 1304 2008-05-14 20:11:57Z peter $
2
3/*
4  Copyright (C) 2005, 2006 Jari Häkkinen, Markus Ringnér
5  Copyright (C) 2007 Jari Häkkinen, Peter Johansson
6
7  This file is part of the yat library, http://trac.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 2 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 this program; if not, write to the Free Software
21  Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
22  02111-1307, USA.
23*/
24
25#include "utility.h"
26
27#include "Matrix.h"
28#include "stl_utility.h"
29#include "VectorConstView.h"
30#include "yat/statistics/Averager.h"
31
32#include <sstream>
33#include <string>
34
35namespace theplu {
36namespace yat {
37namespace utility {
38
39  bool is_double(const std::string& s)
40  {
41    if (is_nan(s) || is_equal(s, "inf") || is_equal(s, "-inf"))
42      return true;
43    std::stringstream ss(s);
44    double a;
45    ss>>a;
46    if(ss.fail()) 
47      return false;
48    // Check that nothing is left on stream
49    std::string b;
50    ss >> b;
51    return (b.size() ? false : true);
52  }
53 
54
55  bool is_equal(std::string s, std::string other)
56  {
57    std::stringstream ss(s);
58    std::string s2;
59    ss >> s2; // to trim surrounding whitespaces
60    to_lower(s2);
61    // Check that nothing is left on stream
62    std::string s3;
63    ss >> s3;
64    if(s3.size())
65      return false;
66    return (other==s2);
67  }
68
69
70  bool is_float(const std::string& s)
71  {
72    if (is_nan(s) || is_equal(s, "inf") || is_equal(s, "-inf"))
73      return true;
74    std::stringstream ss(s);
75    float a;
76    ss>>a;
77    if(ss.fail()) 
78      return false;
79    // Check that nothing is left on stream
80    std::string b;
81    ss >> b;
82    return (b.size() ? false : true);
83  }
84
85
86  bool is_int(const std::string& s)
87  {
88    if (is_nan(s) || is_equal(s, "inf") || is_equal(s, "-inf"))
89      return true;
90    std::stringstream ss(s);
91    int a;
92    ss >> a;
93    if(ss.fail()) 
94      return false;
95    // Check that nothing is left on stream
96    std::string b;
97    ss >> b;
98    return (b.size() ? false : true);
99  }
100
101  bool is_nan(const std::string& s)
102  {
103    return is_equal(s, "nan");
104  }
105
106
107  void quantile_normalize(Matrix& data)
108  {
109    Matrix data_copy(data);
110   
111    // sort columns in copy
112    for (size_t column=0; column<data_copy.columns(); ++column){
113      std::sort(data_copy.begin_column(column), data_copy.end_column(column));
114    }
115
116    // calculate average of each row
117    std::vector<yat::statistics::Averager> averager(data_copy.rows());
118    for (size_t row=0; row<data_copy.rows(); ++row){
119      add(averager[row], data_copy.begin_row(row), data_copy.end_row(row));
120    }
121
122    for (size_t column=0; column<data.columns(); ++column){
123      std::vector<size_t> index;
124      const VectorConstView col_vec(data,column,false);
125      yat::utility::sort_index(index, data.column_const_view(column));
126                               
127      for (size_t row=0; row<data.rows(); ++row)
128        data(index[row], column) = averager[row].mean();
129    }
130  }
131
132
133
134}}} // end of namespace utility, yat and thep
Note: See TracBrowser for help on using the repository browser.