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 order_solution():
solutions = read_sheet(DATASET_PATH + 'neural_solution.dat')
# Sort the solutions on user id (desc), engagement (desc) and tweet id (desc)
solutions = sorted(solutions, key=lambda data: (-int(data['userid']), -float(data['engagement']), -int(data['tweetid'])))
solution_final = []
for solution in solutions:
solution_final.append([solution['userid'], solution['tweetid'], solution['engagement']])
# Write the _solution file
write_the_solution_file(solution_final, DATASET_PATH + 'neural_solution2.dat')
def random_solution():
# Read the training file
# Read the _empty file (the task)
todos = read_todo_from_empty_file(DATASET_PATH + 'test_empty.dat')
# For all (user,tweet) pairs, generate their engagement
solutions = list()
#random.seed(1)
for (user,tweet) in todos:
# Random guess the engagement between 0-50
engagement = random.randint(0,50)
solutions.append((user,tweet,engagement))
# Sort the solutions on user id (desc), engagement (desc) and tweet id (desc)
solutions = sorted(solutions, key=lambda data: (-int(data[0]), -int(data[2]), -int(data[1])))
# Write the _solution file
write_the_solution_file(solutions, DATASET_PATH + 'random_solution.dat')
print 'done.'
