Merge branch 'master' into cuducos-fix-docker-command

rosie/chamber_of_deputies/classifiers/election_expenses_classifier.py

@@ -1,6 +1,8 @@
 from sklearn.base import TransformerMixin
 
 
+ELECTION_LEGAL_ENTITY = '409-0 - CANDIDATO A CARGO POLITICO ELETIVO'
+
 class ElectionExpensesClassifier(TransformerMixin):
     """
     Election Expenses classifier.
@@ -14,11 +16,11 @@ class ElectionExpensesClassifier(TransformerMixin):
         Brazilian Federal Revenue category of companies, preceded by its code.
     """
 
-    def fit(self, X):
-        return self
+    def fit(self, dataframe):
+        pass
 
-    def transform(self, X=None):
-        return self
+    def transform(self, dataframe=None):
+        pass
 
-    def predict(self, X):
-        return X['legal_entity'] == '409-0 - CANDIDATO A CARGO POLITICO ELETIVO'
+    def predict(self, dataframe):
+        return dataframe['legal_entity'] == ELECTION_LEGAL_ENTITY

rosie/chamber_of_deputies/tests/test_election_expenses_classifier.py

@@ -9,18 +9,36 @@
 class TestElectionExpensesClassifier(TestCase):
 
     def setUp(self):
-        self.dataset = pd.read_csv('rosie/chamber_of_deputies/tests/fixtures/election_expenses_classifier.csv',
-                                   dtype={'name': np.str, 'legal_entity': np.str})
-        self.subject = ElectionExpensesClassifier()
+        self.election_expenser_classifier = ElectionExpensesClassifier()
 
-    def test_is_election_company(self):
-        self.assertEqual(self.subject.predict(self.dataset)[0], True)
+    def test_legal_entity_is_a_election_company(self):
+        self.dataframe = self._create_dataframe([[
+            'CARLOS ALBERTO DA SILVA',
+            'ELEICAO 2006 CARLOS ALBERTO DA SILVA DEPUTADO',
+            '409-0 - CANDIDATO A CARGO POLITICO ELETIVO'
+        ]])
 
-    def test_is_not_election_company(self):
-        self.assertEqual(self.subject.predict(self.dataset)[1], False)
+        prediction_result = self.election_expenser_classifier.predict(self.dataframe)
 
-    def test_fit(self):
-        self.assertEqual(self.subject.fit(self.dataset), self.subject)
+        self.assertEqual(prediction_result[0], True)
 
-    def test_tranform(self):
-        self.assertEqual(self.subject.transform(), self.subject)
+    def test_legal_entity_is_not_election_company(self):
+        self.dataframe = self._create_dataframe([[
+            'PAULO ROGERIO ROSSETO DE MELO',
+            'POSTO ROTA 116 DERIVADOS DE PETROLEO LTDA',
+            '401-4 - EMPRESA INDIVIDUAL IMOBILIARIA'
+        ]])
+
+        prediction_result = self.election_expenser_classifier.predict(self.dataframe)
+
+        self.assertEqual(prediction_result[0], False)
+
+    def test_fit_just_for_formality_because_its_never_used(self):
+        empty_dataframe = pd.DataFrame()
+        self.assertTrue(self.election_expenser_classifier.fit(empty_dataframe) is None)
+
+    def test_transform_just_for_formality_because_its_never_used(self):
+        self.assertTrue(self.election_expenser_classifier.transform() is None)
+
+    def _create_dataframe(self, dataframe_data):
+        return pd.DataFrame(data=dataframe_data, columns=['congressperson_name', 'name', 'legal_entity'])