From 1b8181bf0d6e9137e6b9ccdbe414aec37377a1a9 Mon Sep 17 00:00:00 2001
From: Chris Dyer <cdyer@allegro.clab.cs.cmu.edu>
Date: Sun, 18 Nov 2012 13:35:42 -0500
Subject: major restructure of the training code

---
 training/dtrain/dtrain.h | 97 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 97 insertions(+)
 create mode 100644 training/dtrain/dtrain.h

(limited to 'training/dtrain/dtrain.h')

diff --git a/training/dtrain/dtrain.h b/training/dtrain/dtrain.h
new file mode 100644
index 00000000..4b6f415c
--- /dev/null
+++ b/training/dtrain/dtrain.h
@@ -0,0 +1,97 @@
+#ifndef _DTRAIN_H_
+#define _DTRAIN_H_
+
+#undef DTRAIN_FASTER_PERCEPTRON // only look at misranked pairs
+                                 // DO NOT USE WITH SVM!
+//#define DTRAIN_LOCAL
+#define DTRAIN_DOTS 10 // after how many inputs to display a '.'
+#define DTRAIN_GRAMMAR_DELIM "########EOS########"
+#define DTRAIN_SCALE 100000
+
+
+#include <iomanip>
+#include <climits>
+#include <string.h>
+
+#include <boost/algorithm/string.hpp>
+#include <boost/program_options.hpp>
+
+#include "ksampler.h"
+#include "pairsampling.h"
+
+#include "filelib.h"
+
+
+using namespace std;
+using namespace dtrain;
+namespace po = boost::program_options;
+
+inline void register_and_convert(const vector<string>& strs, vector<WordID>& ids)
+{
+  vector<string>::const_iterator it;
+  for (it = strs.begin(); it < strs.end(); it++)
+    ids.push_back(TD::Convert(*it));
+}
+
+inline string gettmpf(const string path, const string infix)
+{
+  char fn[path.size() + infix.size() + 8];
+  strcpy(fn, path.c_str());
+  strcat(fn, "/");
+  strcat(fn, infix.c_str());
+  strcat(fn, "-XXXXXX");
+  if (!mkstemp(fn)) {
+    cerr << "Cannot make temp file in" << path << " , exiting." << endl;
+    exit(1);
+  }
+  return string(fn);
+}
+
+inline void split_in(string& s, vector<string>& parts)
+{
+  unsigned f = 0;
+  for(unsigned i = 0; i < 3; i++) {
+    unsigned e = f;
+    f = s.find("\t", f+1);
+    if (e != 0) parts.push_back(s.substr(e+1, f-e-1));
+    else parts.push_back(s.substr(0, f));
+  }
+  s.erase(0, f+1);
+}
+
+struct HSReporter
+{
+  string task_id_;
+
+  HSReporter(string task_id) : task_id_(task_id) {}
+
+  inline void update_counter(string name, unsigned amount) {
+    cerr << "reporter:counter:" << task_id_ << "," << name << "," << amount << endl;
+  }
+  inline void update_gcounter(string name, unsigned amount) {
+    cerr << "reporter:counter:Global," << name << "," << amount << endl;
+  }
+};
+
+inline ostream& _np(ostream& out) { return out << resetiosflags(ios::showpos); }
+inline ostream& _p(ostream& out)  { return out << setiosflags(ios::showpos); }
+inline ostream& _p2(ostream& out) { return out << setprecision(2); }
+inline ostream& _p5(ostream& out) { return out << setprecision(5); }
+
+inline void printWordIDVec(vector<WordID>& v)
+{
+  for (unsigned i = 0; i < v.size(); i++) {
+    cerr << TD::Convert(v[i]);
+    if (i < v.size()-1) cerr << " ";
+  }
+}
+
+template<typename T>
+inline T sign(T z)
+{
+  if (z == 0) return 0;
+  return z < 0 ? -1 : +1;
+}
+
+#endif
+
-- 
cgit v1.2.3