def train(self, classdict, nb_epochs=500, l2reg=0.01, bias_l2reg=0.01, optimizer='adam'):
""" Train the classifier.
Given the training data, train the classifier.
:param classdict: training data
:param nb_epochs: number of epochs (Defauly: 500)
:param l2reg: L2 regularization coefficient (Default: 0.01)
:param bias_l2reg: L2 regularization coefficient for bias (Default: 0.01)
:param optimizer: optimizer for gradient descent. Options: sgd, rmsprop, adagrad, adadelta, adam, adamax, nadam. (Default: adam)
:return: None
:type classdict: dict
:type nb_epochs: int
:type l2reg: float
:type bias_l2reg: float
:type optimizer: str
"""
self.dictionary, self.corpus, self.classlabels = gc.generate_gensim_corpora(classdict,
preprocess_and_tokenize=lambda s: tokenize(self.preprocessor(s)))
self.index_classlabels()
X, y = self.convert_classdict_to_XY(classdict)
kmodel = logistic_framework(len(self.dictionary),
len(self.classlabels),
l2reg=l2reg,
bias_l2reg=bias_l2reg,
optimizer=optimizer)
kmodel.fit(X.toarray(), y.toarray(), epochs=nb_epochs)
self.model = kmodel
self.trained = True
def generate_corpus(self, classdict):
""" Calculate the gensim dictionary and corpus, and extract the class labels
from the training data. Called by :func:`~train`.
:param classdict: training data
:return: None
:type classdict: dict
"""
self.dictionary, self.corpus, self.classlabels = gc.generate_gensim_corpora(classdict,
preprocess_and_tokenize=lambda sent: tokenize(self.preprocessor(sent)))
