def test_model(self, test_data, empty_solution, evaluate = False):
model_weka = None
if os.path.isfile(self.prediction_file):
print 'Model ' + self.name + ' already tested.'
elif not os.path.isfile(self.model_file):
print 'Impossible testing this model. It should be trained first.'
return
else:
print 'Starting to test_model model ' + self.name + '.'
model_weka = Classifier(jobject = serialization.read(self.model_file))
evaluation = Evaluation(data = test_data)
evaluation.test_model(classifier = model_weka, data = test_data)
predictions = evaluation.predictions()
rows = read_sheet(file_name = empty_solution)
solutions = []
for row in rows:
solution = [row['userid'], row['tweetid'], predictions.pop(0).predicted()]
solutions.append(solution)
write_the_solution_file(solutions, self.prediction_file)
print 'Model ' + self.name + ' tested.'
if evaluate == True:
if os.path.isfile(self.evaluation_file):
print 'Model ' + self.name + ' already evaluated.'
return
elif model_weka == None:
model_weka = Classifier(jobject = serialization.read(self.model_file))
evaluation = Evaluation(data = test_data)
evaluation.test_model(classifier = model_weka, data = test_data)
save_file(file_name = self.evaluation_file, content = evaluation.to_summary())
print 'Model ' + self.name + ' evaluated.'
def train_model(self, training_data):
model_weka = None
if os.path.isfile(self.model_file):
print 'Model ' + self.name + ' already trained.'
else:
print 'Starting to train_model model ' + self.name + '.'
model_weka = Classifier(classname = self.classname, options = self.options)
model_weka.build_classifier(data = training_data)
serialization.write(filename = self.model_file, jobject = model_weka)
print 'Model ' + self.name + ' trained and saved.'
if os.path.isfile(self.parameter_file):
print 'Parameters of the model ' + self.name + ' already saved.'
else:
if model_weka == None:
model_weka = Classifier(jobject = serialization.read(self.model_file))
save_file(file_name = self.parameter_file, content = str(model_weka))
print 'Parameters of the model ' + self.name + ' saved.'
