def handle_data(train_set, test_set):
'''
get the predictions for three algorithms - decision tree, knn and naive bayes
:param train_set: x
:param test_set: y
predict the y_hat, calc the accuracy and write to file the accuracies + the tree
'''
# split the files and get the data and labels
train_data, train_data_labels, attributes, label_key = split_train_data(
train_set)
test_data, test_data_labels = split_test_data(test_set)
# get the algorithms
decision_tree, knn, naive_bayes = DecisionTree.Model(), Knn.Model(
), NaiveBayes.Model()
algorithms = [decision_tree, knn, naive_bayes]
accuracies = []
# for every algorithm - get the prediction on the test set, calc the accuracy and add to list
for algorithm in algorithms:
algorithm.set_data(train_data, train_data_labels,
[label_key, attributes])
prediction = algorithm.predict(test_data)
accuracy = get_acc(prediction, test_data_labels)
accuracies.append(
"{0:.2f}".format(accuracy)) # get the 2 digits after point
# get the output tree and write to the file
tree = decision_tree.get_tree()
tree.write_tree(OUTPUT_FILE)
# write the accuracies to the same file
write_accuracies(OUTPUT_FILE, accuracies)
print(I2F)
print(L2I)
print(I2L)
print(V2I)
print(I2V)
'''
# loading the datasetes
TRAIN = get_data("train.txt")
TEST = get_data("test.txt")
# creating the different models
dt = DecisionTree.Model(
TRAIN, values={i: value.keys()
for i, value in I2V.items()})
knn = KNN.Model(TRAIN, k=5)
nb = NaiveBayes.Model(TRAIN, I2L.keys())
# predicting on the TEST set
r = open("output.txt", 'w')
predict(TEST, [dt, knn, nb])
r.close()
# printing the tree that DecisionTree created
t = open("output_tree.txt", 'w')
print_tree(dt.root)
t.close()
# deleting the last '\n' character
with open("output_tree.txt", 'rb+') as t:
t.seek(-1, os.SEEK_END)
t.truncate()
