lint and full test

IndEcol · Oct 27, 2024 · 1543458 · 1543458
1 parent ca15a26
commit 1543458
Show file tree

Hide file tree

Showing 5 changed files with 41 additions and 25 deletions.
diff --git a/doc/source/notebooks/convert.py b/doc/source/notebooks/convert.py
@@ -389,11 +389,11 @@
 # %% [markdown]
 # The same principles as for individual tables can be used for converting full pymrio type Extensions (aka satellite accounts).
 # In difference to the single tables, pymrio Extensions consist of several pandas DataFrames which can be converted in one go.
-# Almost the same bridge table structure as for single tables can be used. The main additional information needed is in regard to 
+# Almost the same bridge table structure as for single tables can be used. The main additional information needed is in regard to
 # units. Since pymrio Extensions include a unit dataframe, information about the unit names need to be included.
 
 # %% [markdown]
-# Extensions can be converted either one at a time, but the main power of the method lies in collecting stressor data across different extensions 
+# Extensions can be converted either one at a time, but the main power of the method lies in collecting stressor data across different extensions
 # and converting them in one go.
 
 # %% [markdown]
@@ -417,7 +417,7 @@
 mrio.emissions.unit
 
 # %% [markdown]
-# We now setup a bridge table for converting/characterizing these emission data 
+# We now setup a bridge table for converting/characterizing these emission data
 # to several other accounts.
 
 # %%
@@ -471,4 +471,3 @@
 
 
 # CONT: test/explain characterization across different extensions
-
diff --git a/pymrio/core/mriosystem.py b/pymrio/core/mriosystem.py
@@ -2079,17 +2079,15 @@ def convert(
             unit = pd.DataFrame(columns=["unit"], index=new_extension.get_rows())
             bridge_columns = [col for col in df_map.columns if "__" in col]
             unique_new_index = (
-                df_map
-                .drop_duplicates(subset=bridge_columns)
+                df_map.drop_duplicates(subset=bridge_columns)
                 .loc[:, bridge_columns]
                 .set_index(bridge_columns)
                 .index
             )
             unique_new_index.names = [col.split("__")[0] for col in bridge_columns]
 
             unit.unit = (
-                df_map
-                .drop_duplicates(subset=bridge_columns)
+                df_map.drop_duplicates(subset=bridge_columns)
                 .set_index(bridge_columns)
                 .loc[unique_new_index]
                 .loc[:, unit_column_new]

diff --git a/pymrio/tools/ioutil.py b/pymrio/tools/ioutil.py
@@ -1099,7 +1099,7 @@ def convert(
 
     bridge_columns = [col for col in df_map.columns if "__" in col]
 
-    # groupby breaks with NaNs or None, fix it here 
+    # groupby breaks with NaNs or None, fix it here
     df_map.loc[:, bridge_columns] = df_map.loc[:, bridge_columns].fillna("")
 
     unique_new_index = (
@@ -1115,7 +1115,6 @@ def convert(
     if isinstance(df_orig, pd.Series):
         df_orig = pd.DataFrame(df_orig)
 
-
     # some consistency checks of arguments and restructuring if everything is ok
     if len(bridge_columns) == 0:
         raise ValueError("No columns with '__' in the mapping DataFrame")

diff --git a/tests/test_core.py b/tests/test_core.py
@@ -594,7 +594,8 @@ def test_extension_convert(fix_testmrio):
     )
 
     pdt.assert_series_equal(
-        tt_pre.emissions.D_cba.loc["emission_type1", "air"] * 2 + tt_pre.emissions.D_cba.loc["emission_type2", "water"] * 10,
+        tt_pre.emissions.D_cba.loc["emission_type1", "air"] * 2
+        + tt_pre.emissions.D_cba.loc["emission_type2", "water"] * 10,
         tt_pre.pre_calc.D_cba.loc["char_emissions"],
         check_names=False,
     )
@@ -635,7 +636,8 @@ def test_extension_convert(fix_testmrio):
     )
 
     pdt.assert_series_equal(
-        tt_post.emissions.D_cba.loc["emission_type1", "air"] * 2 + tt_post.emissions.D_cba.loc["emission_type2", "water"] * 10,
+        tt_post.emissions.D_cba.loc["emission_type1", "air"] * 2
+        + tt_post.emissions.D_cba.loc["emission_type2", "water"] * 10,
         tt_post.post_calc.D_cba.loc["char_emissions"],
         check_names=False,
     )
@@ -750,7 +752,11 @@ def test_extension_convert_function(fix_testmrio):
 
     df_map_add_across_wrong_name = df_map_add_across.copy()
 
-    df_map_add_across_wrong_name.loc[:, "extension"] = df_map_add_across_wrong_name.extension.str.replace("emissions_new_pre_calc", "foo")
+    df_map_add_across_wrong_name.loc[
+        :, "extension"
+    ] = df_map_add_across_wrong_name.extension.str.replace(
+        "emissions_new_pre_calc", "foo"
+    )
 
     ext_across_correct = pymrio.extension_convert(
         tt_pre.emissions,
@@ -766,9 +772,15 @@ def test_extension_convert_function(fix_testmrio):
         new_extension_name="add_across",
     )
 
-    expected_df_correct_F = tt_pre.emissions.F.loc["emission_type2", :].iloc[0, :] + ext_double.F.loc[("water_emissions", "water")] * 1e-3
+    expected_df_correct_F = (
+        tt_pre.emissions.F.loc["emission_type2", :].iloc[0, :]
+        + ext_double.F.loc[("water_emissions", "water")] * 1e-3
+    )
     expected_df_wrong_F = tt_pre.emissions.F.loc["emission_type2", :].iloc[0, :]
-    expected_df_correct_F_Y = tt_pre.emissions.F_Y.loc["emission_type2", :].iloc[0, :] + ext_double.F_Y.loc[("water_emissions", "water")] * 1e-3
+    expected_df_correct_F_Y = (
+        tt_pre.emissions.F_Y.loc["emission_type2", :].iloc[0, :]
+        + ext_double.F_Y.loc[("water_emissions", "water")] * 1e-3
+    )
     expected_df_wrong_F_Y = tt_pre.emissions.F_Y.loc["emission_type2", :].iloc[0, :]
 
     pdt.assert_series_equal(
@@ -817,9 +829,18 @@ def test_extension_convert_function(fix_testmrio):
         new_extension_name="add_across",
     )
 
-    expected_df_D_cba = tt_post.emissions.D_cba.loc["emission_type2", :].iloc[0, :] + tt_post.add_across.D_cba.loc[("water_emissions", "water")] * 1e-3
-    expected_df_S = tt_post.emissions.S.loc["emission_type2", :].iloc[0, :] + tt_post.add_across.S.loc[("water_emissions", "water")] * 1e-3
-    expected_df_M = tt_post.emissions.M.loc["emission_type2", :].iloc[0, :] + tt_post.add_across.M.loc[("water_emissions", "water")] * 1e-3
+    expected_df_D_cba = (
+        tt_post.emissions.D_cba.loc["emission_type2", :].iloc[0, :]
+        + tt_post.add_across.D_cba.loc[("water_emissions", "water")] * 1e-3
+    )
+    expected_df_S = (
+        tt_post.emissions.S.loc["emission_type2", :].iloc[0, :]
+        + tt_post.add_across.S.loc[("water_emissions", "water")] * 1e-3
+    )
+    expected_df_M = (
+        tt_post.emissions.M.loc["emission_type2", :].iloc[0, :]
+        + tt_post.add_across.M.loc[("water_emissions", "water")] * 1e-3
+    )
 
     pdt.assert_series_equal(
         ext_test_all.D_cba.iloc[0],
@@ -838,7 +859,6 @@ def test_extension_convert_function(fix_testmrio):
     )
 
 
-
 def test_extension_convert_test_unit_fail(fix_testmrio):
     df_fail1 = pd.DataFrame(
         columns=[

diff --git a/tests/test_util.py b/tests/test_util.py
@@ -534,16 +534,18 @@ def test_convert_rename_spread_index():
         99,
     )
 
-
     # TEST WITH EMPTY INDEX
 
-
     rename_bridge_missing_string = pd.DataFrame(
         columns=["stressor", "flow__stressor", "class__stressor", "class2__stressor"],
         data=[
             ["em1", "emission1", "to_air", "to_air (unspecified)"],
             ["em2", "emission2", "to_air", "to_air (specified)"],
-            ["em3", "emission3", "to_water",],
+            [
+                "em3",
+                "emission3",
+                "to_water",
+            ],
         ],
     )
 
@@ -565,7 +567,6 @@ def test_convert_rename_spread_index():
         ],
     )
 
-
     renamed_missing_string = convert(to_char, rename_bridge_missing_string)
     renamed_missing_nan = convert(to_char, rename_bridge_missing_nan)
     renamed_missing_none = convert(to_char, rename_bridge_missing_none)
@@ -582,8 +583,6 @@ def test_convert_rename_spread_index():
     rename_bridge_indexed.index.names = ["flow", "class", "class2"]
     pdt.assert_index_equal(renamed_simple.index, rename_bridge_indexed.index)
 
-
-
     # TEST WITH RENAME IN MUTLIINDEX
 
     to_char_multi = pd.DataFrame(
@@ -908,6 +907,7 @@ def test_convert_characterize():
 
     # TODO: test case for multindex characterization on one of teh inner levels - does not work in the GLAM example
 
+
 def test_convert_wrong_inputs():
     to_char = pd.DataFrame(
         data=5,