def test(self):
if not os.path.exists(FileManager.getTrainedModelFileUrl(self.type)):
raise Exception('You can\'t test a model without training it')
# label encoder
Y_Encoder = preprocessing.LabelEncoder()
Y_Encoder.fit(ConfigurationManager.getLanguages())
# preparing features
X, languages = self.__prepareFeatures('testing', True)
# import trained model
self.importScikitTrainedModel()
# make predictions
Y_real = Y_Encoder.transform(languages)
Y_predicted = self.model.predict(X)
# metrics
accuracy = accuracy_score(Y_real, Y_predicted)
report = classification_report(Y_real,
Y_predicted,
target_names=Y_Encoder.classes_)
print(' > [BAYES] classification report exported!')
print(' > [BAYES] total accuracy = ' +
str(float("{:.2f}".format(accuracy)) * 100) + '%')
# export the classification report
self.exportClassificationReport(str(report))
return self
def train(self):
# check if a trained model already exists
if os.path.exists(FileManager.getTrainedModelFileUrl(self.type)):
return self
# configs
batch_size: int = self.config['batch_size']
epochs: int = self.config['epochs']
# preparing features
X, Y = self.__prepareFeatures('training', False)
# Y dummies encoding
Y = pd.get_dummies(Y)
# prepare model
self.__prepareModel(X, Y)
# set early stopping monitor so the model stops training when it won't improve anymore
early_stopping_monitor = EarlyStopping(monitor='loss', patience=3)
# training
history = self.model.fit(X,
Y,
batch_size,
epochs,
verbose=1,
callbacks=[early_stopping_monitor])
print('\n' + str(self.model.summary()))
# export the trained model
self.exportKerasTrainedModel()
return self
def train(self):
if os.path.exists(FileManager.getTrainedModelFileUrl(self.type)):
return self
# preparing features
X, languages = self.__prepareFeatures('training', False)
# label encoder
Y_Encoder = preprocessing.LabelEncoder()
Y_Encoder.fit(ConfigurationManager.getLanguages())
# (X, Y) creation
Y = Y_Encoder.transform(languages)
# prepare model
self.__prepareModel()
# training
self.model.fit(X, Y)
# export the trained model
self.exportScikitTrainedModel()
return self
def test(self):
if not os.path.exists(FileManager.getTrainedModelFileUrl(self.type)):
raise Exception('You can\'t test a model without training it.')
batch_size: int = self.config['batch_size']
# preparing features
X, Y = self.__prepareFeatures('testing', True)
# import trained model
self.importKerasTrainedModel()
# make predictions
Y_real = pd.get_dummies(Y)
Y_predicted = self.model.predict(X, batch_size=batch_size)
target_names = Y_real.columns.tolist()
Y_real_binary_list = np.argmax(Y_real.values.tolist(), axis=1)
Y_predicted_binary_list = np.argmax(Y_predicted, axis=1)
# metrics
loss, accuracy = self.model.evaluate(X,
Y_real,
verbose=0,
batch_size=batch_size)
report = classification_report(Y_real_binary_list,
Y_predicted_binary_list,
target_names=target_names)
print(' > [CNN] classification report exported!')
print(' > [CNN] total accuracy = ' +
str(float("{:.2f}".format(accuracy)) * 100) + '%')
# export the classification report
self.exportClassificationReport(str(report))
return self
def exportScikitTrainedModel(self):
joblib.dump(self.model, FileManager.getTrainedModelFileUrl(self.type))
return self
def exportKerasTrainedModel(self):
self.model.save(FileManager.getTrainedModelFileUrl(self.type))
return self
def importScikitTrainedModel(self):
self.model = joblib.load(FileManager.getTrainedModelFileUrl(self.type))
return self
def importKerasTrainedModel(self):
self.model = load_model(FileManager.getTrainedModelFileUrl(self.type))
return self
