BUG: Fixed nlargest/smallest functionality for dataframes with MultiIndex columns (pandas-dev#23034)

Author: KristianHolsheimer

doc/source/whatsnew/v0.24.0.txt

@@ -1196,6 +1196,7 @@ Reshaping
 - Bug in :func:`merge_asof` when merging on float values within defined tolerance (:issue:`22981`)
 - Bug in :func:`pandas.concat` when concatenating a multicolumn DataFrame with tz-aware data against a DataFrame with a different number of columns (:issue`22796`)
 - Bug in :func:`merge_asof` where confusing error message raised when attempting to merge with missing values (:issue:`23189`)
+- Bug in :meth:`DataFrame.nsmallest` and :meth:`DataFrame.nlargest` for dataframes that have :class:`MultiIndex`ed columns (:issue:`23033`).
 
 .. _whatsnew_0240.bug_fixes.sparse:
 

pandas/core/algorithms.py

@@ -1161,7 +1161,7 @@ class SelectNFrame(SelectN):
 
     def __init__(self, obj, n, keep, columns):
         super(SelectNFrame, self).__init__(obj, n, keep)
-        if not is_list_like(columns):
+        if not is_list_like(columns) or isinstance(columns, tuple):
             columns = [columns]
         columns = list(columns)
         self.columns = columns

pandas/tests/frame/test_analytics.py

@@ -2153,7 +2153,7 @@ def test_n(self, df_strings, nselect_method, n, order):
             tm.assert_frame_equal(result, expected)
 
     @pytest.mark.parametrize('columns', [
-        ('group', 'category_string'), ('group', 'string')])
+        ['group', 'category_string'], ['group', 'string']])
     def test_n_error(self, df_main_dtypes, nselect_method, columns):
         df = df_main_dtypes
         col = columns[1]
@@ -2259,3 +2259,20 @@ def test_series_nat_conversion(self):
         df.rank()
         result = df
         tm.assert_frame_equal(result, expected)
+
+    def test_multiindex_column_lookup(self):
+        # Check whether tuples are correctly treated as multi-level lookups.
+        # GH 23033
+        df = pd.DataFrame(
+            columns=pd.MultiIndex.from_product([['x'], ['a', 'b']]),
+            data=[[0.33, 0.13], [0.86, 0.25], [0.25, 0.70], [0.85, 0.91]])
+
+        # nsmallest
+        result = df.nsmallest(3, ('x', 'a'))
+        expected = df.iloc[[2, 0, 3]]
+        tm.assert_frame_equal(result, expected)
+
+        # nlargest
+        result = df.nlargest(3, ('x', 'b'))
+        expected = df.iloc[[3, 2, 1]]
+        tm.assert_frame_equal(result, expected)