def visualize(cnt, model, rundir, idxs, str):
"""
Visualize a set of examples using t-SNE.
"""
from vocabulary import wordmap, wordform
PERPLEXITY = 30
idxs = [id % model.parameters.embeddings.shape[0] for id in idxs]
x = model.parameters.embeddings[idxs]
print x.shape
#titles = [`wordmap().str(id)` for id in idxs]
titles = [wordform(id) for id in idxs]
import os.path
filename = os.path.join(
rundir, "embeddings.model-%s.-%s-%d.png" % (model.modelname, str, cnt))
try:
from textSNE.calc_tsne import tsne
# from textSNE.tsne import tsne
out = tsne(x, perplexity=PERPLEXITY)
from textSNE.render import render
render([(title, point[0], point[1])
for title, point in zip(titles, out)], filename)
except IOError:
logging.info("ERROR visualizing", filename, ". Continuing...")
def visualize(cnt, model, rundir, idxs, str):
"""
Visualize a set of examples using t-SNE.
"""
from vocabulary import wordmap, wordform
PERPLEXITY=30
idxs = [id % model.parameters.embeddings.shape[0] for id in idxs]
x = model.parameters.embeddings[idxs]
print x.shape
#titles = [`wordmap().str(id)` for id in idxs]
titles = [wordform(id) for id in idxs]
import os.path
filename = os.path.join(rundir, "embeddings.model-%s.-%s-%d.png" % (model.modelname, str, cnt))
try:
from textSNE.calc_tsne import tsne
# from textSNE.tsne import tsne
out = tsne(x, perplexity=PERPLEXITY)
from textSNE.render import render
render([(title, point[0], point[1]) for title, point in zip(titles, out)], filename)
except IOError:
logging.info("ERROR visualizing", filename, ". Continuing...")
from targetvocabulary import targetmap
for w1 in wordmap().all:
w1 = wordmap().id(w1)
# Actually, should assert W2W SKIP TRANSLATIONS FROM UNKNOWN WORD
assert HYPERPARAMETERS["W2W SKIP TRANSLATIONS TO UNKNOWN WORD"]
if language(w1) is None:
print >> sys.stderr, "Skipping %s" % `wordmap().str(w1)`
continue
if w1 not in targetmap():
print >> sys.stderr, "Skipping %s, not a source word in targetmap" % `wordmap().str(w1)`
continue
for l2 in targetmap()[w1]:
totcnt = 0
for cnt, w2 in dictsort(targetmap()[w1][l2]): totcnt += cnt
print wordmap().str(w1), l2, [(percent(cnt, totcnt), wordform(w2)) for cnt, w2 in dictsort(targetmap()[w1][l2])]
print >> sys.stderr, "REVERSE MAP NOW"
for w1 in wordmap().all:
w1 = wordmap().id(w1)
# Actually, should assert W2W SKIP TRANSLATIONS FROM UNKNOWN WORD
assert HYPERPARAMETERS["W2W SKIP TRANSLATIONS TO UNKNOWN WORD"]
if language(w1) is None:
print >> sys.stderr, "Skipping %s" % `wordmap().str(w1)`
continue
if w1 not in targetmap(name="reverse"):
print >> sys.stderr, "Skipping %s, not a source word in targetmap" % `wordmap().str(w1)`
continue
for l2 in targetmap(name="reverse")[w1]:
totcnt = 0
w1 = wordmap().id(w1)
# Actually, should assert W2W SKIP TRANSLATIONS FROM UNKNOWN WORD
assert HYPERPARAMETERS["W2W SKIP TRANSLATIONS TO UNKNOWN WORD"]
if language(w1) is None:
print >> sys.stderr, "Skipping %s" % ` wordmap().str(w1) `
continue
if w1 not in targetmap():
print >> sys.stderr, "Skipping %s, not a source word in targetmap" % ` wordmap(
).str(w1) `
continue
for l2 in targetmap()[w1]:
totcnt = 0
for cnt, w2 in dictsort(targetmap()[w1][l2]):
totcnt += cnt
print wordmap().str(w1), l2, [
(percent(cnt, totcnt), wordform(w2))
for cnt, w2 in dictsort(targetmap()[w1][l2])
]
print >> sys.stderr, "REVERSE MAP NOW"
for w1 in wordmap().all:
w1 = wordmap().id(w1)
# Actually, should assert W2W SKIP TRANSLATIONS FROM UNKNOWN WORD
assert HYPERPARAMETERS["W2W SKIP TRANSLATIONS TO UNKNOWN WORD"]
if language(w1) is None:
print >> sys.stderr, "Skipping %s" % ` wordmap().str(w1) `
continue
if w1 not in targetmap(name="reverse"):
print >> sys.stderr, "Skipping %s, not a source word in targetmap" % ` wordmap(
).str(w1) `
