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) {
  51     std::vector<double> sums;
  52     std::string ret = "";
  53
  54     int n = -skip;
  55     std::string line_string = "";
  56     std::string state = "";
  57     std::ifstream f(filename.c_str(), std::fstream::in);
  58     while (!f.eof()) {
  59         double energy = 0.0;
  60         double weight = 0.0;
  61         getline(f, line_string);
  62         std::stringstream line(line_string);
  63         if (line_string[0]=='#') {
  64             if (line_string[1]=='!') {
  65                 if (line_string.substr(2, 8)=="prepend ") {
  66                     ret.append(line_string.substr(10, line_string.size()));
  67                     ret.append(" ");
  68                 } else {
  69                 }
  70             }
  71         } else {
  72             n++;
  73             if (n>=0) {
  74                 line >> state >> energy >> weight;
  75                 if (n%len==0) {
  76                     sums.push_back(0.0);
  77                 }
  78                 sums[n/len] += energy;
  79             }
  80         }
  81     }
  82     f.close();
  83     sums.pop_back(); // last one may be incomplete.
  84     for (int i=0;i<sums.size();i++) {
  85         sums[i] /= double(len);
  86     }
  87     // time to do some thing with the sums (now they are averages)
  88     std::pair<double, double> s = compute_stats(sums);
  89     std::stringstream rs;
  90     rs << s.first << " " << s.second;
  91     ret.append(rs.str());
  92     return ret;
  93 }
  94
  95 int main (int argc, char **argv) {
  96     int skip = 1000;
  97     int len = 1000;
  98     vector<string> files;
  99     for (int i=1;i<argc;i++) {
 100         if (argv[i][0]=='-') {
 101             switch (argv[i][1]) {
 102                 case 's':
 103                     skip = atoi(argv[++i]);
 104                     break;
 105                 case 'l':
 106                     len = atoi(argv[++i]);
 107                     break;
 108             }
 109         } else {
 110             files.push_back(argv[i]);
 111         }
 112     }
 113     for (vector<string>::iterator iter = files.begin();iter != files.end();iter++) {
 114         cout << analyze_data_file(*iter, skip, len) << endl;
 115     }
 116     return 0;
 117 }
 118