Python NaiveBayesClassifier.show_informative_features方法代码示例

# 需要导入模块: from text.classifiers import NaiveBayesClassifier [as 别名]
# 或者: from text.classifiers.NaiveBayesClassifier import show_informative_features [as 别名]
test = [
    ('The beer was good.', 'pos'),
    ('I do not enjoy my job', 'neg'),
    ("I ain't feeling dandy today.", 'neg'),
    ("I feel amazing!", 'pos'),
    ('Gary is a friend of mine.', 'pos'),
    ("I can't believe I'm doing this.", 'neg')
]
 
cl = NaiveBayesClassifier(train)
 
# Classify some text
print(cl.classify("Their burgers are amazing."))  # "pos"
print(cl.classify("I don't like their pizza."))   # "neg"
 
# Classify a TextBlob
blob = TextBlob("The beer was amazing. But the hangover was horrible. "
                "My boss was not pleased.", classifier=cl)
print(blob)
print(blob.classify())
 
for sentence in blob.sentences:
    print(sentence)
    print(sentence.classify())
 
# Compute accuracy
print("Accuracy: {0}".format(cl.accuracy(test)))
 
# Show 5 most informative features
cl.show_informative_features(5)

# 需要导入模块: from text.classifiers import NaiveBayesClassifier [as 别名]
# 或者: from text.classifiers.NaiveBayesClassifier import show_informative_features [as 别名]
class TestNaiveBayesClassifier(unittest.TestCase):

    def setUp(self):
        self.train_set =  [
              ('I love this car', 'positive'),
              ('This view is amazing', 'positive'),
              ('I feel great this morning', 'positive'),
              ('I am so excited about the concert', 'positive'),
              ('He is my best friend', 'positive'),
              ('I do not like this car', 'negative'),
              ('This view is horrible', 'negative'),
              ('I feel tired this morning', 'negative'),
              ('I am not looking forward to the concert', 'negative'),
              ('He is my enemy', 'negative')
        ]
        self.classifier = NaiveBayesClassifier(self.train_set)
        self.test_set = [('I feel happy this morning', 'positive'),
                        ('Larry is my friend.', 'positive'),
                        ('I do not like that man.', 'negative'),
                        ('My house is not great.', 'negative'),
                        ('Your song is annoying.', 'negative')]

    def test_basic_extractor(self):
        text = "I feel happy this morning."
        feats = basic_extractor(text, self.train_set)
        assert_true(feats["contains(feel)"])
        assert_true(feats['contains(morning)'])
        assert_false(feats["contains(amazing)"])

    def test_default_extractor(self):
        text = "I feel happy this morning."
        assert_equal(self.classifier.extract_features(text), basic_extractor(text, self.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(self.train_set))

    def test_prob_classify(self):
        res = self.classifier.prob_classify("I feel happy this morning")
        assert_equal(res.max(), "positive")
        assert_true(res.prob("positive") > res.prob("negative"))

    def test_accuracy(self):
        acc = self.classifier.accuracy(self.test_set)
        assert_true(isinstance(acc, float))

    def test_update(self):
        res1 = self.classifier.prob_classify("lorem ipsum")
        original_length = len(self.classifier.train_set)
        self.classifier.update([("lorem ipsum", "positive")])
        new_length = len(self.classifier.train_set)
        res2 = self.classifier.prob_classify("lorem ipsum")
        assert_true(res2.prob("positive") > res1.prob("positive"))
        assert_equal(original_length + 1, new_length)

    def test_show_informative_features(self):
        feats = self.classifier.show_informative_features()

    def test_informative_features(self):
        feats = self.classifier.informative_features(3)
        assert_true(isinstance(feats, list))
        assert_true(isinstance(feats[0], tuple))

    def test_custom_feature_extractor(self):
        cl = NaiveBayesClassifier(self.train_set, custom_extractor)
        cl.classify("Yay! I'm so happy it works.")
        assert_equal(cl.train_features[0][1], 'positive')

# 需要导入模块: from text.classifiers import NaiveBayesClassifier [as 别名]
# 或者: from text.classifiers.NaiveBayesClassifier import show_informative_features [as 别名]
class TestNaiveBayesClassifier(unittest.TestCase):

    def setUp(self):
        self.classifier = NaiveBayesClassifier(train_set)

    def test_basic_extractor(self):
        text = "I feel happy this morning."
        feats = basic_extractor(text, train_set)
        assert_true(feats["contains(feel)"])
        assert_true(feats['contains(morning)'])
        assert_false(feats["contains(amazing)"])

    def test_default_extractor(self):
        text = "I feel happy this morning."
        assert_equal(self.classifier.extract_features(text), basic_extractor(text, 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_classify_a_list_of_words(self):
        res = self.classifier.classify(["I", "feel", "happy", "this", "morning"])
        assert_equal(res, "positive")

    def test_train_from_lists_of_words(self):
        # classifier can be trained on lists of words instead of strings
        train = [(doc.split(), label) for doc, label in train_set]
        classifier = NaiveBayesClassifier(train)
        assert_equal(classifier.accuracy(test_set),
                        self.classifier.accuracy(test_set))

    def test_prob_classify(self):
        res = self.classifier.prob_classify("I feel happy this morning")
        assert_equal(res.max(), "positive")
        assert_true(res.prob("positive") > res.prob("negative"))

    def test_accuracy(self):
        acc = self.classifier.accuracy(test_set)
        assert_true(isinstance(acc, float))

    def test_update(self):
        res1 = self.classifier.prob_classify("lorem ipsum")
        original_length = len(self.classifier.train_set)
        self.classifier.update([("lorem ipsum", "positive")])
        new_length = len(self.classifier.train_set)
        res2 = self.classifier.prob_classify("lorem ipsum")
        assert_true(res2.prob("positive") > res1.prob("positive"))
        assert_equal(original_length + 1, new_length)

    def test_labels(self):
        labels = self.classifier.labels()
        assert_true("positive" in labels)
        assert_true("negative" in labels)

    def test_show_informative_features(self):
        feats = self.classifier.show_informative_features()

    def test_informative_features(self):
        feats = self.classifier.informative_features(3)
        assert_true(isinstance(feats, list))
        assert_true(isinstance(feats[0], tuple))

    def test_custom_feature_extractor(self):
        cl = NaiveBayesClassifier(train_set, custom_extractor)
        cl.classify("Yay! I'm so happy it works.")
        assert_equal(cl.train_features[0][1], 'positive')

    def test_init_with_csv_file(self):
        cl = NaiveBayesClassifier(CSV_FILE, format="csv")
        assert_equal(cl.classify("I feel happy this morning"), 'pos')
        training_sentence = cl.train_set[0][0]
        assert_true(isinstance(training_sentence, unicode))

    def test_init_with_csv_file_without_format_specifier(self):
        cl = NaiveBayesClassifier(CSV_FILE)
        assert_equal(cl.classify("I feel happy this morning"), 'pos')
        training_sentence = cl.train_set[0][0]
        assert_true(isinstance(training_sentence, unicode))

    def test_init_with_json_file(self):
        cl = NaiveBayesClassifier(JSON_FILE, format="json")
        assert_equal(cl.classify("I feel happy this morning"), 'pos')
        training_sentence = cl.train_set[0][0]
        assert_true(isinstance(training_sentence, unicode))

    def test_init_with_json_file_without_format_specifier(self):
        cl = NaiveBayesClassifier(JSON_FILE)
        assert_equal(cl.classify("I feel happy this morning"), 'pos')
        training_sentence = cl.train_set[0][0]
        assert_true(isinstance(training_sentence, unicode))

    def test_accuracy_on_a_csv_file(self):
        a = self.classifier.accuracy(CSV_FILE)
        assert_true(isinstance(a, float))

    def test_accuracy_on_json_file(self):
        a = self.classifier.accuracy(JSON_FILE)
        assert_true(isinstance(a, float))

#.........这里部分代码省略.........