def main():
trainSetFilename, testSetFilename, m = getArgs()
trainData = arffParser.parse(trainSetFilename)
testData = arffParser.parse(testSetFilename)
data = trainData['data']
attr = trainData['attributes']
targetIndex = len(trainData['attributes']) - 1
tree = DecisionTree(data, attr, targetIndex, m)
if tree.root == None:
return
tree.printTree()
print('<Predictions for the Test Set Instances>')
predictedData = []
for row in testData['data']:
predictedClass = tree.classify(row, testData['attributes'])
predictedRow = row[-1:] + [predictedClass]
predictedData.append(predictedRow)
numCorrect = 0
for i, row in zip(list(range(1, len(predictedData) + 1)), predictedData):
print('{0}: Actual: {1} Predicted: {2}'.format(i, row[0], row[1]))
if row[0] == row[1]:
numCorrect += 1
print('Number of correctly classified: ' + str(numCorrect),
'Total number of test instances: ' + str(len(predictedData)))
from fileIO import FileIO
from preprocess import Preprocessing
from decisionTree import DecisionTree
if __name__ == '__main__':
filename = 'house-votes-84.data.txt'
fileio = FileIO()
data = fileio.read_csv(filename)
preprocessing = Preprocessing()
preprocessing.assume_missing_values(data)
for percent in range(3, 8):
training_data, testing_data = preprocessing.split_into_training_and_testing(data, percent/float(10))
attributes_number = len(training_data[0]) - 1
decision_tree = DecisionTree()
root_node = decision_tree.build(training_data)
# decision_tree.print()
# print("Classification: ")
accuracy = 0
for row in testing_data:
classified = decision_tree.classify(row, decision_tree.root)
classified.calc_percentages(len(testing_data))
if classified.republicans_percent > 50.0 and row[0] == 'republican' or (
classified.democrats_percent > 50.0 and row[0] == 'democrat'):
accuracy += 1
accuracy = accuracy / float(len(testing_data))
print("Accuracy using training data", percent/float(10)*100, "% is: ", accuracy)
train_input = '../handout/education_train.tsv'
test_input = '../handout/education_test.tsv'
train_output = '../result/education_train.labels'
test_output = '../result/education_test.labels'
ld = LoadData()
dataset = ld.load_data(train_input)
dt = DecisionTree(ld)
tr_err = []
te_err = []
x_arr = []
print(ld.head)
for i in range(len(ld.head)):
root = dt.construct(dataset, i)
# dt.traverse(root)
dt.classify(ld.load_data(train_input), root, train_output)
dt.classify(ld.load_data(test_input), root, test_output)
with open(train_output, 'r') as f:
predcol = f.read().splitlines()
realcol = np.loadtxt(train_input,
dtype=str,
delimiter='\t',
skiprows=1)[:, -1]
eva_train = Evaluate(realcol, predcol)
train_errate = eva_train.error_rate()
with open(test_output, 'r') as f:
predcol = f.read().splitlines()
realcol = np.loadtxt(test_input, dtype=str, delimiter='\t',
skiprows=1)[:, -1]
eva_test = Evaluate(realcol, predcol)
test_errate = eva_test.error_rate()