Merge branch 'pyjanitor-devs:dev' into ci/testing-env

Author: Zeroto521

CHANGELOG.md

@@ -18,7 +18,7 @@
 -   [BUG] Force `math.softmax` returning `Series`. PR #1139 @Zeroto521
 -   [INF] Set independent environment for building documentation. PR #1141 @Zeroto521
 -   [DOC] Add local documentation preview via github action artifact. PR #1149 @Zeroto521
--   [ENH] Enabel `encode_categorical` handle 2 (or more ) dimensions array. PR #1153 @Zeroto521
+-   [ENH] Enable `encode_categorical` handle 2 (or more ) dimensions array. PR #1153 @Zeroto521
 
 ## [v0.23.1] - 2022-05-03
 

tests/functions/test_pivot_longer.py

@@ -663,8 +663,9 @@ def test_names_pattern_str(test_df):
         column_names="*_*",
         names_to=["set", ".value"],
         names_pattern="(.+)_(.+)",
-        sort_by_appearance=True,
+        sort_by_appearance=False,
     )
+    result = result.sort_values(result.columns.tolist(), ignore_index=True)
 
     actual = test_df.copy()
     actual.columns = actual.columns.str.split("_").str[::-1].str.join("_")
@@ -680,6 +681,7 @@ def test_names_pattern_str(test_df):
         .reset_index("set")
         .reset_index(drop=True)
     )
+    actual = actual.sort_values(actual.columns.tolist(), ignore_index=True)
 
     assert_frame_equal(result, actual)
 
@@ -706,6 +708,9 @@ def test_names_sep(test_df):
         .reset_index(drop=True)
     )
 
+    result = result.sort_values(result.columns.tolist(), ignore_index=True)
+    actual = actual.sort_values(actual.columns.tolist(), ignore_index=True)
+
     assert_frame_equal(result, actual)
 
 
@@ -1188,18 +1193,12 @@ def test_names_transform_numeric():
         }
     )
 
-    expected = (
-        df.pivot_longer(
-            index="A",
-            names_to=(".value", "colname"),
-            names_sep="_",
-            names_transform=float,
-        )
-        .sort_values(
-            ["A", "colname", "result", "treatment"], ignore_index=True
-        )
-        .loc[:, ["A", "colname", "result", "treatment"]]
-    )
+    result = df.pivot_longer(
+        index="A",
+        names_to=(".value", "colname"),
+        names_sep="_",
+        names_transform=float,
+    ).loc[:, ["A", "colname", "result", "treatment"]]
 
     actual = pd.wide_to_long(
         df,
@@ -1210,7 +1209,10 @@ def test_names_transform_numeric():
         sep="_",
     ).reset_index()
 
-    assert_frame_equal(actual, expected)
+    result = result.sort_values(result.columns.tolist(), ignore_index=True)
+    actual = actual.sort_values(actual.columns.tolist(), ignore_index=True)
+
+    assert_frame_equal(actual, result)
 
 
 def test_duplicated_columns():

tests/utils/test__select_column.py

@@ -5,7 +5,7 @@
 import pandas as pd
 import pytest
 
-from pandas.testing import assert_index_equal
+from pandas.testing import assert_index_equal, assert_frame_equal
 from janitor.functions.utils import _select_column_names, patterns
 
 
@@ -165,10 +165,10 @@ def test_strings_dates_range(df_dates):
 def test_unsorted_dates(df_dates):
     """Test output if the dates are unsorted, and a string is passed."""
     df_dates = df_dates.iloc[:, [10, 4, 7, 2, 1, 3, 5, 6, 8, 9, 11, 0]]
-    assert_index_equal(
-        df_dates.loc[:, ["2011-01-31"]].columns,
-        _select_column_names("2011-01-31", df_dates),
-    )
+    expected = df_dates.loc[:, ["2011-01-31"]]
+    actual = _select_column_names("2011-01-31", df_dates)
+    actual = df_dates.loc[:, actual]
+    assert_frame_equal(expected, actual)
 
 
 def test_regex(df1):