def setUp(self):
"""Set up test data.
"""
self.restaurant = {
'restaurants': [0] * 6 + [1] * 6,
'split_patrons': [[0, 0], [1, 1, 1, 1], [1, 1, 0, 0, 0, 0]],
'split_food_type': [[0, 1], [0, 1], [0, 0, 1, 1], [0, 0, 1, 1]]
}
self.dataset = dt.load_csv('part23_data.csv')
self.train_features, self.train_classes = self.dataset
self.challenge_set = dt.load_csv('challenge_train.csv', 0)
self.challenge_set_features, self.challenge_set_classes = self.challenge_set
def test_random_forest_5_trees(self):
path = abspath("challenge_train.csv")
self.train_features, self.train_classes = dt.load_csv(path, 0)
#print classes
# learner = dt.ChallengeClassifier()
# learner.fit(features, classes)
# output = learner.classify(features)
# print output
# result = dt.confusion_matrix(output, classes)
# print "\n\nconfusion_matrix={}".format(result)
# print "accuracy={}".format(dt.accuracy(output, classes))
# print "precision={}".format(dt.precision(output, classes))
# print "recall={}".format(dt.recall(output, classes))
learner = dt.ChallengeClassifier()
learner.fit(self.train_features, self.train_classes)
output = learner.classify(self.train_features)
print output
result = dt.confusion_matrix(output, self.train_classes)
print "\n\nconfusion_matrix={}".format(result)
print "accuracy={}".format(dt.accuracy(output, self.train_classes))
print "precision={}".format(dt.precision(output, self.train_classes))
print "recall={}".format(dt.recall(output, self.train_classes))
def test_challenge_all_data(self):
"""Test challenge section.
Asserts:
classification on average is >= 80%
"""
dataset = dt.load_csv('challenge_train.csv', 0)
# Change as you see fit by adding parameters you have chosen or run
# it with defaults
tree = dt.ChallengeClassifier()
fold_count = 10
ten_folds = dt.generate_k_folds(dataset, fold_count)
avg_accuracy = 0.0
for fold in ten_folds:
training_set, test_set = fold
tree.fit(training_set[0], training_set[1])
output = tree.classify(test_set[0])
avg_accuracy += dt.accuracy(output, test_set[1])
avg_accuracy = avg_accuracy / fold_count
print '\n\nChallenger K-folds:', avg_accuracy
assert avg_accuracy >= .80
def setUp(self):
"""Set up test data.
"""
self.vector = dt.Vectorization()
self.data = dt.load_csv('vectorize.csv', 1)
