def fit(self):
print "Fitting %s:" % self.__class__.__name__
print "positive_unary_rules", self.positive_unary_rules
print "negative_unary_rules", self.negative_unary_rules
print "# of positive examples:", len(self.positive_unary_rules)
print "# of negative examples:", len(self.negative_unary_rules)
self.feature_function = UnaryFeatureFunction(
self.positive_unary_rules + self.negative_unary_rules)
X = []
y = []
for pur in self.positive_unary_rules:
X.append(self.feature_function.map(pur))
y.append(1)
for nur in self.negative_unary_rules:
X.append(self.feature_function.map(nur))
y.append(0)
print "length of feature vector:", np.shape(X)[1]
cw = {
0: len(self.positive_unary_rules),
1: len(self.negative_unary_rules)
}
# self.classifier = RandomForestClassifier(class_weight='auto', n_estimators=30) # RandomForestClassifier()
# self.classifier = SVC(probability=True, class_weight='auto')
self.classifier = LogisticRegression(class_weight='balanced')
self.classifier.fit(X, y)
class RFUnaryModel(UnaryModel):
def __init__(self):
self.positive_unary_rules = []
self.negative_unary_rules = []
self.feature_function = None
self.classifier = None
self.scores = {}
@staticmethod
def val_func(p, c):
if p.signature.id in ('Is', 'CC'):
return False
return UnaryRule.val_func(p, c)
def update(self, tag_rules, positive_unary_rules):
all_unary_rules = self.generate_unary_rules(tag_rules)
negative_unary_rules = all_unary_rules - positive_unary_rules
self.positive_unary_rules.extend(positive_unary_rules)
self.negative_unary_rules.extend(negative_unary_rules)
def fit(self):
print "Fitting %s:" % self.__class__.__name__
print "positive_unary_rules", self.positive_unary_rules
print "negative_unary_rules", self.negative_unary_rules
print "# of positive examples:", len(self.positive_unary_rules)
print "# of negative examples:", len(self.negative_unary_rules)
self.feature_function = UnaryFeatureFunction(
self.positive_unary_rules + self.negative_unary_rules)
X = []
y = []
for pur in self.positive_unary_rules:
X.append(self.feature_function.map(pur))
y.append(1)
for nur in self.negative_unary_rules:
X.append(self.feature_function.map(nur))
y.append(0)
print "length of feature vector:", np.shape(X)[1]
cw = {
0: len(self.positive_unary_rules),
1: len(self.negative_unary_rules)
}
# self.classifier = RandomForestClassifier(class_weight='auto', n_estimators=30) # RandomForestClassifier()
# self.classifier = SVC(probability=True, class_weight='auto')
self.classifier = LogisticRegression(class_weight='balanced')
self.classifier.fit(X, y)
def get_score(self, ur):
if ur in self.scores:
return self.scores[ur]
x = self.feature_function.map(ur)
probas = self.classifier.predict_proba([x])
score = probas[0][1]
self.scores[ur] = score
return score
class RFUnaryModel(UnaryModel):
def __init__(self):
self.positive_unary_rules = []
self.negative_unary_rules = []
self.feature_function = None
self.classifier = None
self.scores = {}
@staticmethod
def val_func(p, c):
if p.signature.id in ('Is', 'CC'):
return False
return UnaryRule.val_func(p, c)
def update(self, tag_rules, positive_unary_rules):
all_unary_rules = self.generate_unary_rules(tag_rules)
negative_unary_rules = all_unary_rules - positive_unary_rules
self.positive_unary_rules.extend(positive_unary_rules)
self.negative_unary_rules.extend(negative_unary_rules)
def fit(self):
print "Fitting %s:" % self.__class__.__name__
print "# of positive examples:", len(self.positive_unary_rules)
print "# of negative examples:", len(self.negative_unary_rules)
self.feature_function = UnaryFeatureFunction(self.positive_unary_rules + self.negative_unary_rules)
X = []
y = []
for pur in self.positive_unary_rules:
X.append(self.feature_function.map(pur))
y.append(1)
for nur in self.negative_unary_rules:
X.append(self.feature_function.map(nur))
y.append(0)
print "length of feature vector:", np.shape(X)[1]
cw = {0: len(self.positive_unary_rules), 1: len(self.negative_unary_rules)}
# self.classifier = RandomForestClassifier(class_weight='auto', n_estimators=30) # RandomForestClassifier()
# self.classifier = SVC(probability=True, class_weight='auto')
self.classifier = LogisticRegression(class_weight='auto')
self.classifier.fit(X, y)
def get_score(self, ur):
if ur in self.scores:
return self.scores[ur]
x = self.feature_function.map(ur)
probas = self.classifier.predict_proba([x])
score = probas[0][1]
self.scores[ur] = score
return score
def fit(self):
print "Fitting %s:" % self.__class__.__name__
print "# of positive examples:", len(self.positive_unary_rules)
print "# of negative examples:", len(self.negative_unary_rules)
self.feature_function = UnaryFeatureFunction(self.positive_unary_rules + self.negative_unary_rules)
X = []
y = []
for pur in self.positive_unary_rules:
X.append(self.feature_function.map(pur))
y.append(1)
for nur in self.negative_unary_rules:
X.append(self.feature_function.map(nur))
y.append(0)
print "length of feature vector:", np.shape(X)[1]
cw = {0: len(self.positive_unary_rules), 1: len(self.negative_unary_rules)}
# self.classifier = RandomForestClassifier(class_weight='auto', n_estimators=30) # RandomForestClassifier()
# self.classifier = SVC(probability=True, class_weight='auto')
self.classifier = LogisticRegression(class_weight='auto')
self.classifier.fit(X, y)
