def main():
# 1. Data analysis
# da.show_data(raw_train, 'raw train set:')
# da.show_data(raw_test, 'raw test set: ')
# da.analyze_training_data(raw_train)
# 2. Feature engineering
fe.raw_train = raw_train
fe.raw_test = raw_test
fe.train_border_index = train_border_index
fe.validation_border_index = validation_border_index
data = fe.engineer_data()
accuracy = knn_cross_validation(data)
print(accuracy)
def main():
# 1. Data analysis
# da.show_data(raw_train, 'raw train set:')
# da.show_data(raw_test, 'raw test set: ')
# da.analyze_training_data(raw_train)
# 2. Feature engineering
fe.raw_train = raw_train
fe.raw_test = raw_test
fe.train_border_index = train_border_index
fe.validation_border_index = validation_border_index
data = fe.engineer_data()
accuracy = random_forest_cross_validation(data, model_params=choose_best_params(data))
print(accuracy)
def main():
# 1. Data analysis
# da.show_data(raw_train, 'raw train set:')
# da.show_data(raw_test, 'raw test set: ')
# da.analyze_training_data(raw_train)
# 2. Feature engineering
fe.raw_train = raw_train
fe.raw_test = raw_test
fe.train_border_index = train_border_index
fe.validation_border_index = validation_border_index
data = fe.engineer_data()
# 3 Model development and prediction
nn_keras_cross_validation(data)
def main():
# 1. Data analysis
# da.show_data(raw_train, 'raw train set:')
# da.show_data(raw_test, 'raw test set: ')
# da.analyze_training_data(raw_train)
# 2. Feature engineering
fe.raw_train = raw_train
fe.raw_test = raw_test
fe.train_border_index = train_border_index
fe.validation_border_index = validation_border_index
data = fe.engineer_data()
# accuracy = naive_bayes_cross_validation(data)
# accuracy = naive_bayes_cross_validation(data, classificator=MultinomialNB())
accuracy = naive_bayes_data(data, classifier=BernoulliNB())
print(accuracy)