def setUp(self):
test_name = self.shortDescription()
super(TfIdfTest, self).setUp()
self.mock_obj = TfIdf()
self.mock_obj._text_set = self.test_data.r_D_text_set
self.token_list = res.token_list
self.mock_obj.build_model()
if test_name == "Test routine build_model() in TfIdf":
print "setting up for testing build_model()"
elif test_name == "Test routine build_df_model() in TfIdf":
print "setting up for testing build_df_model()"
self.document_frequency = res.document_frequency
elif test_name == "Test routine build_tf_model() in TfIdf":
print "setting up for testing build_tf_model()"
self.term_frequency = res.term_frequency
elif test_name == "Test routine build_tf_idf_model()/compute() in TfIdf":
print "setting up for testing compute()/build_tf_idf_model()"
self.test_data.attach_feature("tf_idf")
self.tf_idf_weight = res.tf_idf_weight
def init_attribute(self, attribute_name):
"""Create attribute instance
Parameter
---------
attribute_name : string
Contains the feature name, to create an attribute
instance.
"""
if attribute_name == "bag_of_words":
attribute = BagOfWords(self.bow_model)
return attribute
elif attribute_name == "tf_idf":
attribute = TfIdf(self.bow_model)
return attribute
elif attribute_name == "readability":
attribute = Readability()
return attribute
elif attribute_name == "variety":
attribute = Variety()
return attribute
elif attribute_name == "perfect_tense":
attribute = PerfectTense()
return attribute
elif attribute_name == "nested_sentence":
attribute = NestedSentence()
return attribute
elif attribute_name == "passive":
attribute = Passive()
return attribute
elif attribute_name == "adjective":
attribute = Adjective()
return attribute
elif attribute_name == "sentence_start":
attribute = SentenceStart()
return attribute
elif attribute_name == "bag_of_pos":
attribute = BagOfPos(self.bow_model)
return attribute
elif attribute_name == "modal_verb":
attribute = ModalVerb()
return attribute
else:
raise FeatureNotExistException(attribute_name)
def setUp(self):
test_name = self.shortDescription()
super(TfIdfTest, self).setUp()
self.mock_obj = TfIdf()
self.mock_obj._text_set = self.test_data.r_D_text_set
self.token_list = res.token_list
self.mock_obj.build_model()
if test_name == "Test routine build_model() in TfIdf":
print "setting up for testing build_model()"
elif test_name == "Test routine build_df_model() in TfIdf":
print "setting up for testing build_df_model()"
self.document_frequency = res.document_frequency
elif test_name == "Test routine build_tf_model() in TfIdf":
print "setting up for testing build_tf_model()"
self.term_frequency = res.term_frequency
elif test_name == "Test routine build_tf_idf_model()/compute() in TfIdf":
print "setting up for testing compute()/build_tf_idf_model()"
self.test_data.attach_feature("tf_idf")
self.tf_idf_weight = res.tf_idf_weight
class TfIdfTest(TestBodyAttribute):
@classmethod
def setUpClass(cls):
print "#################### Begin Testing TfIdf Class ####################" + "\n"
@classmethod
def tearDownClass(cls):
print "\n" + "###################### End Testing TfIdf Class ######################"
def setUp(self):
test_name = self.shortDescription()
super(TfIdfTest, self).setUp()
self.mock_obj = TfIdf()
self.mock_obj._text_set = self.test_data.r_D_text_set
self.token_list = res.token_list
self.mock_obj.build_model()
if test_name == "Test routine build_model() in TfIdf":
print "setting up for testing build_model()"
elif test_name == "Test routine build_df_model() in TfIdf":
print "setting up for testing build_df_model()"
self.document_frequency = res.document_frequency
elif test_name == "Test routine build_tf_model() in TfIdf":
print "setting up for testing build_tf_model()"
self.term_frequency = res.term_frequency
elif test_name == "Test routine build_tf_idf_model()/compute() in TfIdf":
print "setting up for testing compute()/build_tf_idf_model()"
self.test_data.attach_feature("tf_idf")
self.tf_idf_weight = res.tf_idf_weight
def tearDown(self):
test_name = self.shortDescription()
self.korpus_file = None
self.anno_file = None
self.test_korpus = None
self.test_data = None
self.token_list = None
self.mock_obj = None
if test_name == "Test routine build_model() in TfIdf":
print "cleaning up for testing build_model()"
print "--------------------------------------------------------------"
elif test_name == "Test routine build_df_model() in TfIdf":
print "cleaning up for testing build_df_model()"
print "--------------------------------------------------------------"
self.document_frequency = None
elif test_name == "Test routine build_tf_model() in TfIdf":
print "cleaning up for testing build_tf_model()"
print "--------------------------------------------------------------"
self.term_frequency = None
elif test_name == "Test routine build_tf_idf_model()/compute() in TfIdf":
print "cleaning up for testing compute()/build_tf_idf_model()"
print "--------------------------------------------------------------"
self.tf_idf_weight = None
def test__tf_idf__build_model(self):
""" Test routine build_model() in TfIdf """
self.assertListEqual(sorted(self.token_list), sorted(self.mock_obj.model.keys()))
def test__tf_idf__build_df_model(self):
""" Test routine build_df_model() in TfIdf """
df_model = collections.OrderedDict(sorted(self.mock_obj.build_df_model().items()))
self.assertListEqual(df_model.values(), self.document_frequency)
def test__tf_idf__build_tf_model(self):
""" Test routine build_tf_model() in TfIdf """
for text in self.mock_obj.text_set:
tf_model = collections.OrderedDict(sorted(self.mock_obj.build_tf_model(text.tokenlist).items()))
self.assertListEqual(tf_model.values(), self.term_frequency[text.id])
def test__tf_idf__compute(self):
""" Test routine build_tf_idf_model()/compute() in TfIdf """
for textpair in self.test_data.real_data.values():
self.assertListEqual(textpair.text1.features["tf_idf"], self.tf_idf_weight[textpair.text1.id])
self.assertListEqual(textpair.text2.features["tf_idf"], self.tf_idf_weight[textpair.text2.id])
class TfIdfTest(TestBodyAttribute):
@classmethod
def setUpClass(cls):
print "#################### Begin Testing TfIdf Class ####################" + "\n"
@classmethod
def tearDownClass(cls):
print "\n" + "###################### End Testing TfIdf Class ######################"
def setUp(self):
test_name = self.shortDescription()
super(TfIdfTest, self).setUp()
self.mock_obj = TfIdf()
self.mock_obj._text_set = self.test_data.r_D_text_set
self.token_list = res.token_list
self.mock_obj.build_model()
if test_name == "Test routine build_model() in TfIdf":
print "setting up for testing build_model()"
elif test_name == "Test routine build_df_model() in TfIdf":
print "setting up for testing build_df_model()"
self.document_frequency = res.document_frequency
elif test_name == "Test routine build_tf_model() in TfIdf":
print "setting up for testing build_tf_model()"
self.term_frequency = res.term_frequency
elif test_name == "Test routine build_tf_idf_model()/compute() in TfIdf":
print "setting up for testing compute()/build_tf_idf_model()"
self.test_data.attach_feature("tf_idf")
self.tf_idf_weight = res.tf_idf_weight
def tearDown(self):
test_name = self.shortDescription()
self.korpus_file = None
self.anno_file = None
self.test_korpus = None
self.test_data = None
self.token_list = None
self.mock_obj = None
if test_name == "Test routine build_model() in TfIdf":
print "cleaning up for testing build_model()"
print "--------------------------------------------------------------"
elif test_name == "Test routine build_df_model() in TfIdf":
print "cleaning up for testing build_df_model()"
print "--------------------------------------------------------------"
self.document_frequency = None
elif test_name == "Test routine build_tf_model() in TfIdf":
print "cleaning up for testing build_tf_model()"
print "--------------------------------------------------------------"
self.term_frequency = None
elif test_name == "Test routine build_tf_idf_model()/compute() in TfIdf":
print "cleaning up for testing compute()/build_tf_idf_model()"
print "--------------------------------------------------------------"
self.tf_idf_weight = None
def test__tf_idf__build_model(self):
""" Test routine build_model() in TfIdf """
self.assertListEqual(sorted(self.token_list),
sorted(self.mock_obj.model.keys()))
def test__tf_idf__build_df_model(self):
""" Test routine build_df_model() in TfIdf """
df_model = collections.OrderedDict(
sorted(self.mock_obj.build_df_model().items()))
self.assertListEqual(df_model.values(), self.document_frequency)
def test__tf_idf__build_tf_model(self):
""" Test routine build_tf_model() in TfIdf """
for text in self.mock_obj.text_set:
tf_model = collections.OrderedDict(
sorted(self.mock_obj.build_tf_model(text.tokenlist).items()))
self.assertListEqual(tf_model.values(),
self.term_frequency[text.id])
def test__tf_idf__compute(self):
""" Test routine build_tf_idf_model()/compute() in TfIdf """
for textpair in self.test_data.real_data.values():
self.assertListEqual(textpair.text1.features["tf_idf"],
self.tf_idf_weight[textpair.text1.id])
self.assertListEqual(textpair.text2.features["tf_idf"],
self.tf_idf_weight[textpair.text2.id])
