From 5584f300821e20369c25343222cd0e8faa393523 Mon Sep 17 00:00:00 2001
From: Patrick Simianer
Date: Sat, 24 Sep 2011 04:45:22 +0200
Subject: get rid of boost str split, more tweaks
---
dtrain/Makefile.am | 5 +-
dtrain/README | 1 +
dtrain/dtrain.cc | 429 +++++++++++++++++++++++---------------------------
dtrain/dtrain.h | 69 ++++----
dtrain/pairsampling.h | 17 +-
5 files changed, 237 insertions(+), 284 deletions(-)
diff --git a/dtrain/Makefile.am b/dtrain/Makefile.am
index 12084a70..baf6883a 100644
--- a/dtrain/Makefile.am
+++ b/dtrain/Makefile.am
@@ -1,8 +1,7 @@
-# TODO I'm sure I can leave something out.
bin_PROGRAMS = dtrain
dtrain_SOURCES = dtrain.cc score.cc hgsampler.cc
-dtrain_LDADD = $(top_srcdir)/decoder/libcdec.a $(top_srcdir)/mteval/libmteval.a $(top_srcdir)/utils/libutils.a ../klm/lm/libklm.a ../klm/util/libklm_util.a -lz -lboost_filesystem -lboost_iostreams
+dtrain_LDADD = $(top_srcdir)/decoder/libcdec.a $(top_srcdir)/mteval/libmteval.a $(top_srcdir)/utils/libutils.a ../klm/lm/libklm.a ../klm/util/libklm_util.a -lz
-AM_CPPFLAGS = -W -Wall -Wno-sign-compare -I$(top_srcdir)/utils -I$(top_srcdir)/decoder -I$(top_srcdir)/mteval
+AM_CPPFLAGS = -W -Wall -Wno-sign-compare -I$(top_srcdir)/utils -I$(top_srcdir)/decoder -I$(top_srcdir)/mteval -O3
diff --git a/dtrain/README b/dtrain/README
index 0cc52acc..137c1b48 100644
--- a/dtrain/README
+++ b/dtrain/README
@@ -31,6 +31,7 @@ TODO
use separate TEST SET
KNOWN BUGS PROBLEMS
+ doesn't select best iteration for weigts
if size of candidate < N => 0 score
cdec kbest vs 1best (no -k param), rescoring? => ok(?)
no sparse vector in decoder => ok
diff --git a/dtrain/dtrain.cc b/dtrain/dtrain.cc
index 01119997..76fdb49c 100644
--- a/dtrain/dtrain.cc
+++ b/dtrain/dtrain.cc
@@ -1,199 +1,161 @@
#include "dtrain.h"
-
-/*
- * register_and_convert
- *
- */
-void
-register_and_convert(const vector& strs, vector& ids)
-{
- vector::const_iterator it;
- for ( it = strs.begin(); it < strs.end(); it++ ) {
- ids.push_back( TD::Convert( *it ) );
- }
-}
-
-
-/*
- * init
- *
- */
bool
-init(int argc, char** argv, po::variables_map* cfg)
+dtrain_init(int argc, char** argv, po::variables_map* cfg)
{
- po::options_description conff( "Configuration File Options" );
- size_t k, N, T, stop;
- string s, f;
+ po::options_description conff("Configuration File Options");
conff.add_options()
- ( "decoder_config", po::value(), "configuration file for cdec" )
- ( "kbest", po::value(&k)->default_value(DTRAIN_DEFAULT_K), "k for kbest" )
- ( "ngrams", po::value(&N)->default_value(DTRAIN_DEFAULT_N), "N for Ngrams" )
- ( "filter", po::value(&f)->default_value("unique"), "filter kbest list" )
- ( "epochs", po::value(&T)->default_value(DTRAIN_DEFAULT_T), "# of iterations T" )
- ( "input", po::value(), "input file" )
- ( "scorer", po::value(&s)->default_value(DTRAIN_DEFAULT_SCORER), "scoring metric" )
- ( "output", po::value(), "output weights file" )
- ( "stop_after", po::value(&stop)->default_value(0), "stop after X input sentences" )
- ( "weights_file", po::value(), "input weights file (e.g. from previous iteration)" )
- ( "wprint", po::value(), "weights to print on each iteration" )
- ( "noup", po::value()->zero_tokens(), "do not update weights" );
+ ("decoder_config", po::value(), "configuration file for cdec")
+ ("kbest", po::value()->default_value(100), "k for kbest")
+ ("ngrams", po::value()->default_value(3), "N for Ngrams")
+ ("filter", po::value()->default_value("unique"), "filter kbest list")
+ ("epochs", po::value()->default_value(2), "# of iterations T")
+ ("input", po::value()->default_value("-"), "input file")
+ ("output", po::value()->default_value("-"), "output weights file")
+ ("scorer", po::value()->default_value("stupid_bleu"), "scoring metric")
+ ("stop_after", po::value()->default_value(0), "stop after X input sentences")
+ ("input_weights", po::value(), "input weights file (e.g. from previous iteration)")
+ ("wprint", po::value(), "weights to print on each iteration")
+ ("hstreaming", po::value()->zero_tokens(), "run in hadoop streaming mode")
+ ("noup", po::value()->zero_tokens(), "do not update weights");
po::options_description clo("Command Line Options");
clo.add_options()
- ( "config,c", po::value(), "dtrain config file" )
- ( "quiet,q", po::value()->zero_tokens(), "be quiet" )
- ( "verbose,v", po::value()->zero_tokens(), "be verbose" );
+ ("config,c", po::value(), "dtrain config file")
+ ("quiet,q", po::value()->zero_tokens(), "be quiet")
+ ("verbose,v", po::value()->zero_tokens(), "be verbose");
po::options_description config_options, cmdline_options;
config_options.add(conff);
cmdline_options.add(clo);
cmdline_options.add(conff);
- po::store( parse_command_line(argc, argv, cmdline_options), *cfg );
- if ( cfg->count("config") ) {
- ifstream config( (*cfg)["config"].as().c_str() );
- po::store( po::parse_config_file(config, config_options), *cfg );
+ po::store(parse_command_line(argc, argv, cmdline_options), *cfg);
+ if (cfg->count("config")) {
+ ifstream config((*cfg)["config"].as().c_str());
+ po::store(po::parse_config_file(config, config_options), *cfg);
}
po::notify(*cfg);
- if ( !cfg->count("decoder_config") || !cfg->count("input") ) {
+ if (!cfg->count("decoder_config")) {
cerr << cmdline_options << endl;
return false;
}
- if ( cfg->count("noup") && cfg->count("decode") ) {
- cerr << "You can't use 'noup' and 'decode' at once." << endl;
+ if (cfg->count("hstreaming") && (*cfg)["output"].as() != "-") {
+ cerr << "When using 'hstreaming' the 'output' param should be '-'.";
return false;
}
- if ( cfg->count("filter") && (*cfg)["filter"].as() != "unique"
- && (*cfg)["filter"].as() != "no" ) {
+ if (cfg->count("filter") && (*cfg)["filter"].as() != "unique"
+ && (*cfg)["filter"].as() != "no") {
cerr << "Wrong 'filter' type: '" << (*cfg)["filter"].as() << "'." << endl;
}
- #ifdef DTRAIN_DEBUG
- if ( !cfg->count("test") ) {
- cerr << cmdline_options << endl;
- return false;
- }
- #endif
return true;
}
+#include "filelib.h"
-// output formatting
-ostream& _nopos( ostream& out ) { return out << resetiosflags( ios::showpos ); }
-ostream& _pos( ostream& out ) { return out << setiosflags( ios::showpos ); }
-ostream& _prec2( ostream& out ) { return out << setprecision(2); }
-ostream& _prec5( ostream& out ) { return out << setprecision(5); }
-
-
-
-
-/*
- * dtrain
- *
- */
int
-main( int argc, char** argv )
+main(int argc, char** argv)
{
- cout << setprecision( 5 );
+ cout << _p5;
// handle most parameters
po::variables_map cfg;
- if ( ! init(argc, argv, &cfg) ) exit(1); // something is wrong
-#ifdef DTRAIN_DEBUG
- if ( cfg.count("test") ) run_tests(); // run tests and exit
-#endif
+ if (! dtrain_init(argc, argv, &cfg)) exit(1); // something is wrong
bool quiet = false;
- if ( cfg.count("quiet") ) quiet = true;
+ if (cfg.count("quiet")) quiet = true;
bool verbose = false;
- if ( cfg.count("verbose") ) verbose = true;
+ if (cfg.count("verbose")) verbose = true;
bool noup = false;
- if ( cfg.count("noup") ) noup = true;
+ if (cfg.count("noup")) noup = true;
+ bool hstreaming = false;
+ if (cfg.count("hstreaming")) {
+ hstreaming = true;
+ quiet = true;
+ }
const size_t k = cfg["kbest"].as();
const size_t N = cfg["ngrams"].as();
const size_t T = cfg["epochs"].as();
const size_t stop_after = cfg["stop_after"].as();
const string filter_type = cfg["filter"].as();
- if ( !quiet ) {
+ if (!quiet) {
cout << endl << "dtrain" << endl << "Parameters:" << endl;
cout << setw(25) << "k " << k << endl;
cout << setw(25) << "N " << N << endl;
cout << setw(25) << "T " << T << endl;
- if ( cfg.count("stop-after") )
+ if (cfg.count("stop-after"))
cout << setw(25) << "stop_after " << stop_after << endl;
- if ( cfg.count("weights") )
+ if (cfg.count("input_weights"))
cout << setw(25) << "weights " << cfg["weights"].as() << endl;
cout << setw(25) << "input " << "'" << cfg["input"].as() << "'" << endl;
cout << setw(25) << "filter " << "'" << filter_type << "'" << endl;
}
vector wprint;
- if ( cfg.count("wprint") ) {
- boost::split( wprint, cfg["wprint"].as(), boost::is_any_of(" ") );
+ if (cfg.count("wprint")) {
+ boost::split(wprint, cfg["wprint"].as(), boost::is_any_of(" "));
}
// setup decoder, observer
register_feature_functions();
SetSilent(true);
- ReadFile ini_rf( cfg["decoder_config"].as() );
- if ( !quiet )
+ ReadFile ini_rf(cfg["decoder_config"].as());
+ if (!quiet)
cout << setw(25) << "cdec cfg " << "'" << cfg["decoder_config"].as() << "'" << endl;
- Decoder decoder( ini_rf.stream() );
- KBestGetter observer( k, filter_type );
+ Decoder decoder(ini_rf.stream());
+ KBestGetter observer(k, filter_type);
MT19937 rng;
- //KSampler observer( k, &rng );
+ //KSampler observer(k, &rng);
// scoring metric/scorer
string scorer_str = cfg["scorer"].as();
- double (*scorer)( NgramCounts&, const size_t, const size_t, size_t, vector );
- if ( scorer_str == "bleu" ) {
+ double (*scorer)(NgramCounts&, const size_t, const size_t, size_t, vector);
+ if (scorer_str == "bleu") {
scorer = &bleu;
- } else if ( scorer_str == "stupid_bleu" ) {
+ } else if (scorer_str == "stupid_bleu") {
scorer = &stupid_bleu;
- } else if ( scorer_str == "smooth_bleu" ) {
+ } else if (scorer_str == "smooth_bleu") {
scorer = &smooth_bleu;
- } else if ( scorer_str == "approx_bleu" ) {
+ } else if (scorer_str == "approx_bleu") {
scorer = &approx_bleu;
} else {
cerr << "Don't know scoring metric: '" << scorer_str << "', exiting." << endl;
exit(1);
}
// for approx_bleu
- NgramCounts global_counts( N ); // counts for 1 best translations
+ NgramCounts global_counts(N); // counts for 1 best translations
size_t global_hyp_len = 0; // sum hypothesis lengths
size_t global_ref_len = 0; // sum reference lengths
// this is all BLEU implmentations
vector bleu_weights; // we leave this empty -> 1/N; TODO?
- if ( !quiet ) cout << setw(26) << "scorer '" << scorer_str << "'" << endl << endl;
+ if (!quiet) cout << setw(26) << "scorer '" << scorer_str << "'" << endl << endl;
// init weights
Weights weights;
- if ( cfg.count("weights") ) weights.InitFromFile( cfg["weights"].as() );
+ if (cfg.count("weights")) weights.InitFromFile(cfg["weights"].as());
SparseVector lambdas;
- weights.InitSparseVector( &lambdas );
+ weights.InitSparseVector(&lambdas);
vector dense_weights;
// input
- if ( !quiet && !verbose )
+ if (!quiet && !verbose)
cout << "(a dot represents " << DTRAIN_DOTS << " lines of input)" << endl;
string input_fn = cfg["input"].as();
ifstream input;
- if ( input_fn != "-" ) input.open( input_fn.c_str() );
+ if (input_fn != "-") input.open(input_fn.c_str());
string in;
vector in_split; // input: src\tref\tpsg
vector ref_tok; // tokenized reference
vector ref_ids; // reference as vector of WordID
- string grammar_str;
// buffer input for t > 0
vector src_str_buf; // source strings, TODO? memory
vector > ref_ids_buf; // references as WordID vecs
- filtering_ostream grammar_buf; // written to compressed file in /tmp
// this is for writing the grammar buffer file
- grammar_buf.push( gzip_compressor() );
- char grammar_buf_tmp_fn[] = DTRAIN_TMP_DIR"/dtrain-grammars-XXXXXX";
- mkstemp( grammar_buf_tmp_fn );
- grammar_buf.push( file_sink(grammar_buf_tmp_fn, ios::binary | ios::trunc) );
+ char grammar_buf_fn[] = DTRAIN_TMP_DIR"/dtrain-grammars-XXXXXX";
+ mkstemp(grammar_buf_fn);
+ ogzstream grammar_buf_out;
+ grammar_buf_out.open(grammar_buf_fn);
size_t sid = 0, in_sz = 99999999; // sentence id, input size
double acc_1best_score = 0., acc_1best_model = 0.;
@@ -208,23 +170,21 @@ main( int argc, char** argv )
// for the perceptron/SVM; TODO as params
double eta = 0.0005;
double gamma = 0.;//01; // -> SVM
- lambdas.add_value( FD::Convert("__bias"), 0 );
+ lambdas.add_value(FD::Convert("__bias"), 0);
// for random sampling
- srand ( time(NULL) );
+ srand (time(NULL));
- for ( size_t t = 0; t < T; t++ ) // T epochs
+ for (size_t t = 0; t < T; t++) // T epochs
{
time_t start, end;
- time( &start );
+ time(&start);
// actually, we need only need this if t > 0 FIXME
- ifstream grammar_file( grammar_buf_tmp_fn, ios_base::in | ios_base::binary );
- filtering_istream grammar_buf_in;
- grammar_buf_in.push( gzip_decompressor() );
- grammar_buf_in.push( grammar_file );
+ igzstream grammar_buf_in;
+ if (t > 0) grammar_buf_in.open(grammar_buf_fn);
// reset average scores
acc_1best_score = acc_1best_model = 0.;
@@ -232,43 +192,43 @@ main( int argc, char** argv )
// reset sentence counter
sid = 0;
- if ( !quiet ) cout << "Iteration #" << t+1 << " of " << T << "." << endl;
+ if (!quiet) cout << "Iteration #" << t+1 << " of " << T << "." << endl;
- while( true )
+ while(true)
{
// get input from stdin or file
in.clear();
next = stop = false; // next iteration, premature stop
- if ( t == 0 ) {
- if ( input_fn == "-" ) {
- if ( !getline(cin, in) ) next = true;
+ if (t == 0) {
+ if (input_fn == "-") {
+ if (!getline(cin, in)) next = true;
} else {
- if ( !getline(input, in) ) next = true;
+ if (!getline(input, in)) next = true;
}
} else {
- if ( sid == in_sz ) next = true; // stop if we reach the end of our input
+ if (sid == in_sz) next = true; // stop if we reach the end of our input
}
// stop after X sentences (but still iterate for those)
- if ( stop_after > 0 && stop_after == sid && !next ) stop = true;
+ if (stop_after > 0 && stop_after == sid && !next) stop = true;
// produce some pretty output
- if ( !quiet && !verbose ) {
- if ( sid == 0 ) cout << " ";
- if ( (sid+1) % (DTRAIN_DOTS) == 0 ) {
+ if (!quiet && !verbose) {
+ if (sid == 0) cout << " ";
+ if ((sid+1) % (DTRAIN_DOTS) == 0) {
cout << ".";
cout.flush();
}
- if ( (sid+1) % (20*DTRAIN_DOTS) == 0) {
+ if ((sid+1) % (20*DTRAIN_DOTS) == 0) {
cout << " " << sid+1 << endl;
- if ( !next && !stop ) cout << " ";
+ if (!next && !stop) cout << " ";
}
- if ( stop ) {
- if ( sid % (20*DTRAIN_DOTS) != 0 ) cout << " " << sid << endl;
+ if (stop) {
+ if (sid % (20*DTRAIN_DOTS) != 0) cout << " " << sid << endl;
cout << "Stopping after " << stop_after << " input sentences." << endl;
} else {
- if ( next ) {
- if ( sid % (20*DTRAIN_DOTS) != 0 ) {
+ if (next) {
+ if (sid % (20*DTRAIN_DOTS) != 0) {
cout << " " << sid << endl;
}
}
@@ -276,68 +236,65 @@ main( int argc, char** argv )
}
// next iteration
- if ( next || stop ) break;
+ if (next || stop) break;
// weights
dense_weights.clear();
- weights.InitFromVector( lambdas );
- weights.InitVector( &dense_weights );
- decoder.SetWeights( dense_weights );
+ weights.InitFromVector(lambdas);
+ weights.InitVector(&dense_weights);
+ decoder.SetWeights(dense_weights);
- if ( t == 0 ) {
+ if (t == 0) {
// handling input
in_split.clear();
- boost::split( in_split, in, boost::is_any_of("\t") ); // in_split[0] is id
+ strsplit(in, in_split, '\t', 4);
// getting reference
ref_tok.clear(); ref_ids.clear();
- boost::split( ref_tok, in_split[2], boost::is_any_of(" ") );
- register_and_convert( ref_tok, ref_ids );
- ref_ids_buf.push_back( ref_ids );
+ strsplit(in_split[2], ref_tok, ' ');
+ register_and_convert(ref_tok, ref_ids);
+ ref_ids_buf.push_back(ref_ids);
// process and set grammar
bool broken_grammar = true;
- for ( string::iterator ti = in_split[3].begin(); ti != in_split[3].end(); ti++ ) {
- if ( !isspace(*ti) ) {
+ for (string::iterator ti = in_split[3].begin(); ti != in_split[3].end(); ti++) {
+ if (!isspace(*ti)) {
broken_grammar = false;
break;
}
}
- if ( broken_grammar ) continue;
- grammar_str = boost::replace_all_copy( in_split[3], " __NEXT__RULE__ ", "\n" ) + "\n"; // FIXME copy, __
- grammar_buf << grammar_str << DTRAIN_GRAMMAR_DELIM << " " << in_split[0] << endl;
- decoder.SetSentenceGrammarFromString( grammar_str );
- // decode, kbest
- src_str_buf.push_back( in_split[1] );
- decoder.Decode( in_split[1], &observer );
+ if (broken_grammar) continue;
+ boost::replace_all(in_split[3], " __NEXT__RULE__ ", "\n");
+ in_split[3] += "\n";
+ grammar_buf_out << in_split[3] << DTRAIN_GRAMMAR_DELIM << " " << in_split[0] << endl;
+ decoder.SetSentenceGrammarFromString(in_split[3]);
+ // decode
+ src_str_buf.push_back(in_split[1]);
+ decoder.Decode(in_split[1], &observer);
} else {
// get buffered grammar
- grammar_str.clear();
- int i = 1;
- while ( true ) {
- string g;
- getline( grammar_buf_in, g );
- //if ( g == DTRAIN_GRAMMAR_DELIM ) break;
- if (boost::starts_with(g, DTRAIN_GRAMMAR_DELIM)) break;
- grammar_str += g+"\n";
- i += 1;
+ string grammar_str;
+ while (true) {
+ string rule;
+ getline(grammar_buf_in, rule);
+ if (boost::starts_with(rule, DTRAIN_GRAMMAR_DELIM)) break;
+ grammar_str += rule + "\n";
}
- decoder.SetSentenceGrammarFromString( grammar_str );
- // decode, kbest
- decoder.Decode( src_str_buf[sid], &observer );
+ decoder.SetSentenceGrammarFromString(grammar_str);
+ // decode
+ decoder.Decode(src_str_buf[sid], &observer);
}
// get kbest list
KBestList* kb;
- //if ( ) { // TODO get from forest
+ //if () { // TODO get from forest
kb = observer.GetKBest();
//}
- // scoring kbest
- if ( t > 0 ) ref_ids = ref_ids_buf[sid];
- for ( size_t i = 0; i < kb->GetSize(); i++ ) {
- NgramCounts counts = make_ngram_counts( ref_ids, kb->sents[i], N );
- // this is for approx bleu
- if ( scorer_str == "approx_bleu" ) {
- if ( i == 0 ) { // 'context of 1best translations'
+ // (local) scoring
+ if (t > 0) ref_ids = ref_ids_buf[sid];
+ for (size_t i = 0; i < kb->GetSize(); i++) {
+ NgramCounts counts = make_ngram_counts(ref_ids, kb->sents[i], N);
+ if (scorer_str == "approx_bleu") {
+ if (i == 0) { // 'context of 1best translations'
global_counts += counts;
global_hyp_len += kb->sents[i].size();
global_ref_len += ref_ids.size();
@@ -347,59 +304,61 @@ main( int argc, char** argv )
cand_len = kb->sents[i].size();
}
NgramCounts counts_tmp = global_counts + counts;
- score = .9*scorer( counts_tmp,
+ score = .9*scorer(counts_tmp,
global_ref_len,
- global_hyp_len + cand_len, N, bleu_weights );
+ global_hyp_len + cand_len, N, bleu_weights);
} else {
- // other scorers
cand_len = kb->sents[i].size();
- score = scorer( counts,
+ score = scorer(counts,
ref_ids.size(),
- kb->sents[i].size(), N, bleu_weights );
+ kb->sents[i].size(), N, bleu_weights);
}
- kb->scores.push_back( score );
+ kb->scores.push_back(score);
- if ( i == 0 ) {
+ if (i == 0) {
acc_1best_score += score;
acc_1best_model += kb->model_scores[i];
}
- if ( verbose ) {
- if ( i == 0 ) cout << "'" << TD::GetString( ref_ids ) << "' [ref]" << endl;
- cout << _prec5 << _nopos << "[hyp " << i << "] " << "'" << TD::GetString( kb->sents[i] ) << "'";
+ if (verbose) {
+ if (i == 0) cout << "'" << TD::GetString(ref_ids) << "' [ref]" << endl;
+ cout << _p5 << _np << "[hyp " << i << "] " << "'" << TD::GetString(kb->sents[i]) << "'";
cout << " [SCORE=" << score << ",model="<< kb->model_scores[i] << "]" << endl;
- cout << kb->feats[i] << endl; // this is maybe too verbose
+ //cout << kb->feats[i] << endl; // too verbose
}
} // Nbest loop
- if ( verbose ) cout << endl;
-
+ if (verbose) cout << endl;
+//////////////////////////////////////////////////////////
// UPDATE WEIGHTS
- if ( !noup ) {
+ if (!noup) {
+
+ int up = 0;
TrainingInstances pairs;
sample_all_pairs(kb, pairs);
- //sample_rand_pairs( kb, pairs, &rng );
+ //sample_rand_pairs(kb, pairs, &rng);
- for ( TrainingInstances::iterator ti = pairs.begin();
- ti != pairs.end(); ti++ ) {
+ for (TrainingInstances::iterator ti = pairs.begin();
+ ti != pairs.end(); ti++) {
SparseVector dv;
- if ( ti->first_score - ti->second_score < 0 ) {
+ if (ti->first_score - ti->second_score < 0) {
+ up++;
dv = ti->second - ti->first;
//} else {
//dv = ti->first - ti->second;
//}
- dv.add_value( FD::Convert("__bias"), -1 );
+ dv.add_value(FD::Convert("__bias"), -1);
//SparseVector reg;
- //reg = lambdas * ( 2 * gamma );
+ //reg = lambdas * (2 * gamma);
//dv -= reg;
lambdas += dv * eta;
- if ( verbose ) {
+ if (verbose) {
cout << "{{ f("<< ti->first_rank <<") > f(" << ti->second_rank << ") but g(i)="<< ti->first_score <<" < g(j)="<< ti->second_score << " so update" << endl;
cout << " i " << TD::GetString(kb->sents[ti->first_rank]) << endl;
cout << " " << kb->feats[ti->first_rank] << endl;
@@ -411,99 +370,99 @@ main( int argc, char** argv )
}
} else {
//SparseVector reg;
- //reg = lambdas * ( 2 * gamma );
- //lambdas += reg * ( -eta );
+ //reg = lambdas * (2 * gamma);
+ //lambdas += reg * (-eta);
}
}
//double l2 = lambdas.l2norm();
- //if ( l2 ) lambdas /= lambdas.l2norm();
-
+ //if (l2) lambdas /= lambdas.l2norm();
+ //cout << up << endl;
}
+//////////////////////////////////////////////////////////
++sid;
- //cerr << "reporter:counter:dtrain,sent," << sid << endl;
+
+ if (hstreaming) cerr << "reporter:counter:dtrain,sid," << sid << endl;
} // input loop
- if ( t == 0 ) in_sz = sid; // remember size (lines) of input
+ if (t == 0) {
+ in_sz = sid; // remember size (lines) of input
+ grammar_buf_out.close();
+ if (input_fn != "-") input.close();
+ } else {
+ grammar_buf_in.close();
+ }
// print some stats
double avg_1best_score = acc_1best_score/(double)in_sz;
double avg_1best_model = acc_1best_model/(double)in_sz;
double avg_1best_score_diff, avg_1best_model_diff;
- if ( t > 0 ) {
+ if (t > 0) {
avg_1best_score_diff = avg_1best_score - scores_per_iter[t-1][0];
avg_1best_model_diff = avg_1best_model - scores_per_iter[t-1][1];
} else {
avg_1best_score_diff = avg_1best_score;
avg_1best_model_diff = avg_1best_model;
}
- if ( !quiet ) {
- cout << _prec5 << _pos << "WEIGHTS" << endl;
+ if (!quiet) {
+ cout << _p5 << _p << "WEIGHTS" << endl;
for (vector::iterator it = wprint.begin(); it != wprint.end(); it++) {
- cout << setw(16) << *it << " = " << dense_weights[FD::Convert( *it )] << endl;
+ cout << setw(16) << *it << " = " << dense_weights[FD::Convert(*it)] << endl;
}
-
cout << " ---" << endl;
- cout << _nopos << " avg score: " << avg_1best_score;
- cout << _pos << " (" << avg_1best_score_diff << ")" << endl;
- cout << _nopos << "avg model score: " << avg_1best_model;
- cout << _pos << " (" << avg_1best_model_diff << ")" << endl;
+ cout << _np << " avg score: " << avg_1best_score;
+ cout << _p << " (" << avg_1best_score_diff << ")" << endl;
+ cout << _np << "avg model score: " << avg_1best_model;
+ cout << _p << " (" << avg_1best_model_diff << ")" << endl;
}
vector remember_scores;
- remember_scores.push_back( avg_1best_score );
- remember_scores.push_back( avg_1best_model );
- scores_per_iter.push_back( remember_scores );
- if ( avg_1best_score > max_score ) {
+ remember_scores.push_back(avg_1best_score);
+ remember_scores.push_back(avg_1best_model);
+ scores_per_iter.push_back(remember_scores);
+ if (avg_1best_score > max_score) {
max_score = avg_1best_score;
best_t = t;
}
-
- // close open files
- if ( input_fn != "-" ) input.close();
- close( grammar_buf );
- grammar_file.close();
-
- time ( &end );
- double time_dif = difftime( end, start );
+ time (&end);
+ double time_dif = difftime(end, start);
overall_time += time_dif;
- if ( !quiet ) {
- cout << _prec2 << _nopos << "(time " << time_dif/60. << " min, ";
+ if (!quiet) {
+ cout << _p2 << _np << "(time " << time_dif/60. << " min, ";
cout << time_dif/(double)in_sz<< " s/S)" << endl;
}
- if ( t+1 != T && !quiet ) cout << endl;
+ if (t+1 != T && !quiet) cout << endl;
- if ( noup ) break;
+ if (noup) break;
} // outer loop
- unlink( grammar_buf_tmp_fn );
- if ( !noup ) {
- // TODO BEST ITER
- if ( !quiet ) cout << endl << "writing weights file '" << cfg["output"].as() << "' ...";
- if ( cfg["output"].as() == "-" ) {
- for ( SparseVector::const_iterator ti = lambdas.begin();
- ti != lambdas.end(); ++ti ) {
- if ( ti->second == 0 ) continue;
- //if ( ti->first == "__bias" ) continue;
- cout << setprecision(9);
- cout << _nopos << FD::Convert(ti->first) << "\t" << ti->second << endl;
- //cout << "__SHARD_COUNT__\t1" << endl;
+ //unlink(grammar_buf_fn);
+
+ if (!noup) {
+ if (!quiet) cout << endl << "writing weights file '" << cfg["output"].as() << "' ...";
+ if (cfg["output"].as() == "-") {
+ for (SparseVector::const_iterator ti = lambdas.begin();
+ ti != lambdas.end(); ++ti) {
+ if (ti->second == 0) continue;
+ cout << _p9;
+ cout << _np << FD::Convert(ti->first) << "\t" << ti->second << endl;
}
+ if (hstreaming) cout << "__SHARD_COUNT__\t1" << endl;
} else {
- weights.InitFromVector( lambdas );
- weights.WriteToFile( cfg["output"].as(), true );
+ weights.InitFromVector(lambdas);
+ weights.WriteToFile(cfg["output"].as(), true);
}
- if ( !quiet ) cout << "done" << endl;
+ if (!quiet) cout << "done" << endl;
}
- if ( !quiet ) {
- cout << _prec5 << _nopos << endl << "---" << endl << "Best iteration: ";
+ if (!quiet) {
+ cout << _p5 << _np << endl << "---" << endl << "Best iteration: ";
cout << best_t+1 << " [SCORE '" << scorer_str << "'=" << max_score << "]." << endl;
- cout << _prec2 << "This took " << overall_time/60. << " min." << endl;
+ cout << _p2 << "This took " << overall_time/60. << " min." << endl;
}
return 0;
diff --git a/dtrain/dtrain.h b/dtrain/dtrain.h
index 3d319233..9bc5be93 100644
--- a/dtrain/dtrain.h
+++ b/dtrain/dtrain.h
@@ -2,59 +2,56 @@
#define _DTRAIN_COMMON_H_
-#include
-#include
-#include
-#include
-#include
#include
-// cdec includes
-#include "sentence_metadata.h"
+#include
+#include
+
#include "verbose.h"
#include "viterbi.h"
-#include "kbest.h"
#include "ff_register.h"
#include "decoder.h"
#include "weights.h"
-// boost includes
-#include
-#include
-
-// own headers
#include "score.h"
-
-#define DTRAIN_DEFAULT_K 100 // k for kbest lists
-#define DTRAIN_DEFAULT_N 4 // N for ngrams (e.g. BLEU)
-#define DTRAIN_DEFAULT_T 1 // iterations
-#define DTRAIN_DEFAULT_SCORER "stupid_bleu" // scorer
-#define DTRAIN_DOTS 100 // when to display a '.'
-#define DTRAIN_TMP_DIR "/tmp" // put this on a SSD?
-#define DTRAIN_GRAMMAR_DELIM "########EOS########"
-
-
#include "kbestget.h"
-#include "pairsampling.h"
-
#include "ksampler.h"
+#include "pairsampling.h"
-// boost compression
-#include
-#include
-#include
-//#include
-//#include
-using namespace boost::iostreams;
-
-#include
-#include
-
+#define DTRAIN_DOTS 100 // when to display a '.'
+#define DTRAIN_TMP_DIR "/var/hadoop/mapred/local" // put this on a SSD?
+#define DTRAIN_GRAMMAR_DELIM "########EOS########"
using namespace std;
using namespace dtrain;
namespace po = boost::program_options;
+inline void register_and_convert(const vector& strs, vector& ids) {
+ vector::const_iterator it;
+ for (it = strs.begin(); it < strs.end(); it++)
+ ids.push_back(TD::Convert(*it));
+}
+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 ostream& _p9(ostream& out) { return out << setprecision(9); }
+inline void strsplit(string &s, vector& v, char d = '\t', size_t parts = 0) {
+ stringstream ss(s);
+ string t;
+ size_t c = 0;
+ while(true)
+ {
+ if (parts > 0 && c == parts-1) {
+ getline(ss, t);
+ v.push_back(t);
+ break;
+ }
+ if (!getline(ss, t, d)) break;
+ v.push_back(t);
+ c++;
+ }
+}
#endif
diff --git a/dtrain/pairsampling.h b/dtrain/pairsampling.h
index 9774ba4a..e06036ca 100644
--- a/dtrain/pairsampling.h
+++ b/dtrain/pairsampling.h
@@ -2,7 +2,7 @@
#define _DTRAIN_PAIRSAMPLING_H_
#include "kbestget.h"
-#include "sampler.h" // cdec MT19937
+#include "sampler.h" // cdec, MT19937
namespace dtrain
{
@@ -17,7 +17,7 @@ struct TPair
typedef vector TrainingInstances;
-void
+inline void
sample_all_pairs(KBestList* kb, TrainingInstances &training)
{
for (size_t i = 0; i < kb->GetSize()-1; i++) {
@@ -30,14 +30,13 @@ sample_all_pairs(KBestList* kb, TrainingInstances &training)
p.first_score = kb->scores[i];
p.second_score = kb->scores[j];
training.push_back(p);
- }
- }
+ } // j
+ } // i
}
-void
+inline void
sample_rand_pairs(KBestList* kb, TrainingInstances &training, MT19937* prng)
{
- srand(time(NULL));
for (size_t i = 0; i < kb->GetSize()-1; i++) {
for (size_t j = i+1; j < kb->GetSize(); j++) {
if (prng->next() < .5) {
@@ -50,14 +49,12 @@ sample_rand_pairs(KBestList* kb, TrainingInstances &training, MT19937* prng)
p.second_score = kb->scores[j];
training.push_back(p);
}
- }
- }
- cout << training.size() << " sampled" << endl;
+ } // j
+ } // i
}
} // namespace
-
#endif
--
cgit v1.2.3