new method sort_like to ensure ordering when extracting meteo and chem variables

mlair/data_handler/data_handler_mixed_sampling.py

@@ -7,7 +7,7 @@ from mlair.data_handler.data_handler_with_filter import DataHandlerFirFilterSing
 from mlair.data_handler.data_handler_with_filter import DataHandlerClimateFirFilter, DataHandlerFirFilter
 from mlair.data_handler import DefaultDataHandler
 from mlair import helpers
-from mlair.helpers import to_list
+from mlair.helpers import to_list, sort_like
 from mlair.configuration.defaults import DEFAULT_SAMPLING, DEFAULT_INTERPOLATION_LIMIT, DEFAULT_INTERPOLATION_METHOD
 from mlair.helpers.filter import filter_width_kzf
 
@@ -340,7 +340,7 @@ class DataHandlerMixedSamplingWithClimateAndFirFilter(DataHandlerMixedSamplingWi
         chem_vars = cls.data_handler_climate_fir.chem_vars
         chem = set(variables).intersection(chem_vars)
         meteo = set(variables).difference(chem_vars)
-        return to_list(chem), to_list(meteo)
+        return sort_like(to_list(chem), variables), sort_like(to_list(meteo), variables)
 
     @classmethod
     def build(cls, station: str, **kwargs):

mlair/helpers/__init__.py

@@ -3,4 +3,4 @@
 from .testing import PyTestRegex, PyTestAllEqual
 from .time_tracking import TimeTracking, TimeTrackingWrapper
 from .logger import Logger
-from .helpers import remove_items, float_round, dict_to_xarray, to_list, extract_value, select_from_dict, make_keras_pickable
+from .helpers import remove_items, float_round, dict_to_xarray, to_list, extract_value, select_from_dict, make_keras_pickable, sort_like

mlair/helpers/helpers.py

@@ -64,6 +64,23 @@ def to_list(obj: Any) -> List:
     return obj
 
 
+def sort_like(list_obj: list, sorted_obj: list):
+    """
+    Sort elements of list_obj as ordered in sorted_obj. Length of sorted_obj as allowed to be higher than length of
+    list_obj, but must contain at least all objects of list_obj. Will raise AssertionError, if not all elements of
+    list_obj are also in sorted_obj. Also it is required for list_obj and sorted_obj to have only unique elements.
+
+    :param list_obj: list to sort
+    :param sorted_obj: list to use ordering from
+
+    :return: sorted list
+    """
+    assert set(list_obj).issubset(sorted_obj)
+    assert len(set(list_obj)) == len(list_obj)
+    assert len(set(sorted_obj)) == len(sorted_obj)
+    return [e for e in sorted_obj if e in list_obj]
+
+
 def dict_to_xarray(d: Dict, coordinate_name: str) -> xr.DataArray:
     """
     Convert a dictionary of 2D-xarrays to single 3D-xarray. The name of new coordinate axis follows <coordinate_name>.

test/test_helpers/test_helpers.py

@@ -12,7 +12,7 @@ import mock
 import pytest
 import string
 
-from mlair.helpers import to_list, dict_to_xarray, float_round, remove_items, extract_value, select_from_dict
+from mlair.helpers import to_list, dict_to_xarray, float_round, remove_items, extract_value, select_from_dict, sort_like
 from mlair.helpers import PyTestRegex
 from mlair.helpers import Logger, TimeTracking
 from mlair.helpers.helpers import is_xarray, convert2xrda
@@ -432,3 +432,25 @@ class TestConvert2xrDa:
                e.value.args[0]
         assert "`use_1d_default=True' is used with `arr' of type da.array. For da.arrays please pass" + \
                " `use_1d_default=False' and specify keywords for xr.DataArray via kwargs." in e.value.args[0]
+
+
+class TestSortLike:
+
+    def test_sort_like(self):
+        l_obj = [1, 2, 3, 8, 4]
+        res = sort_like(l_obj, [1, 2, 3, 4, 5, 6, 7, 8])
+        assert res == [1, 2, 3, 4, 8]
+        assert l_obj == [1, 2, 3, 8, 4]
+
+    def test_sort_like_not_unique(self):
+        l_obj = [1, 2, 3, 8, 4, 3]
+        with pytest.raises(AssertionError) as e:
+            sort_like(l_obj, [1, 2, 3, 4, 5, 6, 7, 8])
+        l_obj = [1, 2, 3, 8, 4]
+        with pytest.raises(AssertionError) as e:
+            sort_like(l_obj, [1, 2, 3, 4, 5, 6, 7, 8, 5])
+
+    def test_sort_like_missing_element(self):
+        l_obj = [1, 2, 3, 8, 4]
+        with pytest.raises(AssertionError) as e:
+            sort_like(l_obj, [1, 2, 3, 5, 6, 7, 8])