Mercurial > pylearn

comparison embeddings/one-per-line.py @ 468:a07948f780b9

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Moved embeddings out of sandbox
author Joseph Turian <turian@iro.umontreal.ca>
date Tue, 21 Oct 2008 16:24:44 -0400
parents sandbox/embeddings/one-per-line.py@131e19dfe793
children
comparison
equal deleted inserted replaced
467:f3711bcc467e 468:a07948f780b9
1 #!/usr/bin/python
2
3 import string
4 #import psyco
5
6 weightsfile = "lm-weights.txt"
7 vocabfile = "words.asc"
8 size = 30000
9 dimensions = 50
10
11 import numpy, math
12 import sys
13 from common.str import percent
14
15 word_to_vector = {}
16
17 f = open(weightsfile)
18 f.readline()
19 vals = [float(v) for v in string.split(f.readline())]
20 assert len(vals) == size * dimensions
21 vals.reverse()
22 #for i in range(size):
23 r = range(size)
24 r.reverse()
25 for i in r:
26 l = vals[dimensions*i:dimensions*(i+1)]
27 print string.join([`s` for s in l], "\t")