def build_domain(data):
"""
Do feature extraction to determine the set of *supported* featues, i.e.
those active in the ground truth configuration and active labels. This
function will each features and label an integer.
"""
L = Alphabet()
A = Alphabet()
for x in data:
L.add_many(x.truth)
A.add_many(f for token in x.sequence for f in token.attributes)
# domains are now ready
L.freeze()
A.stop_growth()
return (L, A)
def build_domain(data):
"""
Do feature extraction to determine the set of *supported* featues, i.e.
those active in the ground truth configuration and active labels. This
function will each features and label an integer.
"""
L = Alphabet()
A = Alphabet()
for x in data:
L.add_many(x.truth) # add labels to label domain
# extract features of the target path
F = x.F
path = x.truth
A.add_many(F(0, None, path[0]))
A.add_many(k for t in xrange(1, x.N) for k in F(t, path[t-1], path[t]))
# domains are now ready
L.freeze()
A.stop_growth()
return (L, A)
