def compute_single_likelihood(self, udi):
"""
Compute the likelihood of a single data point, udi, an utteranceData
"""
assert isinstance(udi, UtteranceData)
# Types of utterances
trues, falses, others = self.partition_utterances(
udi.possible_utterances, udi.context)
#print "T:", trues
#print "F:", falses
#print "U:", others
u = udi.utterance
# compute the weights
all_weights = sum(
map(lambda u: self.weightfunction(u, udi.context),
udi.possible_utterances))
true_weights = sum(
map(lambda u: self.weightfunction(u, udi.context), trues))
met_weights = sum(
map(lambda u: self.weightfunction(u, udi.context),
falses)) + true_weights
w = self.weightfunction(u, udi.context) # the current word weight
if (u in trues):
p = self.palpha * self.alpha * w / true_weights + self.palpha * \
(1.0 - self.alpha) * w / met_weights + (1.0 - self.palpha) * w / \
all_weights # choose from the trues
elif (u in falses):
p = ifelse(true_weights == 0, 1.0,
1.0 - self.alpha) * self.palpha * w / met_weights + (
1.0 - self.palpha
) * w / all_weights # choose from the trues
else:
p = ifelse(met_weights == 0, 1.0,
(1.0 - self.palpha)) * w / all_weights
"""
TODO: WHY NOT THIS WAY, IGNORING tre_weights==0? Because if we sample, then we have 0 chance of getting a true when true_weights is like that. This causes problems in CCGLexicon
w = self.weightfunction(u, udi.context) # the current word weight
if (u in trues): p = self.palpha * (self.alpha * w / true_weights + (1.0 - self.alpha) * w / met_weights) + (1.0 - self.palpha) * w / all_weights # choose from the trues
elif (u in falses): p = self.palpha * (1.0-self.alpha) * w / met_weights + (1.0 - self.palpha) * w / all_weights # choose from the trues
else: p = (1.0 - self.palpha) * w / all_weights
"""
return log(p)
def compute_single_likelihood(self, udi):
"""
Compute the likelihood of a single data point, udi, an utteranceData
"""
assert isinstance(udi, UtteranceData)
# Types of utterances
trues, falses, others = self.partition_utterances( udi.possible_utterances, udi.context)
#print "T:", trues
#print "F:", falses
#print "U:", others
u = udi.utterance
# compute the weights
all_weights = sum(map( lambda u: self.weightfunction(u, udi.context), udi.possible_utterances ))
true_weights = sum(map( lambda u: self.weightfunction(u, udi.context), trues))
met_weights = sum(map( lambda u: self.weightfunction(u, udi.context), falses)) + true_weights
w = self.weightfunction(u, udi.context) # the current word weight
if(u in trues):
p = self.palpha * self.alpha * w / true_weights + self.palpha * \
(1.0 - self.alpha) * w / met_weights + (1.0 - self.palpha) * w / \
all_weights # choose from the trues
elif (u in falses):
p = ifelse(true_weights==0, 1.0, 1.0-self.alpha) * self.palpha * w / met_weights + (1.0 - self.palpha) * w / all_weights # choose from the trues
else:
p = ifelse(met_weights==0, 1.0, (1.0 - self.palpha)) * w / all_weights
"""
TODO: WHY NOT THIS WAY, IGNORING tre_weights==0? Because if we sample, then we have 0 chance of getting a true when true_weights is like that. This causes problems in CCGLexicon
w = self.weightfunction(u, udi.context) # the current word weight
if (u in trues): p = self.palpha * (self.alpha * w / true_weights + (1.0 - self.alpha) * w / met_weights) + (1.0 - self.palpha) * w / all_weights # choose from the trues
elif (u in falses): p = self.palpha * (1.0-self.alpha) * w / met_weights + (1.0 - self.palpha) * w / all_weights # choose from the trues
else: p = (1.0 - self.palpha) * w / all_weights
"""
return log(p)
def gricean_weight(h, testing_set, nu=1.0):
"""Takes a hypothesis and its function and returns the weight under a gricean setup.
Production probability is proportional to: exp( 1.0 / (nu + proportionoftimeitistrue) )
Notes:
The max weight is 1/nu, and this should not be huge compared to 1/alpha
We (should) boundedly memoize this
"""
pct = float(sum(map(lambda s: ifelse(h(s), 1.0, 0.0),
testing_set))) / len(testing_set)
# pul out the context sets and apply f
#pct = float(sum(map(lambda s: ifelse(f(*s) is True, 1.0, 0.0), testing_set) )) / len(testing_set)
# pul out the context sets and apply f
#pct = float(sum(map(lambda s: ifelse(collapse_undef(f(*s)), 1.0, 0.0), testing_set) )) / len(testing_set)
return 1.0 / (nu + pct)
