def setUp(self):
text = u"Comment Google classe les pages Internet"
c = Classifier(CleanTextUtil("french"))
c.add_text(text)
self.dictionary_db = c.dictionary_db
self.vi = VectorItem("googl", "1")
class TestClassifier(unittest.TestCase):
""" Tests the Classifier class.
"""
def setUp(self):
self.c = Classifier(CleanTextUtil("french"))
def tearDown(self):
rm_data_dir()
def test_add_text(self):
""" Tests add_text.
Add a text to the classifier:
1- Verify if the number of text equals 1.
2- Verify if the text added is equals to words wanted.
"""
flux1_text = (
u"Comment Google classe les pages Internet "
u"Bientôt une sphère pour remplacer souris et écrans tactiles ? "
u"Le clip kitsch du couple présidentiel chinois"
)
flux1_text_wanted = [
"bient", "chinois", "class", "clip", "comment", "coupl",
"cran", "googl", "internet", "kitsch", "le", "pag", "pr",
"re", "remplac", "sidentiel", "sour", "sph", "tactil"
]
self.c.add_text(flux1_text)
self.assertEquals(int(self.c.classifier_state_db.get("text_nb")), 1) # 1
words = [word for word, _ in kc_util.gen_db(self.c.dictionary_db.cursor())]
self.assertEquals(words, flux1_text_wanted) # 2
def test_set_idf(self):
""" Tests set_idf.
Add two texts:
1- Verify idf equals 0.0
Add idf:
2- Verify idf not equals 0.0
"""
self.c.add_text("foo")
self.c.add_text("bar") # important for idf
_, word_info = kc_util.gen_db(self.c.dictionary_db.cursor()).next()
self.assertEquals(word_info.idf, 0.0) # 1
self.c.set_idf()
_, word_info = kc_util.gen_db(self.c.dictionary_db.cursor()).next()
self.assertNotEquals(word_info.idf, 0.0) # 2
def test_set_idf_tfidf_norm(self):
""" Tests set_idf_tfidf_norm.
Add two texts:
1- Verify idf equals 0.0
2- Verify idf norm equals '0.0'
Update idf:
2- Verify idf not equals 0.0
3- Verify idf norm not equals '0.0'
"""
text, vector_1 = "foo", "foo_1"
self.c.add_text(text)
self.c.add_text("bar") # important for idf
_, word_info = kc_util.gen_db(self.c.dictionary_db.cursor()).next()
self.assertEquals(word_info.idf, 0.0) # 1
self.c.add_vector(vector_1, text)
norm = self.c.vectors_norm_db.get(vector_1)
self.assertEquals(norm, '0.0') # 2
self.c.set_idf()
_, word_info = kc_util.gen_db(self.c.dictionary_db.cursor()).next()
self.assertNotEquals(word_info.idf, 0.0) # 3
self.c.set_tfidf_norm()
norm = self.c.vectors_norm_db.get(vector_1)
self.assertNotEquals(norm, '0.0') # 4
def test_add_vector(self):
""" Tests add_vector.
Add a text.
1- Check if there is not a vector.
Add a vector:
2- Check if there is a vector.
"""
text, vector_1 = "foo", "foo_1"
self.c.add_text(text)
vector = self.c.get_vector(vector_1)
self.assertIsNone(vector) # 1
self.c.add_vector(vector_1, text)
vector = self.c.get_vector(vector_1)
self.assertIsInstance(vector, Vector) # 2
def test_rm_vector(self):
""" Tests rm_vector.
Add a text.
Add a vector:
1- Check if the vector exists.
Remove the vector:
2- Check if the vector doesn't exist anymore.
"""
text, vector_1 = "foo", "foo_1"
self.c.add_text(text)
self.c.add_vector(vector_1, text)
vector = self.c.get_vector(vector_1)
self.assertIsNotNone(vector) # 1
self.c.rm_vector(vector_1)
vector = self.c.get_vector(vector_1)
self.assertIsNone(vector) # 2
def test_get_vector(self):
""" Tests get_vector.
Add a text.
Add a vector.
1- Check if the vector exists with "get_vector".
Get an unknown vector.
2- Check if the vector is None.
"""
text, vector_1 = "foo", "foo_1"
self.c.add_text(text)
self.c.add_vector(vector_1, text)
vector = self.c.get_vector(vector_1)
self.assertIsNotNone(vector) # 1
vector = self.c.get_vector("unknown vector")
self.assertIsNone(vector) # 2
def test_get_vectors(self):
""" Tests get_vectors.
Add two texts.
Add two vectors.
With get_vectors:
1- Verify names equals by comparing names.
2- Verify object equals by comparing tags.
"""
text_1, vector_1, tag_1 = "foo", "foo_1", "SPORT"
text_2, vector_2, tag_2 = "bar", "bar_1", "BUSINESS"
self.c.add_text(text_1)
self.c.add_text(text_2)
self.c.add_vector(vector_1, text_1, tag_1)
self.c.add_vector(vector_2, text_2, tag_2)
names = [name for name, _ in self.c.get_vectors()]
self.assertEquals(set(names), set(self.c.get_vectors_name())) # 1
tags = [vector.tag for _, vector in self.c.get_vectors()]
self.assertEquals(set([tag_1, tag_2]), set(tags)) # 2
def test_get_vectors_name(self):
""" Tests get_vectors_name.
Add two texts.
Add two vectors.
Get vectors names:
1- Verify names equals.
"""
text_1, vector_1 = "foo", "foo_1"
text_2, vector_2 = "bar", "bar_1"
self.c.add_text(text_1)
self.c.add_text(text_2)
self.c.add_vector(vector_1, text_1)
self.c.add_vector(vector_2, text_2)
names = self.c.get_vectors_name()
self.assertEquals(set([vector_1,vector_2]), set(names)) # 1
def test_idf(self):
#TODO
""" Test .
"""
pass
def test_tf_idf(self):
""" Test .
"""
pass
def test_vector_tfidf_norm(self):
""" Test .
"""
pass
def test_scalar_product(self):
""" Test .
"""
pass
def test_cosine_sim(self):
""" Test .
"""
pass
def test_kNN(self):
""" Test .
"""
pass
def test_get_category(self):
""" Test .
"""
pass
def test_print_words_structure(self):
""" Test .
"""
pass
def test_print_vector(self):
""" Test .
"""
pass
def test_print_vectors(self):
""" Test .
"""
pass