class NaiveBayes(Classifier):
"""
Implements a classifier that uses the Bayes' theorem.
"""
def learn(self):
# Frequency count of target classes
self.C = OnlineLogProbability()
# Frequency count of P(Fi|C):
self.Fi = defaultdict(lambda: # For each class,
defaultdict(lambda: # For each attribute,
OnlineLogProbability())) # For each value, count it
for example in self.dataset:
class_ = self.target(example)
self.C.add(class_)
for attribute in self.attributes:
value = attribute(example)
self.Fi[class_][attribute].add(value)
if not self.C:
raise ValueError("Dataset is empty")
# Cripple defaultdict to a regular dict, so now it can rasie KeyError
self.Fi.default_factory = None
for d in self.Fi.itervalues():
d.default_factory = None
def classify(self, example):
values = [(attribute, attribute(example))
for attribute in self.attributes]
hypotheses = []
for class_ in self.C:
try:
ps = [self.Fi[class_][attr][val] for attr, val in values]
except KeyError:
continue # A value not seen in training, so Prob(class) == 0
ps.append(self.C[class_])
hypotheses.append((sum(ps), class_))
if hypotheses:
logprob, best = max(hypotheses)
Z = numpy.logaddexp.reduce([p for p, class_ in hypotheses])
logprob = logprob - Z
else: # Something not at all seen in training, return best a priori
logprob, best = max((p, class_) for class_, p
in self.C.iteritems())
p = numpy.exp(logprob)
assert 0.0 <= p and p <= 1.0
return best, p
class NaiveBayes(Classifier):
"""
Implements a classifier that uses the Bayes' theorem.
"""
def learn(self):
# Frequency count of target classes
self.C = OnlineLogProbability()
# Frequency count of P(Fi|C):
self.Fi = defaultdict(
lambda: # For each class,
defaultdict(lambda: # For each attribute,
OnlineLogProbability())) # For each value, count it
for example in self.dataset:
class_ = self.target(example)
self.C.add(class_)
for attribute in self.attributes:
value = attribute(example)
self.Fi[class_][attribute].add(value)
if not self.C:
raise ValueError("Dataset is empty")
# Cripple defaultdict to a regular dict, so now it can rasie KeyError
self.Fi.default_factory = None
for d in self.Fi.itervalues():
d.default_factory = None
def classify(self, example):
values = [(attribute, attribute(example))
for attribute in self.attributes]
hypotheses = []
for class_ in self.C:
try:
ps = [self.Fi[class_][attr][val] for attr, val in values]
except KeyError:
continue # A value not seen in training, so Prob(class) == 0
ps.append(self.C[class_])
hypotheses.append((sum(ps), class_))
if hypotheses:
logprob, best = max(hypotheses)
Z = numpy.logaddexp.reduce([p for p, class_ in hypotheses])
logprob = logprob - Z
else: # Something not at all seen in training, return best a priori
logprob, best = max(
(p, class_) for class_, p in self.C.iteritems())
p = numpy.exp(logprob)
assert 0.0 <= p and p <= 1.0
return best, p
def learn(self):
# Frequency count of target classes
self.C = OnlineLogProbability()
# Frequency count of P(Fi|C):
self.Fi = defaultdict(
lambda: # For each class,
defaultdict(lambda: # For each attribute,
OnlineLogProbability())) # For each value, count it
for example in self.dataset:
class_ = self.target(example)
self.C.add(class_)
for attribute in self.attributes:
value = attribute(example)
self.Fi[class_][attribute].add(value)
if not self.C:
raise ValueError("Dataset is empty")
# Cripple defaultdict to a regular dict, so now it can rasie KeyError
self.Fi.default_factory = None
for d in self.Fi.itervalues():
d.default_factory = None
def learn(self):
# Frequency count of target classes
self.C = OnlineLogProbability()
# Frequency count of P(Fi|C):
self.Fi = defaultdict(lambda: # For each class,
defaultdict(lambda: # For each attribute,
OnlineLogProbability())) # For each value, count it
for example in self.dataset:
class_ = self.target(example)
self.C.add(class_)
for attribute in self.attributes:
value = attribute(example)
self.Fi[class_][attribute].add(value)
if not self.C:
raise ValueError("Dataset is empty")
# Cripple defaultdict to a regular dict, so now it can rasie KeyError
self.Fi.default_factory = None
for d in self.Fi.itervalues():
d.default_factory = None
