class TestDecisionTreeClassifier(unittest.TestCase):
def setUp(self):
self.classifier = DecisionTreeClassifier(train_set)
def test_classify(self):
res = self.classifier.classify("I feel happy this morning")
assert_equal(res, 'positive')
assert_equal(len(self.classifier.train_set), len(train_set))
def test_accuracy(self):
acc = self.classifier.accuracy(test_set)
assert_true(isinstance(acc, float))
def test_update(self):
original_length = len(self.classifier.train_set)
self.classifier.update([("lorem ipsum", "positive")])
new_length = len(self.classifier.train_set)
assert_equal(original_length + 1, new_length)
def test_custom_feature_extractor(self):
cl = DecisionTreeClassifier(train_set, custom_extractor)
cl.classify("Yay! I'm so happy it works.")
assert_equal(cl.train_features[0][1], 'positive')
def test_pseudocode(self):
code = self.classifier.pseudocode()
assert_true("if" in code)
def test_pretty_format(self):
pp = self.classifier.pprint(width=60)
pf = self.classifier.pretty_format(width=60)
assert_true(isinstance(pp, unicode))
assert_equal(pp, pf)
def test_repr(self):
assert_equal(
repr(self.classifier),
"<DecisionTreeClassifier trained on {0} instances>".format(
len(train_set)))
class TestDecisionTreeClassifier(unittest.TestCase):
def setUp(self):
self.classifier = DecisionTreeClassifier(train_set)
def test_classify(self):
res = self.classifier.classify("I feel happy this morning")
assert_equal(res, 'positive')
assert_equal(len(self.classifier.train_set), len(train_set))
def test_accuracy(self):
acc = self.classifier.accuracy(test_set)
assert_true(isinstance(acc, float))
def test_update(self):
original_length = len(self.classifier.train_set)
self.classifier.update([("lorem ipsum", "positive")])
new_length = len(self.classifier.train_set)
assert_equal(original_length + 1, new_length)
def test_custom_feature_extractor(self):
cl = DecisionTreeClassifier(train_set, custom_extractor)
cl.classify("Yay! I'm so happy it works.")
assert_equal(cl.train_features[0][1], 'positive')
def test_pseudocode(self):
code = self.classifier.pseudocode()
assert_true("if" in code)
def test_pretty_format(self):
pp = self.classifier.pprint(width=60)
pf = self.classifier.pretty_format(width=60)
assert_true(isinstance(pp, unicode))
assert_equal(pp, pf)
def test_repr(self):
assert_equal(repr(self.classifier),
"<DecisionTreeClassifier trained on {0} instances>".format(len(train_set)))
# Compute accuracy
print("Accuracy: {0}".format(cl.accuracy(test)))
# Show 5 most informative features
cl.show_informative_features()
#Classifying txt file with DecisionTree
train = [('Buy cheap drugs', 'spam'), ('Cheap viagra', 'spam'),
('Win 1000 dollar', 'spam'), ('Greatings, how are you?', 'ham'),
('What an awesome picture', 'ham'), ('Send me your adress', 'ham'),
('viagra', 'spam')]
tr = DecisionTreeClassifier(train)
file = open("test.txt")
t = file.read()
print(type(t))
blob = TextBlob(t, classifier=tr)
blob.tags
print(blob)
for sentence in blob.sentences:
print(sentence)
print(sentence.classify())
print(blob.classify())
print(tr.pseudocode())
print(tr.pretty_format())
print(tr.pprint())