def run(config, codeRoot=''):
classifier = DecisionTreeClassifier([0, 1])
print " ========= %s ========= " % config['header']
pointsPerCase = int(config['pointsPerCase'])
args = {}
args['metric'] = metrics.error
args['maxdepth'] = 1
size = len(config['dataset'])
points = 0
first_error = ''
for i in xrange(size):
data = config['dataset'][i]
print "\tDataset: %s" % data
# Load data
trainingData = samples.loadDataFile(
os.path.join(codeRoot, "data/%s/training_data.csv" % data))
trainingLabels = samples.loadLabelsFile(
os.path.join(codeRoot, "data/%s/training_labels.csv" % data))
# Conduct training and testing
classifier.train(trainingData, trainingLabels, args)
tree = classifier.tree
best_split = int(config['best_split'][i])
test_passed = True
if tree.column != best_split:
error = 'WRONG SPLIT: Correct: %s , Returned: %s' % (best_split,
tree.column)
if not first_error: first_error = error
print '\t\t%s' % error
test_passed = False
if not has_one_level(tree):
error = 'The tree does not have one level'
if not first_error: first_error = error
print '\t\t%s' % error
test_passed = False
if test_passed:
points += pointsPerCase
print '\t\tOK'
needed_all_tests_passed = int(config['totalQuestion']) > 0
if needed_all_tests_passed and first_error:
points = 0
test_error = 'Your code does not pass all tests'
else:
test_error = ''
return (points, test_error)
def run(config, codeRoot=''):
classifier = DecisionTreeClassifier([0, 1])
print " ========= %s ========= " % config['header']
pointsPerCase = int(config['pointsPerCase'])
args = {}
args['metric'] = get_metric(config['metric'])
size = len(config['dataset'])
points = 0
first_error = ''
for i in xrange(size):
data = config['dataset'][i]
print "\tDataset: %s" % data
# Load data
trainingData = samples.loadDataFile(
os.path.join(codeRoot, "data/%s/training_data.csv" % data))
trainingLabels = samples.loadLabelsFile(
os.path.join(codeRoot, "data/%s/training_labels.csv" % data))
# Load test
testData = samples.loadDataFile(
os.path.join(codeRoot, "data/%s/test_data.csv" % data))
testLabels = samples.loadLabelsFile(
os.path.join(codeRoot, "data/%s/test_labels.csv" % data))
# Conduct training and testing
args['maxdepth'] = int(config['maxdepth'][i])
classifier.train(trainingData, trainingLabels, args)
guesses = classifier.classify(testData)
min_accuracy_required = float(config['accuracy'][i])
if is_good_classifier(guesses, testLabels, min_accuracy_required):
print '\t\tOK'
points += pointsPerCase
else:
points += (pointsPerCase / 2.)
print '\t\tMost frequent classifier is better'
needed_all_tests_passed = int(config['totalQuestion']) > 0
if needed_all_tests_passed and first_error:
points = 0
test_error = 'Your code does not pass all tests'
else:
test_error = ''
return (points, test_error)
def run(config, codeRoot=''):
classifier = DecisionTreeClassifier([0, 1])
print " ========= %s ========= " % config['header']
args = {}
args['metric'] = metrics.error
args['maxdepth'] = 0
size = len(config['dataset'])
points = 0
first_error = ''
for i in xrange(size):
data = config['dataset'][i]
print "\tDataset: %s" % data
# Load data
trainingData = samples.loadDataFile(
os.path.join(codeRoot, "data/%s/training_data.csv" % data))
trainingLabels = samples.loadLabelsFile(
os.path.join(codeRoot, "data/%s/training_labels.csv" % data))
# Conduct training and testing
classifier.train(trainingData, trainingLabels, args)
tree = classifier.tree
if not tree.leftchild and not tree.rightchild:
label = int(config['label'][i])
if tree.label != label:
error = 'The tree is not classifying by the most frequent label: %s' % label
if not first_error: first_error = error
print '\t\t%s' % error
else:
points += int(config['pointsPerCase'])
print '\t\tOK'
else:
error = 'The tree has one or more levels'
if not first_error: first_error = error
print '\t\t%s' % error
needed_all_tests_passed = int(config['totalQuestion']) > 0
if needed_all_tests_passed and first_error:
points = 0
test_error = 'Your code does not pass all tests'
else:
test_error = ''
return (points, test_error)
def run(config, codeRoot=''):
classifier = DecisionTreeClassifier([0, 1])
print " ========= %s ========= " % config['header']
pointsPerCase = int(config['pointsPerCase'])
args = {}
args['metric'] = get_metric(config['metric'])
args['maxdepth'] = int(config['maxdepth'])
size = len(config['dataset'])
points = 0
first_error = ''
for i in xrange(size):
data = config['dataset'][i]
print "\tDataset: %s" % data
# Load data
trainingData = samples.loadDataFile(
os.path.join(codeRoot, "data/%s/training_data.csv" % data))
trainingLabels = samples.loadLabelsFile(
os.path.join(codeRoot, "data/%s/training_labels.csv" % data))
# Conduct training and testing
classifier.train(trainingData, trainingLabels, args)
tree = classifier.tree
status, error = compare(tree, get_tree(data, codeRoot))
if status != 0:
if not first_error: first_error = error
print '\t\t%s' % error
else:
points += pointsPerCase
print '\t\tOK'
needed_all_tests_passed = int(config['totalQuestion']) > 0
if needed_all_tests_passed and first_error:
points = 0
test_error = 'Your code does not pass all tests'
else:
test_error = ''
return (points, test_error)