('He is my sworn enemy!', 'neg'),
('My boss is horrible.', 'neg')
]
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')
]
print 'initial training going on....'
cl = NaiveBayesClassifier(train)
print 'initial training done.'
# Grab some movie review data
print 'now gathering reviews...'
reviews = [(list(movie_reviews.words(fileid)), category)
for category in movie_reviews.categories()
for fileid in movie_reviews.fileids(category)]
random.shuffle(reviews)
new_train = reviews[0:200]
print 'reviews gathered.'
# Update the classifier with the new training data
print 'now training using the new data...'
cl.update(new_train)
print 'trained and ready!'
print cl.classify("I hated the movie and hated the food")
# Compute accuracy
accuracy = cl.accuracy(test)
print("Accuracy: {0}".format(accuracy))
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')
('This is an amazing place!', 'pos'),
('I feel very good about these beers.', 'pos'),
('This is my best work.', 'pos'), ("What an awesome view", 'pos'),
('I do not like this restaurant', 'neg'),
('I am tired of this stuff.', 'neg'),
("I can't deal with this", 'neg'), ('He is my sworn enemy!', 'neg'),
('My boss is horrible.', 'neg')]
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)
# Grab some movie review data
reviews = [(list(movie_reviews.words(fileid)), category)
for category in movie_reviews.categories()
for fileid in movie_reviews.fileids(category)]
random.shuffle(reviews)
new_train, new_test = reviews[0:100], reviews[101:200]
# Update the classifier with the new training data
cl.update(new_train)
# Compute accuracy
accuracy = cl.accuracy(test + new_test)
print("Accuracy: {0}".format(accuracy))
# Show 5 most informative features
cl.show_informative_features(15)
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')
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))
def test_init_with_tsv_file(self):
cl = NaiveBayesClassifier(TSV_FILE)
assert_equal(cl.classify("I feel happy this morning"), 'pos')
training_sentence = cl.train_set[0][0]
assert_true(isinstance(training_sentence, unicode))
@attr("py27_only")
def test_init_with_bad_format_specifier(self):
with assert_raises(ValueError):
NaiveBayesClassifier(CSV_FILE, format='unknown')
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))
def test_init_with_tsv_file(self):
cl = NaiveBayesClassifier(TSV_FILE)
assert_equal(cl.classify("I feel happy this morning"), 'pos')
training_sentence = cl.train_set[0][0]
assert_true(isinstance(training_sentence, unicode))
@attr("py27_only")
def test_init_with_bad_format_specifier(self):
with assert_raises(ValueError):
NaiveBayesClassifier(CSV_FILE, format='unknown')
def ask_with_guess(df, c=None):
init()
df['cat'] = ""
if c is None:
c = NaiveBayesClassifier([], extractor)
categories = {1: 'Bill',
2: 'Supermarket',
3: 'Cash',
4: 'Petrol',
5: 'Eating Out',
6: 'Travel',
7: 'Unclassified',
8: 'House',
9: 'Books',
10: 'Craft',
11: 'Charity Shop',
12: 'Presents',
13: 'Toiletries',
14: 'Car',
15: 'Cheque',
16: 'Rent',
17: 'Paypal',
18: 'Ignore',
19: 'Expenses'
}
for index, row in df.iterrows():
#print Fore.GREEN + "-" * 72 + Fore.RESET
# TODO: Make interface nicer
# Ideas:
# * Give list of categories at the end
cats_list = ["%d: %s" % (id, cat) for id,cat in categories.iteritems()]
new_list = []
for item in cats_list:
if len(item.split(":")[1].strip()) < 5:
new_list.append(item + "\t\t\t")
else:
new_list.append(item + "\t\t")
new_list[2::3] = map(lambda x: x+"\n", new_list[2::3])
cats_joined = "".join(new_list)
stripped_text = strip_numbers(row['desc'])
if len(c.train_set) > 1:
guess = c.classify(stripped_text)
else:
guess = ""
# PRINTING STUFF
print chr(27) + "[2J"
print cats_joined
print "\n\n"
print "On: %s\t %.2f\n%s" % (row['date'], row['amount'], row['desc'])
print Fore.RED + Style.BRIGHT + "My guess is: " + guess + Fore.RESET
res = raw_input("> ")
if res.lower().startswith('q'):
# Q = Quit
return df,c
if res == "":
# Our guess was right!
df.ix[index, 'cat'] = guess
c.update([(stripped_text, guess)])
else:
# Our guess was wrong
# Write correct answer
df.ix[index, 'cat'] = categories[int(res)]
# Update classifier
c.update([(stripped_text, categories[int(res)])])
return df,c
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))
def test_init_with_tsv_file(self):
cl = NaiveBayesClassifier(TSV_FILE)
assert_equal(cl.classify("I feel happy this morning"), 'pos')
training_sentence = cl.train_set[0][0]
assert_true(isinstance(training_sentence, unicode))
@attr("py27_only")
def test_init_with_bad_format_specifier(self):
with assert_raises(ValueError):
NaiveBayesClassifier(CSV_FILE, format='unknown')
('This is an amazing place!', 'pos'),
('I feel very good about these beers.', 'pos'),
('This is my best work.', 'pos'), ("What an awesome view", 'pos'),
('I do not like this restaurant', 'neg'),
('I am tired of this stuff.', 'neg'),
("I can't deal with this", 'neg'), ('He is my sworn enemy!', 'neg'),
('My boss is horrible.', 'neg')]
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)
# Grab some movie review data
reviews = [(list(movie_reviews.words(fileid)), category)
for category in movie_reviews.categories()
for fileid in movie_reviews.fileids(category)]
cl.update(reviews[101:200])
random.shuffle(reviews)
print type(reviews)
for it in reviews[0:4]:
print it
print 'Sentiment Analysis:', cl.classify(it[0])
new_train, new_test = reviews[0:100], reviews[101:200]
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)
# Grab some movie review data
reviews = [(list(movie_reviews.words(fileid)), category)
for category in movie_reviews.categories()
for fileid in movie_reviews.fileids(category)]
cl.update(reviews[101:200])
random.shuffle(reviews)
print type(reviews)
for it in reviews[0:4]:
print it
print 'Sentiment Analysis:',cl.classify(it[0])
new_train, new_test = reviews[0:100], reviews[101:200]