class LogReg(object):
'''
logistic regression
'''
def __init__(self, texts, classes, nlpdict=None, scale=1, C=1.0):
self.scale = scale
self.l = LogisticRegression(penalty='l2', dual=True, C=C, \
class_weight='auto')
if nlpdict:
self.dictionary = nlpdict
else:
self.dictionary = NLPDict(texts=texts)
vectors = self.dictionary.feature_vectors(texts)
self.l.fit(vectors, classes)
def classify(self, texts):
'''
Classify a list of texts
'''
vectors = self.dictionary.feature_vectors(texts)
pred_prob = self.l.predict_proba(vectors)
predictions = []
for pair in pred_prob:
predictions.append(pair[1] - pair[0])
predictions = np.array(predictions)
predictions = (predictions + 1) / 2
predictions *= self.scale
predictions[predictions > 1] = 1
predictions[predictions < 0] = 0
return predictions
class LogReg(object):
'''
logistic regression
'''
def __init__(self, texts, classes, nlpdict=None, scale=1, C=1.0):
self.scale = scale
self.l = LogisticRegression(penalty='l2', dual=True, C=C, \
class_weight='auto')
if nlpdict:
self.dictionary = nlpdict
else:
self.dictionary = NLPDict(texts=texts)
vectors = self.dictionary.feature_vectors(texts)
self.l.fit(vectors, classes)
def classify(self, texts):
'''
Classify a list of texts
'''
vectors = self.dictionary.feature_vectors(texts)
pred_prob = self.l.predict_proba(vectors)
predictions = []
for pair in pred_prob:
predictions.append(pair[1] - pair[0])
predictions = np.array(predictions)
predictions = (predictions + 1) / 2
predictions *= self.scale
predictions[predictions > 1] = 1
predictions[predictions < 0] = 0
return predictions
class RFC(object):
def __init__(self, texts, classes):
self.dictionary = NLPDict(texts=texts)
vectors = self.dictionary.feature_vectors(texts)
self.nb = MultinomialNB()
self.nb.fit(vectors, classes)
def classify(self, texts):
vectors = self.dictionary.feature_vectors(texts)
pred_prob = self.nb.predict_proba(vectors)
predictions = []
for pair in pred_prob:
predictions.append(pair[1] - pair[0])
predictions = np.array(predictions)
predictions = (predictions + 1) / 2
#predictions *= 0.75
predictions[predictions > 1] = 1
predictions[predictions < 0] = 0
return predictions
class RFC(object):
def __init__(self, texts, classes):
self.dictionary = NLPDict(texts=texts)
vectors = self.dictionary.feature_vectors(texts)
self.nb = MultinomialNB()
self.nb.fit(vectors, classes)
def classify(self, texts):
vectors = self.dictionary.feature_vectors(texts)
pred_prob = self.nb.predict_proba(vectors)
predictions = []
for pair in pred_prob:
predictions.append(pair[1] - pair[0])
predictions = np.array(predictions)
predictions = (predictions + 1) / 2
#predictions *= 0.75
predictions[predictions > 1] = 1
predictions[predictions < 0] = 0
return predictions
class SGDC(object):
def __init__(self, texts, classes, nlpdict):
# TODO: add list of smileys to texts/classes
self.s = SGDClassifier(loss="hinge", penalty="l1", shuffle=True, class_weight="auto")
if nlpdict:
self.dictionary = nlpdict
else:
self.dictionary = NLPDict(texts=texts)
self._train(texts, classes)
def _train(self, texts, classes):
vectors = self.dictionary.feature_vectors(texts)
self.s.fit(vectors, classes)
def classify(self, texts):
vectors = self.dictionary.feature_vectors(texts)
predictions = self.s.decision_function(vectors)
predictions = predictions / 20 + 0.5
predictions[predictions > 1] = 1
predictions[predictions < 0] = 0
return predictions
class SVM(object):
def __init__(self, texts, classes, nlpdict=None):
# TODO: add list of smileys to texts/classes
self.svm = svm.LinearSVC(C=1000, class_weight='auto')
if nlpdict:
self.dictionary = nlpdict
else:
self.dictionary = NLPDict(texts=texts)
self._train(texts, classes)
def _train(self, texts, classes):
vectors = self.dictionary.feature_vectors(texts)
self.svm.fit(vectors, classes)
def classify(self, texts):
vectors = self.dictionary.feature_vectors(texts)
predictions = self.svm.decision_function(vectors)
predictions = np.transpose(predictions)
predictions = predictions / 2 + 0.5
predictions = map(lambda x: 1 if x>1 else (0 if x<0 else x),predictions)
return predictions
class SVM(object):
def __init__(self, texts, classes, nlpdict=None):
# TODO: add list of smileys to texts/classes
self.svm = svm.LinearSVC(C=1000, class_weight='auto')
if nlpdict:
self.dictionary = nlpdict
else:
self.dictionary = NLPDict(texts=texts)
self._train(texts, classes)
def _train(self, texts, classes):
vectors = self.dictionary.feature_vectors(texts)
self.svm.fit(vectors, classes)
def classify(self, texts):
vectors = self.dictionary.feature_vectors(texts)
predictions = self.svm.decision_function(vectors)
predictions = np.transpose(predictions)[0]
predictions = predictions / 2 + 0.5
predictions[predictions > 1] = 1
predictions[predictions < 0] = 0
return predictions
class SVM(object):
def __init__(self, texts, classes, nlpdict=None):
# TODO: add list of smileys to texts/classes
self.svm = svm.LinearSVC(C=1000, class_weight="auto")
if nlpdict:
self.dictionary = nlpdict
else:
self.dictionary = NLPDict(texts=texts)
self._train(texts, classes)
def _train(self, texts, classes):
vectors = self.dictionary.feature_vectors(texts)
self.svm.fit(vectors, classes)
def classify(self, texts):
vectors = self.dictionary.feature_vectors(texts)
predictions = self.svm.decision_function(vectors)
predictions = np.transpose(predictions)[0]
predictions = predictions / 2 + 0.5
predictions[predictions > 1] = 1
predictions[predictions < 0] = 0
return predictions
class SGDC(object):
def __init__(self, texts, classes, nlpdict):
# TODO: add list of smileys to texts/classes
self.s = SGDClassifier(loss='hinge', penalty='l1', shuffle=True, \
class_weight='auto')
if nlpdict:
self.dictionary = nlpdict
else:
self.dictionary = NLPDict(texts=texts)
self._train(texts, classes)
def _train(self, texts, classes):
vectors = self.dictionary.feature_vectors(texts)
self.s.fit(vectors, classes)
def classify(self, texts):
vectors = self.dictionary.feature_vectors(texts)
predictions = self.s.decision_function(vectors)
predictions = predictions / 20 + 0.5
predictions[predictions > 1] = 1
predictions[predictions < 0] = 0
return predictions