fixed formatting

pandas-dev · gsmll · Apr 3, 2025 · Apr 3, 2025 · Apr 3, 2025 · Apr 3, 2025
commit 7a8fddb6656c73ff785303efd65c185c715829f5
diff --git a/pandas/core/reshape/reshape.py b/pandas/core/reshape/reshape.py
@@ -135,10 +135,10 @@ def __init__(
        if not self.sort:
            unique_codes = unique(self.index.codes[self.level])
            # Bug Fix GH 61221
-            # The -1 in the unsorted unique codes causes for doubling and an eventual ValueError
+            # The -1 in the unsorted unique codes causes for errors
            # saving the NA location to be used in the repeater
            self.na = np.where(unique_codes == -1)[0][0] if -1 in unique_codes else None
-            unique_codes = unique_codes[unique_codes != -1]  
+            unique_codes = unique_codes[unique_codes != -1]
            self.removed_level = self.removed_level.take(unique_codes)
            self.removed_level_full = self.removed_level_full.take(unique_codes)

@@ -395,13 +395,13 @@ def _repeater(self) -> np.ndarray:
            stride = len(self.removed_level) + self.lift
            if self.sort or not self.na:
                repeater = np.arange(stride) - self.lift
-            else :
-                #move the -1 to the position at self.na
+            else:
+                # move the -1 to the position at self.na
                repeater = np.arange(stride)
-                if(self.na):
+                if self.na:
                    repeater[self.na] = -1
-                    if(self.na + 1) < len(repeater):
-                        repeater[self.na + 1:] -= 1
+                    if (self.na + 1) < len(repeater):
+                        repeater[self.na + 1 :] -= 1

        return repeater

@@ -1065,7 +1065,7 @@ def stack_reshape(
            else:
                data.columns = default_index(len(data.columns))
        buf.append(data)
- 
+
    if len(buf) > 0 and not frame.empty:
        result = concat(buf, ignore_index=True)
    else:

diff --git a/pandas/tests/frame/test_stack_unstack.py b/pandas/tests/frame/test_stack_unstack.py
@@ -1610,79 +1610,105 @@ def assert_na_safe_equal(left, right):
    left = left.rename(columns={pd.NA: np.nan}, level=1)
    right = right.rename(columns={pd.NA: np.nan}, level=1)
    tm.assert_frame_equal(left, right, check_dtype=False)
-
+
+
 def test_unstack_sort_false_na():
    # GH 61221
-    levels1 = ['b','a']
-    levels2 = pd.Index([1, 2, 3, pd.NA], dtype=pd.Int64Dtype())
-    index = pd.MultiIndex.from_product([levels1, levels2], names=['level1', 'level2'])
-    df = pd.DataFrame(dict(value=range(len(index))), index=index)
-    result = df.unstack(level='level2', sort=False)
-    expected = pd.DataFrame(
-     {
-         ('value', 1): [0, 4],
-         ('value', 2): [1, 5],
-         ('value', 3): [2, 6],
-         ('value', pd.Int64Dtype().na_value): [3, 7]  
-     },
-     index=pd.Index(['b', 'a'], name='level1'),
-     columns=pd.MultiIndex.from_tuples([
-         ('value', 1), ('value', 2), ('value', 3), ('value', pd.Int64Dtype().na_value)
-     ], names=[None, 'level2'])
- )
+    levels1 = ["b", "a"]
+    levels2 = Index([1, 2, 3, pd.NA], dtype=pd.Int64Dtype())
+    index = MultiIndex.from_product([levels1, levels2], names=["level1", "level2"])
+    df = DataFrame({"value": range(len(index))}, index=index)
+    result = df.unstack(level="level2", sort=False)
+    expected = DataFrame(
+        {
+            ("value", 1): [0, 4],
+            ("value", 2): [1, 5],
+            ("value", 3): [2, 6],
+            ("value", pd.Int64Dtype().na_value): [3, 7],
+        },
+        index=Index(["b", "a"], name="level1"),
+        columns=MultiIndex.from_tuples(
+            [
+                ("value", 1),
+                ("value", 2),
+                ("value", 3),
+                ("value", pd.Int64Dtype().na_value),
+            ],
+            names=[None, "level2"],
+        ),
+    )
    assert_na_safe_equal(result, expected)
-    levels2 = pd.Index([pd.NA, 1, 2, 3], dtype=pd.Int64Dtype())
-    index = pd.MultiIndex.from_product([levels1, levels2], names=['level1', 'level2'])
-    df = pd.DataFrame(dict(value=range(len(index))), index=index)
-    result = df.unstack(level='level2', sort=False)
-    expected = pd.DataFrame(
-     {
-         ('value', pd.Int64Dtype().na_value): [0, 4],
-         ('value', 1): [1, 5],
-         ('value', 2): [2, 6],
-         ('value', 3): [3, 7]  # Use actual pd.NA object
-     },
-     index=pd.Index(['b', 'a'], name='level1'),
-     columns=pd.MultiIndex.from_tuples([
-         ('value', pd.Int64Dtype().na_value), ('value', 1), ('value', 2), ('value', 3)
-     ], names=[None, 'level2'])
- )
+    levels2 = Index([pd.NA, 1, 2, 3], dtype=pd.Int64Dtype())
+    index = MultiIndex.from_product([levels1, levels2], names=["level1", "level2"])
+    df = DataFrame({"value": range(len(index))}, index=index)
+    result = df.unstack(level="level2", sort=False)
+    expected = DataFrame(
+        {
+            ("value", pd.Int64Dtype().na_value): [0, 4],
+            ("value", 1): [1, 5],
+            ("value", 2): [2, 6],
+            ("value", 3): [3, 7],
+        },
+        index=Index(["b", "a"], name="level1"),
+        columns=MultiIndex.from_tuples(
+            [
+                ("value", pd.Int64Dtype().na_value),
+                ("value", 1),
+                ("value", 2),
+                ("value", 3),
+            ],
+            names=[None, "level2"],
+        ),
+    )
    assert_na_safe_equal(result, expected)
-    levels2 = pd.Index([ 1, pd.NA, 2, 3], dtype=pd.Int64Dtype())
-    index = pd.MultiIndex.from_product([levels1, levels2], names=['level1', 'level2'])
-    df = pd.DataFrame(dict(value=range(len(index))), index=index)
-    result = df.unstack(level='level2', sort=False)
-    expected = pd.DataFrame(
-     {
-         ('value', 1): [0, 4],
-         ('value', pd.Int64Dtype().na_value): [1, 5],
-         ('value', 2): [2, 6],
-         ('value', 3): [3, 7]  # Use actual pd.NA object
-     },
-     index=pd.Index(['b', 'a'], name='level1'),
-     columns=pd.MultiIndex.from_tuples([
-         ('value', 1), ('value', pd.Int64Dtype().na_value), ('value', 2), ('value', 3)
-     ], names=[None, 'level2'])
- )
+    levels2 = Index([1, pd.NA, 2, 3], dtype=pd.Int64Dtype())
+    index = MultiIndex.from_product([levels1, levels2], names=["level1", "level2"])
+    df = DataFrame({"value": range(len(index))}, index=index)
+    result = df.unstack(level="level2", sort=False)
+    expected = DataFrame(
+        {
+            ("value", 1): [0, 4],
+            ("value", pd.Int64Dtype().na_value): [1, 5],
+            ("value", 2): [2, 6],
+            ("value", 3): [3, 7],
+        },
+        index=Index(["b", "a"], name="level1"),
+        columns=MultiIndex.from_tuples(
+            [
+                ("value", 1),
+                ("value", pd.Int64Dtype().na_value),
+                ("value", 2),
+                ("value", 3),
+            ],
+            names=[None, "level2"],
+        ),
+    )
    assert_na_safe_equal(result, expected)
-    levels2 = pd.Index([3, pd.NA, 1, 2], dtype=pd.Int64Dtype())
-    index = pd.MultiIndex.from_product([levels1, levels2], names=['level1', 'level2'])
-    df = pd.DataFrame(dict(value=range(len(index))), index=index)
-    result = df.unstack(level='level2', sort=False)
-    expected = pd.DataFrame(
-     {
-         ('value', 3): [0, 4],
-         ('value', pd.Int64Dtype().na_value): [1, 5],
-         ('value', 1): [2, 6],
-         ('value', 2): [3, 7]  # Use actual pd.NA object
-     },
-     index=pd.Index(['b', 'a'], name='level1'),
-     columns=pd.MultiIndex.from_tuples([
-         ('value', 3), ('value', pd.Int64Dtype().na_value), ('value', 1), ('value', 2)
-     ], names=[None, 'level2'])
- )
+    levels2 = Index([3, pd.NA, 1, 2], dtype=pd.Int64Dtype())
+    index = MultiIndex.from_product([levels1, levels2], names=["level1", "level2"])
+    df = DataFrame({"value": range(len(index))}, index=index)
+    result = df.unstack(level="level2", sort=False)
+    expected = DataFrame(
+        {
+            ("value", 3): [0, 4],
+            ("value", pd.Int64Dtype().na_value): [1, 5],
+            ("value", 1): [2, 6],
+            ("value", 2): [3, 7],  # Use actual pd.NA object
+        },
+        index=Index(["b", "a"], name="level1"),
+        columns=MultiIndex.from_tuples(
+            [
+                ("value", 3),
+                ("value", pd.Int64Dtype().na_value),
+                ("value", 1),
+                ("value", 2),
+            ],
+            names=[None, "level2"],
+        ),
+    )
    assert_na_safe_equal(result, expected)

+
 @pytest.mark.filterwarnings("ignore:The previous implementation of stack is deprecated")
 def test_stack_sort_false_multi_level(future_stack):
    # GH 15105