further adjustments

test/test_run_modules/test_pre_processing.py

@@ -28,17 +28,16 @@ class TestPreProcessing:
 
     @pytest.fixture
     def obj_with_exp_setup(self):
-        ExperimentSetup(stations=['DEBW107', 'DEBY081', 'DEBW013', 'DEBW087', 'DEBW99X'],
+        ExperimentSetup(stations=['DEBW107', 'DEBW013', 'DEBW087', 'DEBW99X'],
                         statistics_per_var={'o3': 'dma8eu', 'temp': 'maximum'}, station_type="background",
-                        data_origin={'o3': 'UBA', 'temp': 'UBA'},
-                        data_handler=DefaultDataHandler)
+                        data_origin={'o3': 'UBA', 'temp': 'UBA'}, data_handler=DefaultDataHandler)
         pre = object.__new__(PreProcessing)
         super(PreProcessing, pre).__init__()
         yield pre
         RunEnvironment().__del__()
 
     def test_init(self, caplog):
-        ExperimentSetup(stations=['DEBW107', 'DEBY081', 'DEBW013', 'DEBW087'],
+        ExperimentSetup(stations=['DEBW107', 'DEBW013', 'DEBW087'],
                         statistics_per_var={'o3': 'dma8eu', 'temp': 'maximum'},
                         data_origin={'o3': 'UBA', 'temp': 'UBA'})
         caplog.clear()
@@ -46,8 +45,8 @@ class TestPreProcessing:
         with PreProcessing():
             assert caplog.record_tuples[0] == ('root', 20, 'PreProcessing started')
             assert caplog.record_tuples[1] == ('root', 20, 'check valid stations started (preprocessing)')
-            assert caplog.record_tuples[-6] == ('root', 20, PyTestRegex(r'run for \d+:\d+:\d+ \(hh:mm:ss\) to check 4 '
-                                                                        r'station\(s\). Found 4/4 valid stations.'))
+            assert caplog.record_tuples[-6] == ('root', 20, PyTestRegex(r'run for \d+:\d+:\d+ \(hh:mm:ss\) to check 3 '
+                                                                        r'station\(s\). Found 3/3 valid stations.'))
             assert caplog.record_tuples[-5] == ('root', 20, "use serial create_info_df (train)")
             assert caplog.record_tuples[-4] == ('root', 20, "use serial create_info_df (val)")
             assert caplog.record_tuples[-3] == ('root', 20, "use serial create_info_df (test)")
@@ -77,23 +76,23 @@ class TestPreProcessing:
         caplog.set_level(logging.DEBUG)
         obj_with_exp_setup.data_store.set("use_all_stations_on_all_data_sets", False, "general")
         obj_with_exp_setup.create_set_split(slice(0, 2), "awesome")
-        assert ('root', 10, "Awesome stations (len=2): ['DEBW107', 'DEBY081']") in caplog.record_tuples
+        assert ('root', 10, "Awesome stations (len=1): ['DEBW107']") in caplog.record_tuples
         data_store = obj_with_exp_setup.data_store
         assert isinstance(data_store.get("data_collection", "general.awesome"), DataCollection)
         with pytest.raises(NameNotFoundInScope):
             data_store.get("data_collection", "general")
-        assert data_store.get("stations", "general.awesome") == ["DEBW107", "DEBY081"]
+        assert data_store.get("stations", "general.awesome") == ["DEBW107"]
 
     def test_create_set_split_all_stations(self, caplog, obj_with_exp_setup):
         caplog.set_level(logging.DEBUG)
         obj_with_exp_setup.create_set_split(slice(0, 2), "awesome")
-        message = "Awesome stations (len=5): ['DEBW107', 'DEBY081', 'DEBW013', 'DEBW087', 'DEBW99X']"
+        message = "Awesome stations (len=5): ['DEBW107', 'DEBW013', 'DEBW087', 'DEBW99X']"
         assert ('root', 10, message) in caplog.record_tuples
         data_store = obj_with_exp_setup.data_store
         assert isinstance(data_store.get("data_collection", "general.awesome"), DataCollection)
         with pytest.raises(NameNotFoundInScope):
             data_store.get("data_collection", "general")
-        assert data_store.get("stations", "general.awesome") == ['DEBW107', 'DEBY081', 'DEBW013',  'DEBW087']
+        assert data_store.get("stations", "general.awesome") == ['DEBW107', 'DEBW013',  'DEBW087']
 
     @pytest.mark.parametrize("name", (None, "tester"))
     def test_validate_station_serial(self, caplog, obj_with_exp_setup, name):
@@ -108,8 +107,8 @@ class TestPreProcessing:
         expected = "check valid stations started" + ' (%s)' % (name if name else 'all')
         assert caplog.record_tuples[0] == ('root', 20, expected)
         assert caplog.record_tuples[1] == ('root', 20, "use serial validate station approach")
-        assert caplog.record_tuples[-1] == ('root', 20, PyTestRegex(r'run for \d+:\d+:\d+ \(hh:mm:ss\) to check 5 '
-                                                                    r'station\(s\). Found 4/5 valid stations.'))
+        assert caplog.record_tuples[-1] == ('root', 20, PyTestRegex(r'run for \d+:\d+:\d+ \(hh:mm:ss\) to check 4 '
+                                                                    r'station\(s\). Found 3/4 valid stations.'))
 
     @mock.patch("psutil.cpu_count", return_value=3)
     @mock.patch("multiprocessing.Pool", return_value=multiprocessing.Pool(3))
@@ -126,8 +125,8 @@ class TestPreProcessing:
         assert caplog.record_tuples[0] == ('root', 20, "check valid stations started (all)")
         assert caplog.record_tuples[1] == ('root', 20, "use parallel validate station approach")
         assert caplog.record_tuples[2] == ('root', 20, "running 3 processes in parallel")
-        assert caplog.record_tuples[-1] == ('root', 20, PyTestRegex(r'run for \d+:\d+:\d+ \(hh:mm:ss\) to check 5 '
-                                                                    r'station\(s\). Found 4/5 valid stations.'))
+        assert caplog.record_tuples[-1] == ('root', 20, PyTestRegex(r'run for \d+:\d+:\d+ \(hh:mm:ss\) to check 4 '
+                                                                    r'station\(s\). Found 3/4 valid stations.'))
 
     def test_split_set_indices(self, obj_super_init):
         dummy_list = list(range(0, 15))