10000 BUG/PERF: groupby.transform with unobserved categories by undermyumbrella1 · Pull Request #58084 · pandas-dev/pandas · GitHub
[go: up one dir, main page]
Skip to content

BUG/PERF: groupby.transform with unobserved categories #58084

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 19 commits into from
May 8, 2024
+120 −19
Merged

BUG/PERF: groupby.transform with unobserved categories #58084

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
a52e7fe
Temporarily change observed=True, for groupby.transform
Apr 17, 2024
898fd12
Add tests
Apr 17, 2024
5311004
Add orig_obj in BaseGroupBy hidden attr
Apr 17, 2024
fb548ad
Update tests according to pr comments
Apr 17, 2024
baa1b28
Move orig_obj arg in constructor to last param, to account for possib…
Apr 17, 2024
30013ee
Move calculation of observed grouper to when initialising groupby
Apr 20, 2024
3b9d27b
Only calculate observed_grouper when grouper is absent to account to …
Apr 20, 2024
4221c34
Merge branch 'main' into fix/type_coercion_for_unobserved_categories
Apr 20, 2024
8588a1e
Remove observed exclusions
Apr 20, 2024
8e669d9
Add observed grouper/grouping as cached method
Apr 20, 2024
0d9f89d
change return type to grouping
Apr 20, 2024
84f83ae
Update rst docs
Apr 25, 2024
cbabce0
Update rst docs
Apr 25, 2024
bcca14f
Cache observed grouping/grouper instead of self obj
Apr 29, 2024
f3a3f63
Update according to pr comments
May 2, 2024
58e759f
Merge main
May 2, 2024
7f99b71
Revert unintentional changes
May 7, 2024
4364440
Revert unintentional changes
May 7, 2024
5d63405
Merge branch 'main' into fix/type_coercion_for_unobserved_categories
undermyumbrella1 May 7, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Update according to pr comments
  • Loading branch information
Kei committed May 2, 2024
commit f3a3f639051de04bd3ab3df9d09253923cde923d
1 change: 0 additions & 1 deletion pandas/core/generic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2044,7 +2044,6 @@ def __setstate__(self, state) -> None:
object.__setattr__(self, "_attrs", attrs)
flags = state.get("_flags", {"allows_duplicate_labels": True})
object.__setattr__(self, "_flags", Flags(self, **flags))

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you revert this line removal. Shouldn't have any diff in this file.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

resolved

# set in the order of internal names
# to avoid definitional recursion
# e.g. say fill_value needing _mgr to be
Expand Down
119 changes: 8 additions & 111 deletions pandas/tests/groupby/transform/test_transform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1537,128 +1537,25 @@ def test_transform_sum_one_column_with_matching_labels_and_missing_labels():
tm.assert_frame_equal(result, expected)


# GH#58084
def test_min_one_unobserved_category_no_type_coercion():
@pytest.mark.parametrize("dtype", ["int32", "float32"])
def test_min_one_unobserved_category_no_type_coercion(dtype):
# GH#58084
df = DataFrame({"A": Categorical([1, 1, 2], categories=[1, 2, 3]), "B": [3, 4, 5]})
df["B"] = df["B"].astype("int32")
df["B"] = df["B"].astype(dtype)
gb = df.groupby("A", observed=False)
result = gb.transform("min")

expected = DataFrame({"B": [3, 3, 5]}, dtype="int32")
expected = DataFrame({"B": [3, 3, 5]}, dtype=dtype)
tm.assert_frame_equal(expected, result)


# GH#58084
def test_min_multiple_unobserved_categories_no_type_coercion():
df = DataFrame(
{
"X": Categorical(
["432945", "randomcat", -4325466, "randomcat", -4325466, -4325466],
categories=[
1,
"randomcat",
100,
333,
"cat43543",
-4325466,
54665,
-546767,
"432945",
767076,
],
),
"Y": [0, 940645, np.iinfo(np.int64).min, 9449, 100044444, 40],
}
)
df["Y"] = df["Y"].astype("int64")

gb = df.groupby("X", observed=False)
result = gb.transform("min")

expected = DataFrame(
{
"Y": [
0,
9449,
np.iinfo(np.int64).min,
9449,
np.iinfo(np.int64).min,
np.iinfo(np.int64).min,
]
},
dtype="int64",
)
tm.assert_frame_equal(expected, result)


# GH#58084
def test_min_float32_multiple_unobserved_categories_no_type_coercion():
df = DataFrame(
{
"X": Categorical(
["cat43543", -4325466, 54665, "cat43543", -4325466, 54665],
categories=[
1,
"randomcat",
100,
333,
"cat43543",
-4325466,
54665,
-546767,
"432945",
767076,
],
),
"Y": [
0.3940429,
940645.49,
np.finfo(np.float32).min,
9449.03333,
100044444.403294,
40.3020909,
],
}
)
df["Y"] = df["Y"].astype("float32")

gb = df.groupby("X", observed=False)
result = gb.transform("min")

expected = DataFrame(
{
"Y": [
0.3940429,
940645.49,
np.finfo(np.float32).min,
0.3940429,
940645.49,
np.finfo(np.float32).min,
]
},
dtype="float32",
)
tm.assert_frame_equal(expected, result)


# GH#58084
def test_min_all_empty_data_no_type_coercion():
# GH#58084
df = DataFrame(
{
"X": Categorical(
[],
categories=[
1,
"randomcat",
100,
333,
"cat43543",
-4325466,
54665,
-546767,
"432945",
767076,
],
categories=[1, "randomcat", 100],
),
"Y": [],
}
Expand All @@ -1672,8 +1569,8 @@ def test_min_all_empty_data_no_type_coercion():
tm.assert_frame_equal(expected, result)


# GH#58084
def test_min_one_dim_no_type_coercion():
# GH#58084
df = DataFrame({"Y": [9435, -5465765, 5055, 0, 954960]})
df["Y"] = df["Y"].astype("int32")
categories = Categorical([1, 2, 2, 5, 1], categories=[1, 2, 3, 4, 5])
Expand Down
0