Merge branch 'cuducos-reestructuring-rosie' into anaschwendler-reestr…

…ucturing-rosie
okfn-brasil · Apr 13, 2017 · e621769 · e621769
2 parents 36fc8c8 + 758df0a
commit e621769
Show file tree

Hide file tree

Showing 29 changed files with 30 additions and 30 deletions.
diff --git a/rosie.py b/rosie.py
@@ -18,15 +18,15 @@ def help():
 
 
 def run():
-    from ceap import classifiers
+    from rosie.ceap import classifiers
     target_directory = argv[2] if len(argv) >= 3 else '/tmp/serenata-data/'
     classifiers.main(target_directory)
 
 
 def test():
     import unittest
     loader = unittest.TestLoader()
-    tests = loader.discover('ceap/tests')
+    tests = loader.discover('rosie')
     testRunner = unittest.runner.TextTestRunner()
     testRunner.run(tests)
 

diff --git a/ceap/__init__.py → rosie/__init__.py b/ceap/__init__.py → rosie/__init__.py
diff --git a/ceap/tests/__init__.py → rosie/ceap/__init__.py b/ceap/tests/__init__.py → rosie/ceap/__init__.py
diff --git a/ceap/classifiers/__init__.py → rosie/ceap/classifiers/__init__.py b/ceap/classifiers/__init__.py → rosie/ceap/classifiers/__init__.py
@@ -3,13 +3,13 @@
 import numpy as np
 from sklearn.externals import joblib
 
-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
+from rosie.ceap.classifiers.dataset import Dataset
+from rosie.ceap.classifiers.election_expenses_classifier import ElectionExpensesClassifier
+from rosie.ceap.classifiers.invalid_cnpj_cpf_classifier import InvalidCnpjCpfClassifier
+from rosie.ceap.classifiers.meal_price_outlier_classifier import MealPriceOutlierClassifier
+from rosie.ceap.classifiers.monthly_subquota_limit_classifier import MonthlySubquotaLimitClassifier
+from rosie.ceap.classifiers.traveled_speeds_classifier import TraveledSpeedsClassifier
+from rosie.ceap.classifiers.irregular_companies_classifier import IrregularCompaniesClassifier
 
 
 class Ceap:

diff --git a/ceap/classifiers/__main__.py → rosie/ceap/classifiers/__main__.py b/ceap/classifiers/__main__.py → rosie/ceap/classifiers/__main__.py
diff --git a/ceap/classifiers/dataset.py → rosie/ceap/classifiers/dataset.py b/ceap/classifiers/dataset.py → rosie/ceap/classifiers/dataset.py
diff --git a/...assifiers/election_expenses_classifier.py → ...assifiers/election_expenses_classifier.py b/...assifiers/election_expenses_classifier.py → ...assifiers/election_expenses_classifier.py
diff --git a/...lassifiers/invalid_cnpj_cpf_classifier.py → ...lassifiers/invalid_cnpj_cpf_classifier.py b/...lassifiers/invalid_cnpj_cpf_classifier.py → ...lassifiers/invalid_cnpj_cpf_classifier.py
diff --git a/...sifiers/irregular_companies_classifier.py → ...sifiers/irregular_companies_classifier.py b/...sifiers/irregular_companies_classifier.py → ...sifiers/irregular_companies_classifier.py
diff --git a/...ssifiers/meal_price_outlier_classifier.py → ...ssifiers/meal_price_outlier_classifier.py b/...ssifiers/meal_price_outlier_classifier.py → ...ssifiers/meal_price_outlier_classifier.py
diff --git a/...iers/monthly_subquota_limit_classifier.py → ...iers/monthly_subquota_limit_classifier.py b/...iers/monthly_subquota_limit_classifier.py → ...iers/monthly_subquota_limit_classifier.py
diff --git a/...classifiers/traveled_speeds_classifier.py → ...classifiers/traveled_speeds_classifier.py b/...classifiers/traveled_speeds_classifier.py → ...classifiers/traveled_speeds_classifier.py
diff --git a/rosie/ceap/tests/__init__.py b/rosie/ceap/tests/__init__.py
diff --git a/ceap/tests/fixtures/companies.xz → rosie/ceap/tests/fixtures/companies.xz b/ceap/tests/fixtures/companies.xz → rosie/ceap/tests/fixtures/companies.xz
diff --git a/...fixtures/election_expenses_classifier.csv → ...fixtures/election_expenses_classifier.csv b/...fixtures/election_expenses_classifier.csv → ...fixtures/election_expenses_classifier.csv
diff --git a/.../fixtures/invalid_cnpj_cpf_classifier.csv → .../fixtures/invalid_cnpj_cpf_classifier.csv b/.../fixtures/invalid_cnpj_cpf_classifier.csv → .../fixtures/invalid_cnpj_cpf_classifier.csv
diff --git a/...xtures/irregular_companies_classifier.csv → ...xtures/irregular_companies_classifier.csv b/...xtures/irregular_companies_classifier.csv → ...xtures/irregular_companies_classifier.csv
diff --git a/...ixtures/meal_price_outlier_classifier.csv → ...ixtures/meal_price_outlier_classifier.csv b/...ixtures/meal_price_outlier_classifier.csv → ...ixtures/meal_price_outlier_classifier.csv
diff --git a/...res/monthly_subquota_limit_classifier.csv → ...res/monthly_subquota_limit_classifier.csv b/...res/monthly_subquota_limit_classifier.csv → ...res/monthly_subquota_limit_classifier.csv
diff --git a/ceap/tests/fixtures/reimbursements.xz → rosie/ceap/tests/fixtures/reimbursements.xz b/ceap/tests/fixtures/reimbursements.xz → rosie/ceap/tests/fixtures/reimbursements.xz
diff --git a/...s/fixtures/traveled_speeds_classifier.csv → ...s/fixtures/traveled_speeds_classifier.csv b/...s/fixtures/traveled_speeds_classifier.csv → ...s/fixtures/traveled_speeds_classifier.csv
diff --git a/ceap/tests/test_ceap.py → rosie/ceap/tests/test_ceap.py b/ceap/tests/test_ceap.py → rosie/ceap/tests/test_ceap.py
@@ -6,7 +6,7 @@
 
 import pandas as pd
 
-from ceap.classifiers import Ceap
+from rosie.ceap.classifiers import Ceap
 
 
 class TestCeap(TestCase):
@@ -22,12 +22,12 @@ def setUp(self):
         self.dataset = pd.DataFrame().append(row, ignore_index=True)
         self.subject = Ceap(self.dataset, mkdtemp())
 
-    @patch('ceap.classifiers.joblib')
+    @patch('rosie.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('ceap.classifiers.joblib')
+    @patch('rosie.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)

diff --git a/ceap/tests/test_dataset.py → rosie/ceap/tests/test_dataset.py b/ceap/tests/test_dataset.py → rosie/ceap/tests/test_dataset.py
@@ -4,20 +4,20 @@
 from unittest.mock import patch
 from shutil import copy2
 
-from ceap.classifiers import Dataset
+from rosie.ceap.classifiers import Dataset
 
 
 class TestDataset(TestCase):
 
     def setUp(self):
         temp_path = mkdtemp()
-        copy2('ceap/tests/fixtures/companies.xz',
+        copy2('rosie/ceap/tests/fixtures/companies.xz',
               os.path.join(temp_path, Dataset.COMPANIES_DATASET))
-        copy2('ceap/tests/fixtures/reimbursements.xz', temp_path)
+        copy2('rosie/ceap/tests/fixtures/reimbursements.xz', temp_path)
         self.subject = Dataset(temp_path)
 
-    @patch('ceap.classifiers.dataset.CEAPDataset')
-    @patch('ceap.classifiers.dataset.fetch')
+    @patch('rosie.ceap.classifiers.dataset.CEAPDataset')
+    @patch('rosie.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))

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

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

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

diff --git a/...sts/test_meal_price_outlier_classifier.py → ...sts/test_meal_price_outlier_classifier.py b/...sts/test_meal_price_outlier_classifier.py → ...sts/test_meal_price_outlier_classifier.py
@@ -5,18 +5,18 @@
 import pandas as pd
 from numpy.testing import assert_array_equal
 
-from ceap.classifiers.meal_price_outlier_classifier import MealPriceOutlierClassifier
+from rosie.ceap.classifiers.meal_price_outlier_classifier import MealPriceOutlierClassifier
 
 
 class TestMealPriceOutlierClassifier(TestCase):
 
     def setUp(self):
-        self.dataset = pd.read_csv('ceap/tests/fixtures/meal_price_outlier_classifier.csv',
+        self.dataset = pd.read_csv('rosie/ceap/tests/fixtures/meal_price_outlier_classifier.csv',
                                    dtype={'cnpj_cpf': np.str})
         self.subject = MealPriceOutlierClassifier()
         self.subject.fit(self.dataset)
 
-    @patch('ceap.classifiers.meal_price_outlier_classifier.KMeans')
+    @patch('rosie.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)

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

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