2013-08-01 21:28:42 +02:00
|
|
|
make
|
|
|
|
if [ ! -e text8 ]; then
|
|
|
|
wget http://mattmahoney.net/dc/text8.zip -O text8.gz
|
|
|
|
gzip -d text8.gz -f
|
|
|
|
fi
|
2014-09-06 18:54:27 +02:00
|
|
|
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
|
2013-08-01 21:28:42 +02:00
|
|
|
sort classes.txt -k 2 -n > classes.sorted.txt
|
|
|
|
echo The word classes were saved to file classes.sorted.txt
|