def prob_classify(self, featureset):
"""Calculate the probabilities the given featureset classifications
and return a DictionaryProbDist instance.
Works in O(nm) with n = # of labels, m = # of featureset elements.
"""
# Work on a copy of the feature set, because we mutate it.
fset = featureset.copy()
for fname in featureset:
for label in self._labels:
if (label, fname) in self._feature_probdist:
break
else:
# Discard feature name we haven't been trained on from the
# input set.
del fset[fname]
# Now we're working with a feature set that only includes known
# features.
# Instead of working with the product of the separate probabilities,
# we use the sum of the logarithms to prevent underflows and make the
# result more stable.
#: The probability of each label, given the features. Starting with
#: the probability of the label itself.
logprob = {}
for label in self._labels:
logprob[label] = self._label_probdist.logprob(label)
# Add the logarithmic probability of the features given the labels.
for label in self._labels:
for (fname, fval) in fset.items():
feature_probs = self._feature_probdist.get((label, fname))
if feature_probs is not None:
logprob[label] += feature_probs.logprob(fval)
else:
# This should not occur if the classifier was created with
# the train() method.
logprob[label] += sum_logs([]) # = -INF.
return DictionaryProbDist(logprob, normalize=True, log=True)
def prob_classify(self, featureset):
"""Calculate the probabilities the given featureset classifications
and return a DictionaryProbDist instance.
Works in O(nm) with n = # of labels, m = # of featureset elements.
"""
# Work on a copy of the feature set, because we mutate it.
fset = featureset.copy()
for fname in featureset:
for label in self._labels:
if (label, fname) in self._feature_probdist:
break
else:
# Discard feature name we haven't been trained on from the
# input set.
del fset[fname]
# Now we're working with a feature set that only includes known
# features.
# Instead of working with the product of the separate probabilities,
# we use the sum of the logarithms to prevent underflows and make the
# result more stable.
#: The probability of each label, given the features. Starting with
#: the probability of the label itself.
logprob = {}
for label in self._labels:
logprob[label] = self._label_probdist.logprob(label)
# Add the logarithmic probability of the features given the labels.
for label in self._labels:
for (fname, fval) in fset.items():
feature_probs = self._feature_probdist.get((label, fname))
if feature_probs is not None:
logprob[label] += feature_probs.logprob(fval)
else:
# This should not occur if the classifier was created with
# the train() method.
logprob[label] += sum_logs([]) # = -INF.
return DictionaryProbDist(logprob, normalize=True, log=True)
def test_sum_logs_ninf(self):
from twentiment.thirdparty.probability import sum_logs
self.assertEqual(sum_logs([]), _NINF)
def test_sum_logs_ninf(self):
from twentiment.thirdparty.probability import sum_logs
self.assertEqual(sum_logs([]), _NINF)