Reestructuring rosie based on python packages

First steps towards making rosie more generic following
[this gist](https://gist.github.com/c98a91a9447b9404abd3b449daba50ec) and [this part](https://docs.python.org/3/tutorial/modules.html#packages) of python documentation.
Thanks to @jtemporal for the time the help to start it.

rosie/__init__.py → ceap/classifiers/__init__.py

@@ -3,16 +3,16 @@
 import numpy as np
 from sklearn.externals import joblib
 
-from rosie.dataset import Dataset
-from rosie.election_expenses_classifier import ElectionExpensesClassifier
-from rosie.invalid_cnpj_cpf_classifier import InvalidCnpjCpfClassifier
-from rosie.meal_price_outlier_classifier import MealPriceOutlierClassifier
-from rosie.monthly_subquota_limit_classifier import MonthlySubquotaLimitClassifier
-from rosie.traveled_speeds_classifier import TraveledSpeedsClassifier
-from rosie.irregular_companies_classifier import IrregularCompaniesClassifier
+from ceap.classifiers.dataset import Dataset
+from ceap.classifiers.election_expenses_classifier import ElectionExpensesClassifier
+from ceap.classifiers.invalid_cnpj_cpf_classifier import InvalidCnpjCpfClassifier
+from ceap.classifiers.meal_price_outlier_classifier import MealPriceOutlierClassifier
+from ceap.classifiers.monthly_subquota_limit_classifier import MonthlySubquotaLimitClassifier
+from ceap.classifiers.traveled_speeds_classifier import TraveledSpeedsClassifier
+from ceap.classifiers.irregular_companies_classifier import IrregularCompaniesClassifier
 
 
-class Rosie:
+class Ceap:
     CLASSIFIERS = {
         MealPriceOutlierClassifier: 'meal_price_outlier',
         MonthlySubquotaLimitClassifier: 'over_monthly_subquota_limit',
@@ -66,4 +66,4 @@ def predict(self, model, irregularity):
 
 def main(target_directory='/tmp/serenata-data'):
     dataset = Dataset(target_directory).get()
-    Rosie(dataset, target_directory).run_classifiers()
+    Ceap(dataset, target_directory).run_classifiers()

ceap/classifiers/__main__.py

@@ -0,0 +1,4 @@
+from ceap import main
+
+
+main()

tests/fixtures/irregular_companies_classifier.csv → ceap/tests/fixtures/irregular_companies_classifier.csv

@@ -1,5 +1,5 @@
 cnpj_cpf,situation,situation_date,issue_date
-02989654001197,ABERTA,2013-01-03,2013-01-30
+02989654001197,ABERTA,201 3-01-03,2013-01-30
 02989654001197,BAIXADA,2013-01-03,2013-01-30
 02989654001197,NULA,2013-01-03,2013-01-30
 02989654001197,INAPTA,2013-01-03,2013-01-30

tests/test_rosie.py → ceap/tests/test_ceap.py

@@ -6,10 +6,10 @@
 
 import pandas as pd
 
-from rosie import Rosie
+from ceap.classifiers import Ceap
 
 
-class TestRosie(TestCase):
+class TestCeap(TestCase):
 
     def setUp(self):
         row = pd.Series({'applicant_id': 444,
@@ -20,14 +20,14 @@ def setUp(self):
                          'total_net_value': 178,
                          'year': 2016})
         self.dataset = pd.DataFrame().append(row, ignore_index=True)
-        self.subject = Rosie(self.dataset, mkdtemp())
+        self.subject = Ceap(self.dataset, mkdtemp())
 
-    @patch('rosie.joblib')
+    @patch('ceap.classifiers.joblib')
     def test_load_trained_model_trains_model_when_not_persisted(self, _):
         model = self.subject.load_trained_model(MagicMock)
         model.fit.assert_called_once_with(self.dataset)
 
-    @patch('rosie.joblib')
+    @patch('ceap.classifiers.joblib')
     def test_load_trained_model_doesnt_train_model_when_already_persisted(self, _):
         Path(os.path.join(self.subject.data_path, 'magicmock.pkl')).touch()
         model = self.subject.load_trained_model(MagicMock)

tests/test_dataset.py → ceap/tests/test_dataset.py

@@ -4,20 +4,20 @@
 from unittest.mock import patch
 from shutil import copy2
 
-from rosie import Dataset
+from ceap.classifiers import Dataset
 
 
 class TestDataset(TestCase):
 
     def setUp(self):
         temp_path = mkdtemp()
-        copy2('tests/fixtures/companies.xz',
+        copy2('ceap/tests/fixtures/companies.xz',
               os.path.join(temp_path, Dataset.COMPANIES_DATASET))
-        copy2('tests/fixtures/reimbursements.xz', temp_path)
+        copy2('ceap/tests/fixtures/reimbursements.xz', temp_path)
         self.subject = Dataset(temp_path)
 
-    @patch('rosie.dataset.CEAPDataset')
-    @patch('rosie.dataset.fetch')
+    @patch('ceap.classifiers.dataset.CEAPDataset')
+    @patch('ceap.classifiers.dataset.fetch')
     def test_get_performs_a_left_merge_between_reimbursements_and_companies(self, _ceap_dataset, _fetch):
         dataset = self.subject.get()
         self.assertEqual(5, len(dataset))

tests/test_election_expenses_classifier.py → ceap/tests/test_election_expenses_classifier.py

@@ -3,13 +3,13 @@
 import numpy as np
 import pandas as pd
 
-from rosie.election_expenses_classifier import ElectionExpensesClassifier
+from ceap.classifiers.election_expenses_classifier import ElectionExpensesClassifier
 
 
 class TestElectionExpensesClassifier(TestCase):
 
     def setUp(self):
-        self.dataset = pd.read_csv('tests/fixtures/election_expenses_classifier.csv',
+        self.dataset = pd.read_csv('ceap/tests/fixtures/election_expenses_classifier.csv',
                                    dtype={'name': np.str, 'legal_entity': np.str})
         self.subject = ElectionExpensesClassifier()
 

tests/test_invalid_cnpj_cpf_classifier.py → ceap/tests/test_invalid_cnpj_cpf_classifier.py

@@ -3,13 +3,13 @@
 import numpy as np
 import pandas as pd
 
-from rosie.invalid_cnpj_cpf_classifier import InvalidCnpjCpfClassifier
+from ceap.classifiers.invalid_cnpj_cpf_classifier import InvalidCnpjCpfClassifier
 
 
 class TestInvalidCnpjCpfClassifier(TestCase):
 
     def setUp(self):
-        self.dataset = pd.read_csv('tests/fixtures/invalid_cnpj_cpf_classifier.csv',
+        self.dataset = pd.read_csv('ceap/tests/fixtures/invalid_cnpj_cpf_classifier.csv',
                                    dtype={'cnpj_cpf': np.str})
         self.subject = InvalidCnpjCpfClassifier()
 

tests/test_irregular_companies_classifier.py → ceap/tests/test_irregular_companies_classifier.py

@@ -3,13 +3,13 @@
 import numpy as np
 import pandas as pd
 
-from rosie.irregular_companies_classifier import IrregularCompaniesClassifier
+from ceap.classifiers.irregular_companies_classifier import IrregularCompaniesClassifier
 
 
 class TestIrregularCompaniesClassifier(TestCase):
 
     def setUp(self):
-        self.dataset = pd.read_csv('tests/fixtures/irregular_companies_classifier.csv',
+        self.dataset = pd.read_csv('ceap/tests/fixtures/irregular_companies_classifier.csv',
                                    dtype={'cnpj': np.str})
         self.subject = IrregularCompaniesClassifier()
 

tests/test_meal_price_outlier_classifier.py → ceap/tests/test_meal_price_outlier_classifier.py

@@ -5,18 +5,18 @@
 import pandas as pd
 from numpy.testing import assert_array_equal
 
-from rosie.meal_price_outlier_classifier import MealPriceOutlierClassifier
+from ceap.classifiers.meal_price_outlier_classifier import MealPriceOutlierClassifier
 
 
 class TestMealPriceOutlierClassifier(TestCase):
 
     def setUp(self):
-        self.dataset = pd.read_csv('tests/fixtures/meal_price_outlier_classifier.csv',
+        self.dataset = pd.read_csv('ceap/tests/fixtures/meal_price_outlier_classifier.csv',
                                    dtype={'cnpj_cpf': np.str})
         self.subject = MealPriceOutlierClassifier()
         self.subject.fit(self.dataset)
 
-    @patch('rosie.meal_price_outlier_classifier.KMeans')
+    @patch('ceap.classifiers.meal_price_outlier_classifier.KMeans')
     def test_predict_returns_a_prediction_for_each_observation(self, kmeans_mock):
         kmeans_mock.return_value.predict.return_value = np.ones(3)
         self.subject.fit(self.dataset)

tests/test_monthly_subquota_limit_classifier.py → ceap/tests/test_monthly_subquota_limit_classifier.py

@@ -4,13 +4,13 @@
 import pandas as pd
 from numpy.testing import assert_array_equal
 
-from rosie.monthly_subquota_limit_classifier import MonthlySubquotaLimitClassifier
+from ceap.classifiers.monthly_subquota_limit_classifier import MonthlySubquotaLimitClassifier
 
 
 class TestMonthlySubquotaLimitClassifier(TestCase):
 
     def setUp(self):
-        self.dataset = pd.read_csv('tests/fixtures/monthly_subquota_limit_classifier.csv',
+        self.dataset = pd.read_csv('ceap/tests/fixtures/monthly_subquota_limit_classifier.csv',
                                    dtype={'subquota_number': np.str})
         self.subject = MonthlySubquotaLimitClassifier()
         self.subject.fit_transform(self.dataset)

tests/test_traveled_speeds_classifier.py → ceap/tests/test_traveled_speeds_classifier.py

@@ -5,13 +5,13 @@
 import sklearn
 from numpy.testing import assert_array_equal
 
-from rosie.traveled_speeds_classifier import TraveledSpeedsClassifier
+from ceap.classifiers.traveled_speeds_classifier import TraveledSpeedsClassifier
 
 
 class TestTraveledSpeedsClassifier(TestCase):
 
     def setUp(self):
-        self.dataset = pd.read_csv('tests/fixtures/traveled_speeds_classifier.csv',
+        self.dataset = pd.read_csv('ceap/tests/fixtures/traveled_speeds_classifier.csv',
                                    dtype={'cnpj_cpf': np.str})
         self.subject = TraveledSpeedsClassifier()
         self.subject.fit(self.dataset)

rosie.py

@@ -18,15 +18,15 @@ def help():
 
 
 def run():
-    import rosie
+    from ceap import classifiers
     target_directory = argv[2] if len(argv) >= 3 else '/tmp/serenata-data/'
-    rosie.main(target_directory)
+    classifiers.main(target_directory)
 
 
 def test():
     import unittest
     loader = unittest.TestLoader()
-    tests = loader.discover('tests')
+    tests = loader.discover('ceap/tests')
     testRunner = unittest.runner.TextTestRunner()
     testRunner.run(tests)