Files

74 lines
5.5 KiB
Diff
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
Adjust demo paths so they work regardless of the current working directory.
--- demo-analogy.sh.orig 2014-09-07 01:54:27.000000000 +0900
+++ demo-analogy.sh 2014-12-24 22:55:24.000000000 +0900
@@ -7,5 +7,5 @@
echo Note that for the word analogy to perform well, the model should be trained on much larger data set
echo Example input: paris france berlin
echo ---------------------------------------------------------------------------------------------------
-time ./word2vec -train text8 -output vectors.bin -cbow 1 -size 200 -window 8 -negative 25 -hs 0 -sample 1e-4 -threads 20 -binary 1 -iter 15
-./word-analogy vectors.bin
+time @EXECDIR@/word2vec -train text8 -output vectors.bin -cbow 1 -size 200 -window 8 -negative 25 -hs 0 -sample 1e-4 -threads 20 -binary 1 -iter 15
+@EXECDIR@/word-analogy vectors.bin
--- demo-classes.sh.orig 2014-09-07 01:54:27.000000000 +0900
+++ demo-classes.sh 2014-12-24 22:57:00.000000000 +0900
@@ -3,6 +3,6 @@
wget http://mattmahoney.net/dc/text8.zip -O text8.gz
gzip -d text8.gz -f
fi
-time ./word2vec -train text8 -output classes.txt -cbow 1 -size 200 -window 8 -negative 25 -hs 0 -sample 1e-4 -threads 20 -iter 15 -classes 500
+time @EXECDIR@/word2vec -train text8 -output classes.txt -cbow 1 -size 200 -window 8 -negative 25 -hs 0 -sample 1e-4 -threads 20 -iter 15 -classes 500
sort classes.txt -k 2 -n > classes.sorted.txt
echo The word classes were saved to file classes.sorted.txt
--- demo-phrase-accuracy.sh.orig 2014-09-07 01:54:27.000000000 +0900
+++ demo-phrase-accuracy.sh 2014-12-24 22:57:51.000000000 +0900
@@ -4,8 +4,8 @@
gzip -d news.2012.en.shuffled.gz -f
fi
sed -e "s//'/g" -e "s//'/g" -e "s/''/ /g" < news.2012.en.shuffled | tr -c "A-Za-z'_ \n" " " > news.2012.en.shuffled-norm0
-time ./word2phrase -train news.2012.en.shuffled-norm0 -output news.2012.en.shuffled-norm0-phrase0 -threshold 200 -debug 2
-time ./word2phrase -train news.2012.en.shuffled-norm0-phrase0 -output news.2012.en.shuffled-norm0-phrase1 -threshold 100 -debug 2
+time @EXECDIR@/word2phrase -train news.2012.en.shuffled-norm0 -output news.2012.en.shuffled-norm0-phrase0 -threshold 200 -debug 2
+time @EXECDIR@/word2phrase -train news.2012.en.shuffled-norm0-phrase0 -output news.2012.en.shuffled-norm0-phrase1 -threshold 100 -debug 2
tr A-Z a-z < news.2012.en.shuffled-norm0-phrase1 > news.2012.en.shuffled-norm1-phrase1
-time ./word2vec -train news.2012.en.shuffled-norm1-phrase1 -output vectors-phrase.bin -cbow 1 -size 200 -window 10 -negative 25 -hs 0 -sample 1e-5 -threads 20 -binary 1 -iter 15
-./compute-accuracy vectors-phrase.bin < questions-phrases.txt
+time @EXECDIR@/word2vec -train news.2012.en.shuffled-norm1-phrase1 -output vectors-phrase.bin -cbow 1 -size 200 -window 10 -negative 25 -hs 0 -sample 1e-5 -threads 20 -binary 1 -iter 15
+@EXECDIR@/compute-accuracy vectors-phrase.bin < questions-phrases.txt
--- demo-phrases.sh.orig 2014-09-07 01:54:27.000000000 +0900
+++ demo-phrases.sh 2014-12-24 22:58:20.000000000 +0900
@@ -4,8 +4,8 @@
gzip -d news.2012.en.shuffled.gz -f
fi
sed -e "s//'/g" -e "s//'/g" -e "s/''/ /g" < news.2012.en.shuffled | tr -c "A-Za-z'_ \n" " " > news.2012.en.shuffled-norm0
-time ./word2phrase -train news.2012.en.shuffled-norm0 -output news.2012.en.shuffled-norm0-phrase0 -threshold 200 -debug 2
-time ./word2phrase -train news.2012.en.shuffled-norm0-phrase0 -output news.2012.en.shuffled-norm0-phrase1 -threshold 100 -debug 2
+time @EXECDIR@/word2phrase -train news.2012.en.shuffled-norm0 -output news.2012.en.shuffled-norm0-phrase0 -threshold 200 -debug 2
+time @EXECDIR@/word2phrase -train news.2012.en.shuffled-norm0-phrase0 -output news.2012.en.shuffled-norm0-phrase1 -threshold 100 -debug 2
tr A-Z a-z < news.2012.en.shuffled-norm0-phrase1 > news.2012.en.shuffled-norm1-phrase1
-time ./word2vec -train news.2012.en.shuffled-norm1-phrase1 -output vectors-phrase.bin -cbow 1 -size 200 -window 10 -negative 25 -hs 0 -sample 1e-5 -threads 20 -binary 1 -iter 15
-./distance vectors-phrase.bin
+time @EXECDIR@/word2vec -train news.2012.en.shuffled-norm1-phrase1 -output vectors-phrase.bin -cbow 1 -size 200 -window 10 -negative 25 -hs 0 -sample 1e-5 -threads 20 -binary 1 -iter 15
+@EXECDIR@/distance vectors-phrase.bin
--- demo-word-accuracy.sh.orig 2014-09-07 01:54:27.000000000 +0900
+++ demo-word-accuracy.sh 2014-12-24 22:58:49.000000000 +0900
@@ -3,6 +3,6 @@
wget http://mattmahoney.net/dc/text8.zip -O text8.gz
gzip -d text8.gz -f
fi
-time ./word2vec -train text8 -output vectors.bin -cbow 1 -size 200 -window 8 -negative 25 -hs 0 -sample 1e-4 -threads 20 -binary 1 -iter 15
-./compute-accuracy vectors.bin 30000 < questions-words.txt
-# to compute accuracy with the full vocabulary, use: ./compute-accuracy vectors.bin < questions-words.txt
+time @EXECDIR@/word2vec -train text8 -output vectors.bin -cbow 1 -size 200 -window 8 -negative 25 -hs 0 -sample 1e-4 -threads 20 -binary 1 -iter 15
+@EXECDIR@/compute-accuracy vectors.bin 30000 < questions-words.txt
+# to compute accuracy with the full vocabulary, use: @EXECDIR@/compute-accuracy vectors.bin < questions-words.txt
--- demo-word.sh.orig 2014-09-07 01:54:27.000000000 +0900
+++ demo-word.sh 2014-12-24 22:59:00.000000000 +0900
@@ -3,5 +3,5 @@
wget http://mattmahoney.net/dc/text8.zip -O text8.gz
gzip -d text8.gz -f
fi
-time ./word2vec -train text8 -output vectors.bin -cbow 1 -size 200 -window 8 -negative 25 -hs 0 -sample 1e-4 -threads 20 -binary 1 -iter 15
-./distance vectors.bin
+time @EXECDIR@/word2vec -train text8 -output vectors.bin -cbow 1 -size 200 -window 8 -negative 25 -hs 0 -sample 1e-4 -threads 20 -binary 1 -iter 15
+@EXECDIR@/distance vectors.bin