def solveAssignment(training_file, test_file, k):
# read data from both files as it is
features, training_class, training_data = nb.readFile(training_file)
f2, ref_ids, test_data = nb.readFile(test_file)
# find max number of attributes in both the files
max_attribute, max_attribute_values = nb.findMaxNumAttributes(training_data, test_data)
# format training and test data which can be used by classifier
# training_class, training_data = nb.formatData(training_data, max_attribute)
# test_class, test_data = nb.formatData(test_data, max_attribute)
# make k classifiers from training_data and class labels using ensemble method adaboost
kClassifiers, kClassifiers_errors = formEnsembleClassifiers(training_class, training_data, max_attribute_values, k)
# print kClassifiers_errors
# predict using all the classifier built using adaboost on test data
boosted_predicted_class = ensembleClassify(training_data, training_class, kClassifiers, kClassifiers_errors)
boosted_predicted_test_class = ensembleClassify(test_data, [], kClassifiers, kClassifiers_errors)
output = []
for i in range(0, len(boosted_predicted_test_class)):
output.append([ref_ids[i], boosted_predicted_test_class[i]])
with open("output.csv", "wb") as f:
writer = csv.writer(f)
writer.writerows(output)