analyze.cpp

   1 /*
   2  * Copyright (c) 2009 Mauro Iazzi
   3  *
   4  * Permission is hereby granted, free of charge, to any person
   5  * obtaining a copy of this software and associated documentation
   6  * files (the "Software"), to deal in the Software without
   7  * restriction, including without limitation the rights to use,
   8  * copy, modify, merge, publish, distribute, sublicense, and/or sell
   9  * copies of the Software, and to permit persons to whom the
  10  * Software is furnished to do so, subject to the following
  11  * conditions:
  12  *
  13  * The above copyright notice and this permission notice shall be
  14  * included in all copies or substantial portions of the Software.
  15  *
  16  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
  17  * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
  18  * OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
  19  * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
  20  * HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
  21  * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
  22  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  23  * OTHER DEALINGS IN THE SOFTWARE.
  24  */
  25
  26 #include <string>
  27 #include <vector>
  28 #include <iostream>
  29 #include <fstream>
  30 #include <sstream>
  31 #include <cmath>
  32 #include <cstdlib>
  33
  34 using namespace std;
  35
  36 std::pair<double, double> compute_stats (const std::vector<double> &d) {
  37     double avg = 0.0, var = 0.0;
  38     const int N = d.size();
  39     for (int i=0;i<N;i++) {
  40         avg += d[i];
  41         var += d[i]*d[i];
  42     }
  43     avg /= N;
  44     var /= (N);
  45     var -= avg*avg;
  46     var = sqrt(var);
  47     return std::pair<double, double>(avg, var);
  48 }
  49
  50 std::string analyze_data_file (std::string filename, const int skip, const int len, int w = -1) {
  51     std::vector<double> sums;
  52     std::string ret = "";
  53
  54     int n = -skip;
  55     double norm = 0.0;
  56     std::string line_string = "";
  57     std::string state = "";
  58     std::ifstream f(filename.c_str(), std::fstream::in);
  59     while (!f.eof()) {
  60         double energy = 0.0;
  61         double weight = 0.0;
  62         getline(f, line_string);
  63         std::stringstream line(line_string);
  64         if (line_string[0]=='#') {
  65             if (line_string[1]=='!') {
  66                 if (line_string.substr(2, 8)=="prepend ") {
  67                     ret.insert(0, " ");
  68                     ret.insert(0, line_string.substr(10, line_string.size()));
  69                 } else {
  70                 }
  71             }
  72         } else {
  73             n++;
  74             if (n>=0) {
  75                 line >> state >> energy;
  76                 weight = 1.0;
  77                 for (int j=0;j<w;j++) {
  78                     line >> weight;
  79                 }
  80                 norm += weight;
  81                 if (n%len==0) {
  82                     if (n>0) sums[sums.size()-1] /= norm;
  83                     sums.push_back(0.0);
  84                     norm = 0.0;
  85                 }
  86                 sums[n/len] += energy*(w?weight:1.0);
  87             }
  88         }
  89     }
  90     f.close();
  91     sums.pop_back(); // last one may be incomplete.
  92     // time to do some thing with the sums (now they are averages)
  93     std::pair<double, double> s = compute_stats(sums);
  94     std::stringstream rs;
  95     rs << s.first << " " << s.second;
  96     ret.append(rs.str());
  97     return ret;
  98 }
  99
 100 #define NEXTOPT(a, n) ( (a[i][2]=='\0')?(a[++i]):&(a[i][2]) )
 101
 102 int main (int argc, char **argv) {
 103     int skip = 1000;
 104     int len = 1000;
 105     int w_col = -1;
 106     vector<string> files;
 107     for (int i=1;i<argc;i++) {
 108         if (argv[i][0]=='-') {
 109             switch (argv[i][1]) {
 110                 case 'w':
 111                     w_col = atoi(NEXTOPT(argv, i));
 112                     break;
 113                 case 's':
 114                     skip = atoi(NEXTOPT(argv, i));
 115                     break;
 116                 case 'l':
 117                     len = atoi(NEXTOPT(argv, i));
 118                     break;
 119             }
 120         } else {
 121             files.push_back(argv[i]);
 122         }
 123     }
 124     for (vector<string>::iterator iter = files.begin();iter != files.end();iter++) {
 125         cout << analyze_data_file(*iter, skip, len, w_col) << endl;
 126     }
 127     return 0;
 128 }
 129