Skip to content

fix(histogram): add NULL handling for histogram #35693

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
rusackas merged 8 commits into from
Nov 14, 2025
Merged

fix(histogram): add NULL handling for histogram #35693

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
2f23078
fix(histogram): add NULL handling for histogram (#33738)
panrach Oct 4, 2025
ccef6c9
fix(histogram): remove unnecessary check
panrach Oct 5, 2025
50cfe80
move dropna so the non numeric check is not redundant
panrach Oct 5, 2025
49d7165
fix(histogram): add NULL handling for histogram (apache#33738)
panrach Oct 5, 2025
8e93aca
fix(histogram): add handling for empty df
panrach Oct 6, 2025
7e37e67
test(backend): add histogram tests
janani-gurram Oct 16, 2025
55b453f
fix(histogram): prevent creating new df
panrach Oct 17, 2025
af3615e
fix(histogram): create new df
janani-gurram Nov 13, 2025
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
5 changes: 5 additions & 0 deletions superset/utils/pandas_postprocessing/histogram.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,6 +48,11 @@ def histogram(
if groupby is None:
groupby = []

# drop empty values from the target column

Copilot AI Nov 13, 2025

Copy link

Choose a reason for hiding this comment

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

[nitpick] The comment says "drop empty values" but the code actually drops NULL/NaN values. Consider using more precise terminology: "Drop NULL values from the target column" to be clearer about what's being removed.

Suggested change
# drop empty values from the target column
# drop NULL/NaN values from the target column

Copilot uses AI. Check for mistakes.

@rusackas rusackas Nov 14, 2025

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Nice, but optional in my mind.

df = df.dropna(subset=[column])
if df.empty:
return df
Comment thread
janani-gurram marked this conversation as resolved.

# convert to numeric, coercing errors to NaN
df[column] = to_numeric(df[column], errors="coerce")

Expand Down
67 changes: 67 additions & 0 deletions tests/unit_tests/pandas_postprocessing/test_histogram.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,3 +140,70 @@ def test_histogram_with_some_non_numeric_values():
histogram(data_with_non_numeric, "a", ["group"], bins)
except ValueError as e:
assert str(e) == "Column 'group' contains non-numeric values" # noqa: PT017


def test_histogram_with_groupby_and_some_null_values():
data_with_groupby_and_some_nulls = DataFrame(
{
"group": ["A", "A", "B", "B", "A", "A", "B", "B", "A", "A"],
"a": [1, 2, 3, 4, 5, None, 7, 8, 9, 10],
"b": [1, 2, 3, 4, 5, None, 7, 8, 9, 10],
}
)

result = histogram(data_with_groupby_and_some_nulls, "a", ["group"], bins)
assert result.shape == (2, bins + 1)
assert result.columns.tolist() == [
"group",
"1.0 - 2.8",
"2.8 - 4.6",
"4.6 - 6.4",
"6.4 - 8.2",
"8.2 - 10.0",
]
assert result.values.tolist() == [["A", 2, 0, 1, 0, 2], ["B", 0, 2, 0, 2, 0]]


def test_histogram_with_no_groupby_and_some_null_values():
data_with_no_groupby_and_some_nulls = DataFrame(
{
"a": [1, 2, 3, 4, 5, None, 7, 8, 9, 10],
"b": [1, 2, 3, 4, 5, None, 7, 8, 9, 10],
}
)

result = histogram(data_with_no_groupby_and_some_nulls, "a", [], bins)
assert result.shape == (1, bins)
assert result.columns.tolist() == [
"1.0 - 2.8",
"2.8 - 4.6",
"4.6 - 6.4",
"6.4 - 8.2",
"8.2 - 10.0",
]
assert result.values.tolist() == [[2, 2, 1, 2, 2]]


def test_histogram_with_groupby_and_all_null_values():
data_with_groupby_and_all_nulls = DataFrame(
{
"group": ["A", "A", "B", "B", "A", "A", "B", "B", "A", "A"],
"a": [None, None, None, None, None, None, None, None, None, None],
"b": [None, None, None, None, None, None, None, None, None, None],
}
)

result = histogram(data_with_groupby_and_all_nulls, "a", ["group"], bins)
assert result.empty


def test_histogram_with_no_groupby_and_all_null_values():
data_with_no_groupby_and_all_nulls = DataFrame(
{
"a": [None, None, None, None, None, None, None, None, None, None],
"b": [None, None, None, None, None, None, None, None, None, None],
}
)

result = histogram(data_with_no_groupby_and_all_nulls, "a", [], bins)
assert result.empty
Loading