def setUp(self):
self.classifier = CustomWorkClassifier(name="Pride and Prejudice",
datastore=TEST_REDIS,
simple=True)
self.labels = [0, # b1629290
0,
1,
1,
1,
1,
1,
0,
1,
1,
1,
0,
0,
0,
0,
0,
0,
0,
1,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0]
def setUp(self):
self.classifier = CustomWorkClassifier(name="Pride and Prejudice", datastore=TEST_REDIS, simple=True)
self.labels = [
0, # b1629290
0,
1,
1,
1,
1,
1,
0,
1,
1,
1,
0,
0,
0,
0,
0,
0,
0,
1,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
]
class TestCustomPrideAndPrejudice(unittest.TestCase):
def setUp(self):
self.classifier = CustomWorkClassifier(name="Pride and Prejudice", datastore=TEST_REDIS, simple=True)
self.labels = [
0, # b1629290
0,
1,
1,
1,
1,
1,
0,
1,
1,
1,
0,
0,
0,
0,
0,
0,
0,
1,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
]
def test_init(self):
self.assert_(self.classifier is not None)
self.assertEquals(len(self.labels), 30)
def test_load_training_marc(self):
self.classifier.load_training_marc(os.path.join("ColoradoCollege", "pride-and-prejudice.mrc"))
self.assertEquals(len(self.classifier.training_data), 30)
def test_generate_training_labels(self):
labels = 30 * [0]
self.classifier.load_training_marc(os.path.join("ColoradoCollege", "pride-and-prejudice.mrc"))
self.classifier.generate_training_labels(labels=labels)
self.assertEquals(labels, self.classifier.training_labels)
def test_generate_training_vocabulary(self):
self.classifier.load_training_marc(os.path.join("ColoradoCollege", "pride-and-prejudice.mrc"))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.assertEquals(
self.classifier.training_vocabulary,
set(
[
"affair",
"bebris",
"helen",
"matters",
"1817",
"prejudice",
"jane",
"impressions",
"pride",
"crawford",
"1958",
"first",
"sentimental",
"carrie",
"1883",
"prejudiceor",
"mansfield",
"1775",
"austen",
"prejudice",
"comedy",
"jerome",
"mystery",
"emma",
"annotated",
"edition",
"darcy",
"acknowledged",
"mr",
"park",
"revisited",
"mrs",
"prescience",
"suspense",
"truth",
"sense",
"sensibility",
"universally",
]
),
)
def test_tokens2vectors(self):
self.classifier.load_training_marc(os.path.join("ColoradoCollege", "pride-and-prejudice.mrc"))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.assertEquals(
self.classifier.tokens2vectors(["austen", "first", "matters"]),
[0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1],
)
def test_generate_training_matrix(self):
self.classifier.load_training_marc(os.path.join("ColoradoCollege", "pride-and-prejudice.mrc"))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.classifier.generate_training_matrix()
print("IN training matrix test={0}".format(self.classifier.training_matrix))
self.assertEquals(self.classifier.training_matrix[0][6], 1)
def test_train_naive_bayes(self):
self.classifier.load_training_marc(os.path.join("ColoradoCollege", "pride-and-prejudice.mrc"))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.classifier.generate_training_matrix()
self.classifier.train_naive_bayes()
self.assertEquals(self.classifier.pWork, 0.47368421052631576)
self.assertEquals(self.classifier.p0Vector[0], 0.029411764705882353)
self.assertEquals(self.classifier.p1Vector[6], 0.16666667)
def test_classify(self):
self.classifier.load_training_marc(os.path.join("ColoradoCollege", "pride-and-prejudice.mrc"))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.classifier.generate_training_matrix()
self.classifier.train_naive_bayes()
self.assertEquals(self.classifier.classify(["jane", "austen", "pride", "prejudice"]), 1)
self.assertEquals(self.classifier.classify(["jane", "eyre", "anne", "green"]), 0)
def tearDown(self):
pass
class TestCustomPrideAndPrejudice(unittest.TestCase):
def setUp(self):
self.classifier = CustomWorkClassifier(name="Pride and Prejudice",
datastore=TEST_REDIS,
simple=True)
self.labels = [0, # b1629290
0,
1,
1,
1,
1,
1,
0,
1,
1,
1,
0,
0,
0,
0,
0,
0,
0,
1,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0,
0]
def test_init(self):
self.assert_(self.classifier is not None)
self.assertEquals(len(self.labels), 30)
def test_load_training_marc(self):
self.classifier.load_training_marc(
os.path.join('ColoradoCollege',
'pride-and-prejudice.mrc'))
self.assertEquals(len(self.classifier.training_data),
30)
def test_generate_training_labels(self):
labels = 30*[0]
self.classifier.load_training_marc(
os.path.join('ColoradoCollege',
'pride-and-prejudice.mrc'))
self.classifier.generate_training_labels(labels=labels)
self.assertEquals(labels,
self.classifier.training_labels)
def test_generate_training_vocabulary(self):
self.classifier.load_training_marc(
os.path.join('ColoradoCollege',
'pride-and-prejudice.mrc'))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.assertEquals(self.classifier.training_vocabulary,
set(['affair', 'bebris', 'helen', 'matters',
'1817', 'prejudice', 'jane', 'impressions',
'pride', 'crawford', '1958', 'first',
'sentimental', 'carrie', '1883', 'prejudiceor',
'mansfield', '1775', 'austen', 'prejudice',
'comedy', 'jerome', 'mystery', 'emma',
'annotated', 'edition', 'darcy', 'acknowledged',
'mr', 'park', 'revisited', 'mrs', 'prescience',
'suspense', 'truth', 'sense', 'sensibility',
'universally']))
def test_tokens2vectors(self):
self.classifier.load_training_marc(
os.path.join('ColoradoCollege',
'pride-and-prejudice.mrc'))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.assertEquals(self.classifier.tokens2vectors(['austen',
'first',
'matters']),
[0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 1])
def test_generate_training_matrix(self):
self.classifier.load_training_marc(
os.path.join('ColoradoCollege',
'pride-and-prejudice.mrc'))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.classifier.generate_training_matrix()
print("IN training matrix test={0}".format(self.classifier.training_matrix))
self.assertEquals(self.classifier.training_matrix[0][6],
1)
def test_train_naive_bayes(self):
self.classifier.load_training_marc(
os.path.join('ColoradoCollege',
'pride-and-prejudice.mrc'))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.classifier.generate_training_matrix()
self.classifier.train_naive_bayes()
self.assertEquals(self.classifier.pWork,
0.47368421052631576)
self.assertEquals(self.classifier.p0Vector[0], 0.029411764705882353)
self.assertEquals(self.classifier.p1Vector[6], 0.16666667)
def test_classify(self):
self.classifier.load_training_marc(
os.path.join('ColoradoCollege',
'pride-and-prejudice.mrc'))
self.classifier.generate_training_labels(labels=self.labels)
self.classifier.generate_training_vocabulary()
self.classifier.generate_training_matrix()
self.classifier.train_naive_bayes()
self.assertEquals(self.classifier.classify(['jane', 'austen',
'pride', 'prejudice']),
1)
self.assertEquals(self.classifier.classify(['jane', 'eyre', 'anne', 'green']),
0)
def tearDown(self):
pass
