From 4cd076acd1760035df693ff4f93a79b5d5c3d29d Mon Sep 17 00:00:00 2001
From: Patrick Simianer
Date: Sun, 25 Sep 2011 21:59:39 +0200
Subject: removed old stuff
---
dtrain/dtrain.cc | 2 +-
dtrain/ksampler.h | 6 +-----
dtrain/test/cdec_toy/cdec.ini | 4 ----
dtrain/test/cdec_toy/grammar | 12 ------------
dtrain/test/cdec_toy/in | 1 -
dtrain/test/cdec_toy/weights | 2 --
dtrain/test/toy/cdec.ini | 2 ++
dtrain/test/toy/dtrain.ini | 8 ++++++++
dtrain/test/toy/in | 2 ++
dtrain/test/toy_example/cdec.ini | 2 --
dtrain/test/toy_example/dtrain.ini | 8 --------
dtrain/test/toy_example/in | 2 --
dtrain/test/wc_pipes/bible.txt.gz | Bin 1193106 -> 0 bytes
dtrain/test/wc_pipes/jobconf.xml | 16 ----------------
dtrain/test/wc_pipes/run.sh | 11 -----------
dtrain/test/wc_pipes/wordcount.cc | 38 -------------------------------------
dtrain/test/wc_pipes/wordcount.h | 34 ---------------------------------
17 files changed, 14 insertions(+), 136 deletions(-)
delete mode 100644 dtrain/test/cdec_toy/cdec.ini
delete mode 100644 dtrain/test/cdec_toy/grammar
delete mode 100644 dtrain/test/cdec_toy/in
delete mode 100644 dtrain/test/cdec_toy/weights
create mode 100644 dtrain/test/toy/cdec.ini
create mode 100644 dtrain/test/toy/dtrain.ini
create mode 100644 dtrain/test/toy/in
delete mode 100644 dtrain/test/toy_example/cdec.ini
delete mode 100644 dtrain/test/toy_example/dtrain.ini
delete mode 100644 dtrain/test/toy_example/in
delete mode 100644 dtrain/test/wc_pipes/bible.txt.gz
delete mode 100644 dtrain/test/wc_pipes/jobconf.xml
delete mode 100755 dtrain/test/wc_pipes/run.sh
delete mode 100644 dtrain/test/wc_pipes/wordcount.cc
delete mode 100644 dtrain/test/wc_pipes/wordcount.h
diff --git a/dtrain/dtrain.cc b/dtrain/dtrain.cc
index ad1ab7b7..b1ea1e46 100644
--- a/dtrain/dtrain.cc
+++ b/dtrain/dtrain.cc
@@ -253,7 +253,7 @@ main(int argc, char** argv)
}
}
if (broken_grammar) continue;
- boost::replace_all(in_split[3], " __NEXT__RULE__ ", "\n");
+ boost::replace_all(in_split[3], " __NEXT__RULE__ ", "\n"); // TODO
in_split[3] += "\n";
grammar_buf_out << in_split[3] << DTRAIN_GRAMMAR_DELIM << " " << in_split[0] << endl;
decoder.SetSentenceGrammarFromString(in_split[3]);
diff --git a/dtrain/ksampler.h b/dtrain/ksampler.h
index bbe2b402..08bf1498 100644
--- a/dtrain/ksampler.h
+++ b/dtrain/ksampler.h
@@ -9,10 +9,6 @@ namespace dtrain
{
-/*
- * KSampler
- *
- */
struct KSampler : public HypSampler
{
const size_t k_;
@@ -34,7 +30,7 @@ struct KSampler : public HypSampler
s_.clear();
std::vector samples;
HypergraphSampler::sample_hypotheses(forest, k_, prng_, &samples);
- for ( size_t i = 0; i < k_; ++i ) {
+ for (size_t i = 0; i < k_; ++i) {
ScoredHyp h;
h.w = samples[i].words;
h.f = samples[i].fmap;
diff --git a/dtrain/test/cdec_toy/cdec.ini b/dtrain/test/cdec_toy/cdec.ini
deleted file mode 100644
index 9eb34512..00000000
--- a/dtrain/test/cdec_toy/cdec.ini
+++ /dev/null
@@ -1,4 +0,0 @@
-formalism=scfg
-grammar=../dtrain/test/toy_cdec/grammar
-add_pass_through_rules=true
-weights=../dtrain/test/toy_cdec/weights
diff --git a/dtrain/test/cdec_toy/grammar b/dtrain/test/cdec_toy/grammar
deleted file mode 100644
index aeed75ef..00000000
--- a/dtrain/test/cdec_toy/grammar
+++ /dev/null
@@ -1,12 +0,0 @@
-[S] ||| [NP,1] [VP,2] ||| [1] [2] ||| logp=0
-[NP] ||| ich ||| i ||| logp=0
-[NP] ||| ein [NN,1] ||| a [1] ||| logp=0
-[NN] ||| [JJ,1] haus ||| [1] house ||| logp=0 use_house=1
-[NN] ||| [JJ,1] haus ||| [1] shell ||| logp=0 use_shell=1
-[JJ] ||| kleines ||| small ||| logp=0
-[JJ] ||| kleines ||| little ||| logp=0
-[JJ] ||| grosses ||| big ||| logp=0
-[JJ] ||| grosses ||| large ||| logp=0
-[VP] ||| [V,1] [NP,2] ||| [1] [2] ||| logp=0
-[V] ||| sah ||| saw ||| logp=0
-[V] ||| fand ||| found ||| logp=0
diff --git a/dtrain/test/cdec_toy/in b/dtrain/test/cdec_toy/in
deleted file mode 100644
index e6df9275..00000000
--- a/dtrain/test/cdec_toy/in
+++ /dev/null
@@ -1 +0,0 @@
-ich sah ein kleines haus
diff --git a/dtrain/test/cdec_toy/weights b/dtrain/test/cdec_toy/weights
deleted file mode 100644
index 10d7ed83..00000000
--- a/dtrain/test/cdec_toy/weights
+++ /dev/null
@@ -1,2 +0,0 @@
-logp 1
-use_shell 1
diff --git a/dtrain/test/toy/cdec.ini b/dtrain/test/toy/cdec.ini
new file mode 100644
index 00000000..98b02d44
--- /dev/null
+++ b/dtrain/test/toy/cdec.ini
@@ -0,0 +1,2 @@
+formalism=scfg
+add_pass_through_rules=true
diff --git a/dtrain/test/toy/dtrain.ini b/dtrain/test/toy/dtrain.ini
new file mode 100644
index 00000000..3ab4f8d4
--- /dev/null
+++ b/dtrain/test/toy/dtrain.ini
@@ -0,0 +1,8 @@
+decoder_config=test/toy_example/cdec.ini
+ksamples=4
+ngrams=3
+epochs=2
+input=test/toy_example/toy.in
+scorer=bleu
+output=-
+wprint=logp use_shell use_house PassThrough
diff --git a/dtrain/test/toy/in b/dtrain/test/toy/in
new file mode 100644
index 00000000..63f97158
--- /dev/null
+++ b/dtrain/test/toy/in
@@ -0,0 +1,2 @@
+0 ich sah ein kleines haus i saw a little house [S] ||| [NP,1] [VP,2] ||| [1] [2] ||| logp=0 __NEXT_RULE__ [NP] ||| ich ||| i ||| logp=0 __NEXT_RULE__ [NP] ||| ein [NN,1] ||| a [1] ||| logp=0 __NEXT_RULE__ [NN] ||| [JJ,1] haus ||| [1] house ||| logp=0 use_house=1 __NEXT_RULE__ [NN] ||| [JJ,1] haus ||| [1] shell ||| logp=0 use_shell=1 __NEXT_RULE__ [JJ] ||| kleines ||| small ||| logp=0 __NEXT_RULE__ [JJ] ||| kleines ||| little ||| logp=0 __NEXT_RULE__ [JJ] ||| grosses ||| big ||| logp=0 __NEXT_RULE__ [JJ] ||| grosses ||| large ||| logp=0 __NEXT_RULE__ [VP] ||| [V,1] [NP,2] ||| [1] [2] ||| logp=0 __NEXT_RULE__ [V] ||| sah ||| saw ||| logp=0 __NEXT_RULE__ [V] ||| fand ||| found ||| logp=0
+1 ich fand ein grosses haus i found a large house [S] ||| [NP,1] [VP,2] ||| [1] [2] ||| logp=0 __NEXT_RULE__ [NP] ||| ich ||| i ||| logp=0 __NEXT_RULE__ [NP] ||| ein [NN,1] ||| a [1] ||| logp=0 __NEXT_RULE__ [NN] ||| [JJ,1] haus ||| [1] house ||| logp=0 use_house=1 __NEXT_RULE__ [NN] ||| [JJ,1] haus ||| [1] shell ||| logp=0 use_shell=1 __NEXT_RULE__ [JJ] ||| kleines ||| small ||| logp=0 __NEXT_RULE__ [JJ] ||| kleines ||| little ||| logp=0 __NEXT_RULE__ [JJ] ||| grosses ||| big ||| logp=0 __NEXT_RULE__ [JJ] ||| grosses ||| large ||| logp=0 __NEXT_RULE__ [VP] ||| [V,1] [NP,2] ||| [1] [2] ||| logp=0 __NEXT_RULE__ [V] ||| sah ||| saw ||| logp=0 __NEXT_RULE__ [V] ||| fand ||| found ||| logp=0
diff --git a/dtrain/test/toy_example/cdec.ini b/dtrain/test/toy_example/cdec.ini
deleted file mode 100644
index 98b02d44..00000000
--- a/dtrain/test/toy_example/cdec.ini
+++ /dev/null
@@ -1,2 +0,0 @@
-formalism=scfg
-add_pass_through_rules=true
diff --git a/dtrain/test/toy_example/dtrain.ini b/dtrain/test/toy_example/dtrain.ini
deleted file mode 100644
index 3ab4f8d4..00000000
--- a/dtrain/test/toy_example/dtrain.ini
+++ /dev/null
@@ -1,8 +0,0 @@
-decoder_config=test/toy_example/cdec.ini
-ksamples=4
-ngrams=3
-epochs=2
-input=test/toy_example/toy.in
-scorer=bleu
-output=-
-wprint=logp use_shell use_house PassThrough
diff --git a/dtrain/test/toy_example/in b/dtrain/test/toy_example/in
deleted file mode 100644
index 63f97158..00000000
--- a/dtrain/test/toy_example/in
+++ /dev/null
@@ -1,2 +0,0 @@
-0 ich sah ein kleines haus i saw a little house [S] ||| [NP,1] [VP,2] ||| [1] [2] ||| logp=0 __NEXT_RULE__ [NP] ||| ich ||| i ||| logp=0 __NEXT_RULE__ [NP] ||| ein [NN,1] ||| a [1] ||| logp=0 __NEXT_RULE__ [NN] ||| [JJ,1] haus ||| [1] house ||| logp=0 use_house=1 __NEXT_RULE__ [NN] ||| [JJ,1] haus ||| [1] shell ||| logp=0 use_shell=1 __NEXT_RULE__ [JJ] ||| kleines ||| small ||| logp=0 __NEXT_RULE__ [JJ] ||| kleines ||| little ||| logp=0 __NEXT_RULE__ [JJ] ||| grosses ||| big ||| logp=0 __NEXT_RULE__ [JJ] ||| grosses ||| large ||| logp=0 __NEXT_RULE__ [VP] ||| [V,1] [NP,2] ||| [1] [2] ||| logp=0 __NEXT_RULE__ [V] ||| sah ||| saw ||| logp=0 __NEXT_RULE__ [V] ||| fand ||| found ||| logp=0
-1 ich fand ein grosses haus i found a large house [S] ||| [NP,1] [VP,2] ||| [1] [2] ||| logp=0 __NEXT_RULE__ [NP] ||| ich ||| i ||| logp=0 __NEXT_RULE__ [NP] ||| ein [NN,1] ||| a [1] ||| logp=0 __NEXT_RULE__ [NN] ||| [JJ,1] haus ||| [1] house ||| logp=0 use_house=1 __NEXT_RULE__ [NN] ||| [JJ,1] haus ||| [1] shell ||| logp=0 use_shell=1 __NEXT_RULE__ [JJ] ||| kleines ||| small ||| logp=0 __NEXT_RULE__ [JJ] ||| kleines ||| little ||| logp=0 __NEXT_RULE__ [JJ] ||| grosses ||| big ||| logp=0 __NEXT_RULE__ [JJ] ||| grosses ||| large ||| logp=0 __NEXT_RULE__ [VP] ||| [V,1] [NP,2] ||| [1] [2] ||| logp=0 __NEXT_RULE__ [V] ||| sah ||| saw ||| logp=0 __NEXT_RULE__ [V] ||| fand ||| found ||| logp=0
diff --git a/dtrain/test/wc_pipes/bible.txt.gz b/dtrain/test/wc_pipes/bible.txt.gz
deleted file mode 100644
index a25a65d9..00000000
Binary files a/dtrain/test/wc_pipes/bible.txt.gz and /dev/null differ
diff --git a/dtrain/test/wc_pipes/jobconf.xml b/dtrain/test/wc_pipes/jobconf.xml
deleted file mode 100644
index facdbce6..00000000
--- a/dtrain/test/wc_pipes/jobconf.xml
+++ /dev/null
@@ -1,16 +0,0 @@
-
-
-
- hadoop.pipes.executable
- path/to/dp_hadoop_pipes_test
-
-
- hadoop.pipes.java.recordreader
- true
-
-
- hadoop.pipes.java.recordwriter
- true
-
-
-
diff --git a/dtrain/test/wc_pipes/run.sh b/dtrain/test/wc_pipes/run.sh
deleted file mode 100755
index de7d8aef..00000000
--- a/dtrain/test/wc_pipes/run.sh
+++ /dev/null
@@ -1,11 +0,0 @@
-#!/bin/sh
-
-HADOOP=~/z/hadoop-0.20.2/
-
-$HADOOP/bin/hadoop dfs -put wordcount wordcount
-
-$HADOOP/bin/hadoop pipes -D hadoop.pipes.java.recordreader=true \
- -D hadoop.pipes.java.recordwriter=true \
- -input in/bible.txt -output out/bible_out \
- -program ./wordcount
-
diff --git a/dtrain/test/wc_pipes/wordcount.cc b/dtrain/test/wc_pipes/wordcount.cc
deleted file mode 100644
index 39560a31..00000000
--- a/dtrain/test/wc_pipes/wordcount.cc
+++ /dev/null
@@ -1,38 +0,0 @@
-#include "wordcount.hh"
-
-
-void
-WordcountMapper::map(HadoopPipes::MapContext & context)
-{
- typedef boost::tokenizer<> tokenizer_t;
- tokenizer_t tokenizer(context.getInputValue());
-
- for( tokenizer_t::const_iterator i = tokenizer.begin();
- tokenizer.end() != i; ++i ) {
- context.emit(boost::to_lower_copy(*i), "1");
- }
-}
-
-void
-WordcountReducer::reduce(HadoopPipes::ReduceContext & context)
-{
- uint32_t count( 0 );
-
- do {
- ++count;
- } while( context.nextValue() );
-
- std::cout << context.getInputKey() << endl;
- context.emit( context.getInputKey(),
- boost::lexical_cast(count) );
-}
-
-
-int
-main( int argc, char * argv[] )
-{
- HadoopPipes::TemplateFactory2 factory;
- return HadoopPipes::runTask( factory );
-}
-
diff --git a/dtrain/test/wc_pipes/wordcount.h b/dtrain/test/wc_pipes/wordcount.h
deleted file mode 100644
index c8fc8a29..00000000
--- a/dtrain/test/wc_pipes/wordcount.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef __WORDCOUNT_HH__
-#define __WORDCOUNT_HH__
-
-
-#include
-#include
-
-#include "hadoop/Pipes.hh"
-#include "hadoop/TemplateFactory.hh"
-
-#include
-#include
-#include
-
-using namespace std;
-
-
-class WordcountMapper : public HadoopPipes::Mapper
-{
- public:
- WordcountMapper( const HadoopPipes::TaskContext & ) {};
- void map( HadoopPipes::MapContext &context );
-};
-
-class WordcountReducer : public HadoopPipes::Reducer
-{
- public:
- WordcountReducer( const HadoopPipes::TaskContext & ) {};
- void reduce( HadoopPipes::ReduceContext & context );
-};
-
-
-#endif
-
--
cgit v1.2.3