diff options
| -rw-r--r-- | training/dtrain/README.md | 28 | ||||
| -rw-r--r-- | training/dtrain/dtrain.cc | 121 | ||||
| -rw-r--r-- | training/dtrain/dtrain.h | 8 | ||||
| -rwxr-xr-x | training/dtrain/hstreaming/avg.rb | 32 | ||||
| -rw-r--r-- | training/dtrain/hstreaming/cdec.ini | 22 | ||||
| -rw-r--r-- | training/dtrain/hstreaming/dtrain.ini | 15 | ||||
| -rwxr-xr-x | training/dtrain/hstreaming/dtrain.sh | 9 | ||||
| -rwxr-xr-x | training/dtrain/hstreaming/hadoop-streaming-job.sh | 30 | ||||
| -rw-r--r-- | training/dtrain/hstreaming/red-test | 9 | ||||
| -rwxr-xr-x | training/dtrain/lplp.rb (renamed from training/dtrain/hstreaming/lplp.rb) | 0 | ||||
| -rwxr-xr-x | training/dtrain/parallelize.rb | 4 | ||||
| -rw-r--r-- | training/dtrain/test/example/cdec.ini | 2 |
12 files changed, 13 insertions, 267 deletions
diff --git a/training/dtrain/README.md b/training/dtrain/README.md index 7edabbf1..2ab2f232 100644 --- a/training/dtrain/README.md +++ b/training/dtrain/README.md @@ -13,36 +13,18 @@ Builds when building cdec, see ../BUILDING . To build only parts needed for dtrain do ``` autoreconf -ifv - ./configure [--disable-gtest] - cd dtrain/; make + ./configure + cd training/dtrain/; make ``` Running ------- -To run this on a dev set locally: -``` - #define DTRAIN_LOCAL -``` -otherwise remove that line or undef, then recompile. You need a single -grammar file or input annotated with per-sentence grammars (psg) as you -would use with cdec. Additionally you need to give dtrain a file with -references (--refs) when running locally. - -The input for use with hadoop streaming looks like this: -``` - <sid>\t<source>\t<ref>\t<grammar rules separated by \t> -``` -To convert a psg to this format you need to replace all "\n" -by "\t". Make sure there are no tabs in your data. - -For an example of local usage (with the 'distributed' format) -the see test/example/ . This expects dtrain to be built without -DTRAIN_LOCAL. +See directories under test/ . Legal ----- -Copyright (c) 2012 by Patrick Simianer <p@simianer.de> +Copyright (c) 2012-2013 by Patrick Simianer <p@simianer.de> -See the file ../LICENSE.txt for the licensing terms that this software is +See the file LICENSE.txt in the root folder for the licensing terms that this software is released under. diff --git a/training/dtrain/dtrain.cc b/training/dtrain/dtrain.cc index 53487d34..dfb5b351 100644 --- a/training/dtrain/dtrain.cc +++ b/training/dtrain/dtrain.cc @@ -12,9 +12,7 @@ dtrain_init(int argc, char** argv, po::variables_map* cfg) ("decoder_config", po::value<string>(), "configuration file for cdec") ("print_weights", po::value<string>(), "weights to print on each iteration") ("stop_after", po::value<unsigned>()->default_value(0), "stop after X input sentences") - ("tmp", po::value<string>()->default_value("/tmp"), "temp dir to use") ("keep", po::value<bool>()->zero_tokens(), "keep weights files for each iteration") - ("hstreaming", po::value<string>(), "run in hadoop streaming mode, arg is a task id") ("epochs", po::value<unsigned>()->default_value(10), "# of iterations T (per shard)") ("k", po::value<unsigned>()->default_value(100), "how many translations to sample") ("sample_from", po::value<string>()->default_value("kbest"), "where to sample translations from: 'kbest', 'forest'") @@ -28,16 +26,14 @@ dtrain_init(int argc, char** argv, po::variables_map* cfg) ("gamma", po::value<weight_t>()->default_value(0.), "gamma for SVM (0 for perceptron)") ("select_weights", po::value<string>()->default_value("last"), "output best, last, avg weights ('VOID' to throw away)") ("rescale", po::value<bool>()->zero_tokens(), "rescale weight vector after each input") - ("l1_reg", po::value<string>()->default_value("none"), "apply l1 regularization as in 'Tsuroka et al' (2010)") + ("l1_reg", po::value<string>()->default_value("none"), "apply l1 regularization as in 'Tsuroka et al' (2010) UNTESTED") ("l1_reg_strength", po::value<weight_t>(), "l1 regularization strength") ("fselect", po::value<weight_t>()->default_value(-1), "select top x percent (or by threshold) of features after each epoch NOT IMPLEMENTED") // TODO ("approx_bleu_d", po::value<score_t>()->default_value(0.9), "discount for approx. BLEU") ("scale_bleu_diff", po::value<bool>()->zero_tokens(), "learning rate <- bleu diff of a misranked pair") ("loss_margin", po::value<weight_t>()->default_value(0.), "update if no error in pref pair but model scores this near") ("max_pairs", po::value<unsigned>()->default_value(std::numeric_limits<unsigned>::max()), "max. # of pairs per Sent.") -#ifdef DTRAIN_LOCAL ("refs,r", po::value<string>(), "references in local mode") -#endif ("noup", po::value<bool>()->zero_tokens(), "do not update weights"); po::options_description cl("Command Line Options"); cl.add_options() @@ -55,16 +51,6 @@ dtrain_init(int argc, char** argv, po::variables_map* cfg) cerr << cl << endl; return false; } - if (cfg->count("hstreaming") && (*cfg)["output"].as<string>() != "-") { - cerr << "When using 'hstreaming' the 'output' param should be '-'." << endl; - return false; - } -#ifdef DTRAIN_LOCAL - if ((*cfg)["input"].as<string>() == "-") { - cerr << "Can't use stdin as input with this binary. Recompile without DTRAIN_LOCAL" << endl; - return false; - } -#endif if ((*cfg)["sample_from"].as<string>() != "kbest" && (*cfg)["sample_from"].as<string>() != "forest") { cerr << "Wrong 'sample_from' param: '" << (*cfg)["sample_from"].as<string>() << "', use 'kbest' or 'forest'." << endl; @@ -111,17 +97,8 @@ main(int argc, char** argv) if (cfg.count("verbose")) verbose = true; bool noup = false; if (cfg.count("noup")) noup = true; - bool hstreaming = false; - string task_id; - if (cfg.count("hstreaming")) { - hstreaming = true; - quiet = true; - task_id = cfg["hstreaming"].as<string>(); - cerr.precision(17); - } bool rescale = false; if (cfg.count("rescale")) rescale = true; - HSReporter rep(task_id); bool keep = false; if (cfg.count("keep")) keep = true; @@ -224,16 +201,8 @@ main(int argc, char** argv) // buffer input for t > 0 vector<string> src_str_buf; // source strings (decoder takes only strings) vector<vector<WordID> > ref_ids_buf; // references as WordID vecs - // where temp files go - string tmp_path = cfg["tmp"].as<string>(); -#ifdef DTRAIN_LOCAL string refs_fn = cfg["refs"].as<string>(); ReadFile refs(refs_fn); -#else - string grammar_buf_fn = gettmpf(tmp_path, "dtrain-grammars"); - ogzstream grammar_buf_out; - grammar_buf_out.open(grammar_buf_fn.c_str()); -#endif unsigned in_sz = std::numeric_limits<unsigned>::max(); // input index, input size vector<pair<score_t, score_t> > all_scores; @@ -270,9 +239,7 @@ main(int argc, char** argv) cerr << setw(25) << "max pairs " << max_pairs << endl; cerr << setw(25) << "cdec cfg " << "'" << cfg["decoder_config"].as<string>() << "'" << endl; cerr << setw(25) << "input " << "'" << input_fn << "'" << endl; -#ifdef DTRAIN_LOCAL cerr << setw(25) << "refs " << "'" << refs_fn << "'" << endl; -#endif cerr << setw(25) << "output " << "'" << output_fn << "'" << endl; if (cfg.count("input_weights")) cerr << setw(25) << "weights in " << "'" << cfg["input_weights"].as<string>() << "'" << endl; @@ -285,14 +252,10 @@ main(int argc, char** argv) for (unsigned t = 0; t < T; t++) // T epochs { - if (hstreaming) cerr << "reporter:status:Iteration #" << t+1 << " of " << T << endl; - time_t start, end; time(&start); -#ifndef DTRAIN_LOCAL igzstream grammar_buf_in; if (t > 0) grammar_buf_in.open(grammar_buf_fn.c_str()); -#endif score_t score_sum = 0.; score_t model_sum(0); unsigned ii = 0, rank_errors = 0, margin_violations = 0, npairs = 0, f_count = 0, list_sz = 0; @@ -340,52 +303,6 @@ main(int argc, char** argv) // getting input vector<WordID> ref_ids; // reference as vector<WordID> -#ifndef DTRAIN_LOCAL - vector<string> in_split; // input: sid\tsrc\tref\tpsg - if (t == 0) { - // handling input - split_in(in, in_split); - if (hstreaming && ii == 0) cerr << "reporter:counter:" << task_id << ",First ID," << in_split[0] << endl; - // getting reference - vector<string> ref_tok; - 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); - // process and set grammar - bool broken_grammar = true; // ignore broken grammars - for (string::iterator it = in.begin(); it != in.end(); it++) { - if (!isspace(*it)) { - broken_grammar = false; - break; - } - } - if (broken_grammar) { - cerr << "Broken grammar for " << ii+1 << "! Ignoring this input." << endl; - continue; - } - boost::replace_all(in, "\t", "\n"); - in += "\n"; - grammar_buf_out << in << DTRAIN_GRAMMAR_DELIM << " " << in_split[0] << endl; - decoder.AddSupplementalGrammarFromString(in); - src_str_buf.push_back(in_split[1]); - // decode - observer->SetRef(ref_ids); - decoder.Decode(in_split[1], observer); - } else { - // get buffered grammar - 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.AddSupplementalGrammarFromString(grammar_str); - // decode - observer->SetRef(ref_ids_buf[ii]); - decoder.Decode(src_str_buf[ii], observer); - } -#else if (t == 0) { string r_; getline(*refs, r_); @@ -402,7 +319,6 @@ main(int argc, char** argv) decoder.Decode(in, observer); else decoder.Decode(src_str_buf[ii], observer); -#endif // get (scored) samples vector<ScoredHyp>* samples = observer->GetSamples(); @@ -505,11 +421,6 @@ main(int argc, char** argv) ++ii; - if (hstreaming) { - rep.update_counter("Seen #"+boost::lexical_cast<string>(t+1), 1u); - rep.update_counter("Seen", 1u); - } - } // input loop if (average) w_average += lambdas; @@ -518,21 +429,8 @@ main(int argc, char** argv) if (t == 0) { in_sz = ii; // remember size of input (# lines) - if (hstreaming) { - rep.update_counter("|Input|", ii); - rep.update_gcounter("|Input|", ii); - rep.update_gcounter("Shards", 1u); - } } -#ifndef DTRAIN_LOCAL - if (t == 0) { - grammar_buf_out.close(); - } else { - grammar_buf_in.close(); - } -#endif - // print some stats score_t score_avg = score_sum/(score_t)in_sz; score_t model_avg = model_sum/(score_t)in_sz; @@ -546,7 +444,7 @@ main(int argc, char** argv) } unsigned nonz = 0; - if (!quiet || hstreaming) nonz = (unsigned)lambdas.num_nonzero(); + if (!quiet) nonz = (unsigned)lambdas.num_nonzero(); if (!quiet) { cerr << _p5 << _p << "WEIGHTS" << endl; @@ -571,16 +469,6 @@ main(int argc, char** argv) cerr << " avg f count: " << f_count/(float)list_sz << endl; } - if (hstreaming) { - rep.update_counter("Score 1best avg #"+boost::lexical_cast<string>(t+1), (unsigned)(score_avg*DTRAIN_SCALE)); - rep.update_counter("Model 1best avg #"+boost::lexical_cast<string>(t+1), (unsigned)(model_avg*DTRAIN_SCALE)); - rep.update_counter("Pairs avg #"+boost::lexical_cast<string>(t+1), (unsigned)((npairs/(weight_t)in_sz)*DTRAIN_SCALE)); - rep.update_counter("Rank errors avg #"+boost::lexical_cast<string>(t+1), (unsigned)((rank_errors/(weight_t)in_sz)*DTRAIN_SCALE)); - rep.update_counter("Margin violations avg #"+boost::lexical_cast<string>(t+1), (unsigned)((margin_violations/(weight_t)in_sz)*DTRAIN_SCALE)); - rep.update_counter("Non zero feature count #"+boost::lexical_cast<string>(t+1), nonz); - rep.update_gcounter("Non zero feature count #"+boost::lexical_cast<string>(t+1), nonz); - } - pair<score_t,score_t> remember; remember.first = score_avg; remember.second = model_avg; @@ -611,10 +499,6 @@ main(int argc, char** argv) if (average) w_average /= (weight_t)T; -#ifndef DTRAIN_LOCAL - unlink(grammar_buf_fn.c_str()); -#endif - if (!noup) { if (!quiet) cerr << endl << "Writing weights file to '" << output_fn << "' ..." << endl; if (select_weights == "last" || average) { // last, average @@ -651,7 +535,6 @@ main(int argc, char** argv) } } } - if (output_fn == "-" && hstreaming) cout << "__SHARD_COUNT__\t1" << endl; if (!quiet) cerr << "done" << endl; } diff --git a/training/dtrain/dtrain.h b/training/dtrain/dtrain.h index 572fd613..f368d810 100644 --- a/training/dtrain/dtrain.h +++ b/training/dtrain/dtrain.h @@ -1,14 +1,12 @@ #ifndef _DTRAIN_H_ #define _DTRAIN_H_ -#undef DTRAIN_FASTER_PERCEPTRON // only look at misranked pairs - // DO NOT USE WITH SVM! -#define DTRAIN_LOCAL +#undef DTRAIN_FASTER_PERCEPTRON // only consider actually misranked pairs + // DO NOT ENABLE WITH SVM (gamma > 0) OR loss_margin! + #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> diff --git a/training/dtrain/hstreaming/avg.rb b/training/dtrain/hstreaming/avg.rb deleted file mode 100755 index 2599c732..00000000 --- a/training/dtrain/hstreaming/avg.rb +++ /dev/null @@ -1,32 +0,0 @@ -#!/usr/bin/env ruby -# first arg may be an int of custom shard count - -shard_count_key = "__SHARD_COUNT__" - -STDIN.set_encoding 'utf-8' -STDOUT.set_encoding 'utf-8' - -w = {} -c = {} -w.default = 0 -c.default = 0 -while line = STDIN.gets - key, val = line.split /\s/ - w[key] += val.to_f - c[key] += 1 -end - -if ARGV.size == 0 - shard_count = w["__SHARD_COUNT__"] -else - shard_count = ARGV[0].to_f -end -w.each_key { |k| - if k == shard_count_key - next - else - puts "#{k}\t#{w[k]/shard_count}" - #puts "# #{c[k]}" - end -} - diff --git a/training/dtrain/hstreaming/cdec.ini b/training/dtrain/hstreaming/cdec.ini deleted file mode 100644 index d4f5cecd..00000000 --- a/training/dtrain/hstreaming/cdec.ini +++ /dev/null @@ -1,22 +0,0 @@ -formalism=scfg -add_pass_through_rules=true -scfg_max_span_limit=15 -intersection_strategy=cube_pruning -cubepruning_pop_limit=30 -feature_function=WordPenalty -feature_function=KLanguageModel nc-wmt11.en.srilm.gz -#feature_function=ArityPenalty -#feature_function=CMR2008ReorderingFeatures -#feature_function=Dwarf -#feature_function=InputIndicator -#feature_function=LexNullJump -#feature_function=NewJump -#feature_function=NgramFeatures -#feature_function=NonLatinCount -#feature_function=OutputIndicator -#feature_function=RuleIdentityFeatures -#feature_function=RuleNgramFeatures -#feature_function=RuleShape -#feature_function=SourceSpanSizeFeatures -#feature_function=SourceWordPenalty -#feature_function=SpanFeatures diff --git a/training/dtrain/hstreaming/dtrain.ini b/training/dtrain/hstreaming/dtrain.ini deleted file mode 100644 index a2c219a1..00000000 --- a/training/dtrain/hstreaming/dtrain.ini +++ /dev/null @@ -1,15 +0,0 @@ -input=- -output=- -decoder_config=cdec.ini -tmp=/var/hadoop/mapred/local/ -epochs=1 -k=100 -N=4 -learning_rate=0.0001 -gamma=0 -scorer=stupid_bleu -sample_from=kbest -filter=uniq -pair_sampling=XYX -pair_threshold=0 -select_weights=last diff --git a/training/dtrain/hstreaming/dtrain.sh b/training/dtrain/hstreaming/dtrain.sh deleted file mode 100755 index 877ff94c..00000000 --- a/training/dtrain/hstreaming/dtrain.sh +++ /dev/null @@ -1,9 +0,0 @@ -#!/bin/bash -# script to run dtrain with a task id - -pushd . &>/dev/null -cd .. -ID=$(basename $(pwd)) # attempt_... -popd &>/dev/null -./dtrain -c dtrain.ini --hstreaming $ID - diff --git a/training/dtrain/hstreaming/hadoop-streaming-job.sh b/training/dtrain/hstreaming/hadoop-streaming-job.sh deleted file mode 100755 index 92419956..00000000 --- a/training/dtrain/hstreaming/hadoop-streaming-job.sh +++ /dev/null @@ -1,30 +0,0 @@ -#!/bin/sh - -EXP=a_simple_test - -# change these vars to fit your hadoop installation -HADOOP_HOME=/usr/lib/hadoop-0.20 -JAR=contrib/streaming/hadoop-streaming-0.20.2-cdh3u1.jar -HSTREAMING="$HADOOP_HOME/bin/hadoop jar $HADOOP_HOME/$JAR" - - IN=input_on_hdfs -OUT=output_weights_on_hdfs - -# you can -reducer to NONE if you want to -# do feature selection/averaging locally (e.g. to -# keep weights of all epochs) -$HSTREAMING \ - -mapper "dtrain.sh" \ - -reducer "ruby lplp.rb l2 select_k 100000" \ - -input $IN \ - -output $OUT \ - -file dtrain.sh \ - -file lplp.rb \ - -file ../dtrain \ - -file dtrain.ini \ - -file cdec.ini \ - -file ../test/example/nc-wmt11.en.srilm.gz \ - -jobconf mapred.reduce.tasks=30 \ - -jobconf mapred.max.map.failures.percent=0 \ - -jobconf mapred.job.name="dtrain $EXP" - diff --git a/training/dtrain/hstreaming/red-test b/training/dtrain/hstreaming/red-test deleted file mode 100644 index 2623d697..00000000 --- a/training/dtrain/hstreaming/red-test +++ /dev/null @@ -1,9 +0,0 @@ -a 1 -b 2 -c 3.5 -a 1 -b 2 -c 3.5 -d 1 -e 2 -__SHARD_COUNT__ 2 diff --git a/training/dtrain/hstreaming/lplp.rb b/training/dtrain/lplp.rb index f0cd58c5..f0cd58c5 100755 --- a/training/dtrain/hstreaming/lplp.rb +++ b/training/dtrain/lplp.rb diff --git a/training/dtrain/parallelize.rb b/training/dtrain/parallelize.rb index fca9b10d..24e7f49e 100755 --- a/training/dtrain/parallelize.rb +++ b/training/dtrain/parallelize.rb @@ -80,7 +80,7 @@ def make_shards(input, refs, num_shards, epoch, rand) shard_refs = File.new refs_fn, 'w+' refs_fns << refs_fn 0.upto(shard_sz-1) { |i| - j = index.pop + j = index.pop shard_in.write in_lines[j] shard_refs.write refs_lines[j] } @@ -125,7 +125,7 @@ end if use_qsub qsub_str_start = "qsub -cwd -sync y -b y -j y -o work/out.#{shard}.#{epoch} -N dtrain.#{shard}.#{epoch} \"" qsub_str_end = "\"" - local_end = '' + local_end = '' else local_end = "&>work/out.#{shard}.#{epoch}" end diff --git a/training/dtrain/test/example/cdec.ini b/training/dtrain/test/example/cdec.ini index 068ebd4d..0215416d 100644 --- a/training/dtrain/test/example/cdec.ini +++ b/training/dtrain/test/example/cdec.ini @@ -2,7 +2,7 @@ formalism=scfg add_pass_through_rules=true scfg_max_span_limit=15 intersection_strategy=cube_pruning -cubepruning_pop_limit=30 +cubepruning_pop_limit=200 feature_function=WordPenalty feature_function=KLanguageModel ./nc-wmt11.en.srilm.gz # all currently working feature functions for translation: |