def main():
while True:
data_set_name = input("Please provide the name of the data set you want to work with: ")
# Load, Randomize, Normalize, Discretize Dataset
data_set = Dataset()
data_set.read_file_into_dataset("C:\\Users\\Grant\\Documents\\School\\Winter 2016\\CS 450\\Prove03\\" + data_set_name)
data_set.randomize()
data_set.data = normalize(data_set.data)
data_set.discretize()
data_set.set_missing_data()
# Split Dataset
split_percentage = 0.7
data_sets = split_dataset(data_set, split_percentage)
training_set = data_sets['train']
testing_set = data_sets['test']
# Create Custom Classifier, Train Dataset, Predict Target From Testing Set
id3Classifier = ID3()
id3Classifier.train(training_set)
predictions = id3Classifier.predict(testing_set)
id3Classifier.display_tree(0, id3Classifier.tree)
# Check Results
my_accuracy = get_accuracy(predictions, testing_set.target)
print("Accuracy: " + str(my_accuracy) + "%")
# Compare To Existing Implementations
dtc = tree.DecisionTreeClassifier()
dtc.fit(training_set.data, training_set.target)
predictions = dtc.predict(testing_set.data)
dtc_accuracy = get_accuracy(predictions, testing_set.target)
print("DTC Accuracy: " + str(dtc_accuracy) + "%")
# Do another or not
toContinue = False
while True:
another = input("Do you want to examine another dataset? (y / n) ")
if another != 'y' and another != 'n':
print("Please provide you answer in a 'y' or 'n' format.")
elif another == 'y':
toContinue = True
break
else:
toContinue = False
break
if not toContinue:
break
