def test_random_forest_5_trees(self):
learner = dt.RandomForest(num_trees=5,
depth_limit=5,
example_subsample_rate=0.5,
attr_subsample_rate=0.5)
learner.fit(self.train_features, self.train_classes)
output = learner.classify(self.train_features)
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_precision_calculation(self):
"""Test precision calculation.
Asserts:
Precision matches for all true labels.
"""
answer = [0, 0, 0, 0, 0]
true_label = [1, 0, 0, 0, 0]
for index in range(0, len(answer)):
answer[index] = 1
precision = 1 / (1 + index)
rslt = dt.precision(answer, true_label)
assert rslt == precision
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))