Skip to content

feat: float support for range functions #962

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

Open
alfredzimmer wants to merge 3 commits into
base: main
Choose a base branch
from
Open

feat: float support for range functions #962

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0a73f53
feat: float support for range functions
alfredzimmer Dec 5, 2025
75b3115
Merge branch 'main' into 937-feature-add-float-is_in_range
mwojtyczka Dec 8, 2025
9de2e52
Merge branch 'main' into 937-feature-add-float-is_in_range
mwojtyczka Dec 9, 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
8 changes: 4 additions & 4 deletions src/databricks/labs/dqx/check_funcs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -611,8 +611,8 @@ def is_not_greater_than(
@register_rule("row")
def is_in_range(
column: str | Column,
min_limit: int | datetime.date | datetime.datetime | str | Column | None = None,
max_limit: int | datetime.date | datetime.datetime | str | Column | None = None,
min_limit: int | float | datetime.date | datetime.datetime | str | Column | None = None,
max_limit: int | float | datetime.date | datetime.datetime | str | Column | None = None,
) -> Column:
"""Checks whether the values in the input column are in the provided limits (inclusive of both boundaries).

Expand Down Expand Up @@ -649,8 +649,8 @@ def is_in_range(
@register_rule("row")
def is_not_in_range(
column: str | Column,
min_limit: int | datetime.date | datetime.datetime | str | Column | None = None,
max_limit: int | datetime.date | datetime.datetime | str | Column | None = None,
min_limit: int | float | datetime.date | datetime.datetime | str | Column | None = None,
max_limit: int | float | datetime.date | datetime.datetime | str | Column | None = None,
) -> Column:
"""Checks whether the values in the input column are outside the provided limits (inclusive of both boundaries).

Expand Down
54 changes: 34 additions & 20 deletions tests/integration/test_row_checks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -804,15 +804,15 @@ def test_col_is_not_greater_than(spark, set_utc_timezone):


def test_col_is_in_range(spark, set_utc_timezone):
schema_num = "a: int, b: date, c: timestamp, d: int, e: int, f: int, g: decimal(10,2), h: map<string, int>"
schema_num = "a: int, b: date, c: timestamp, d: int, e: int, f: int, g: decimal(10,2), h: map<string, int>, i:float"
test_df = spark.createDataFrame(
[
[0, datetime(2024, 12, 1).date(), datetime(2024, 12, 1), -1, 5, 6, Decimal("2.00"), {"val": 0}],
[1, datetime(2025, 1, 1).date(), datetime(2025, 1, 1), 2, 6, 3, Decimal("1.00"), {"val": 1}],
[2, datetime(2025, 2, 1).date(), datetime(2025, 2, 1), 2, 7, 3, Decimal("3.00"), {"val": 2}],
[3, datetime(2025, 3, 1).date(), datetime(2025, 3, 1), 3, 8, 3, Decimal("1.01"), {"val": 3}],
[4, datetime(2025, 4, 1).date(), datetime(2025, 4, 1), 2, 9, 3, Decimal("3.01"), {"val": 4}],
[None, None, None, None, None, None, None, {"val": None}],
[0, datetime(2024, 12, 1).date(), datetime(2024, 12, 1), -1, 5, 6, Decimal("2.00"), {"val": 0}, 0.0],
[1, datetime(2025, 1, 1).date(), datetime(2025, 1, 1), 2, 6, 3, Decimal("1.00"), {"val": 1}, 0.2],
[2, datetime(2025, 2, 1).date(), datetime(2025, 2, 1), 2, 7, 3, Decimal("3.00"), {"val": 2}, 0.4],
[3, datetime(2025, 3, 1).date(), datetime(2025, 3, 1), 3, 8, 3, Decimal("1.01"), {"val": 3}, 0.6],
[4, datetime(2025, 4, 1).date(), datetime(2025, 4, 1), 2, 9, 3, Decimal("3.01"), {"val": 4}, 0.8],
[None, None, None, None, None, None, None, {"val": None}, None],
],
schema_num,
)
Expand All @@ -827,12 +827,13 @@ def test_col_is_in_range(spark, set_utc_timezone):
is_in_range("f", "a", 5),
is_in_range("g", 1, 3),
is_in_range(F.col("h").getItem("val"), 1, 3),
is_in_range("i", 0.1, 0.7),
)

checked_schema = (
"a_not_in_range: string, b_not_in_range: string, c_not_in_range: string, "
"d_not_in_range: string, f_not_in_range: string, g_not_in_range: string, "
"unresolvedextractvalue_h_val_not_in_range: string"
"unresolvedextractvalue_h_val_not_in_range: string, i_not_in_range: string"
)
expected = spark.createDataFrame(
[
Expand All @@ -844,10 +845,11 @@ def test_col_is_in_range(spark, set_utc_timezone):
"Value '6' in Column 'f' not in range: [0, 5]",
None,
"Value '0' in Column 'UnresolvedExtractValue(h, val)' not in range: [1, 3]",
"Value '0.0' in Column 'i' not in range: [0.1, 0.7]",
],
[None, None, None, None, None, None, None],
[None, None, None, None, None, None, None],
[None, None, None, None, None, None, None],
[None, None, None, None, None, None, None, None],
[None, None, None, None, None, None, None, None],
[None, None, None, None, None, None, None, None],
[
"Value '4' in Column 'a' not in range: [1, 3]",
"Value '2025-04-01' in Column 'b' not in range: [2025-01-01, 2025-03-01]",
Expand All @@ -856,8 +858,9 @@ def test_col_is_in_range(spark, set_utc_timezone):
"Value '3' in Column 'f' not in range: [4, 5]",
"Value '3.01' in Column 'g' not in range: [1, 3]",
"Value '4' in Column 'UnresolvedExtractValue(h, val)' not in range: [1, 3]",
"Value '0.8' in Column 'i' not in range: [0.1, 0.7]",
],
[None, None, None, None, None, None, None],
[None, None, None, None, None, None, None, None],
],
checked_schema,
)
Expand All @@ -866,13 +869,21 @@ def test_col_is_in_range(spark, set_utc_timezone):


def test_col_is_not_in_range(spark, set_utc_timezone):
schema_num = "a: int, b: date, c: timestamp, d: timestamp, e: decimal(10,2), f: array<int>"
schema_num = "a: int, b: date, c: timestamp, d: timestamp, e: decimal(10,2), f: array<int>, g: float"
test_df = spark.createDataFrame(
[
[0, datetime(2024, 12, 31).date(), datetime(2025, 1, 4), datetime(2025, 1, 7), Decimal("0.99"), [0, 1]],
[1, datetime(2025, 1, 1).date(), datetime(2025, 1, 3), datetime(2025, 1, 1), Decimal("1.00"), [1, 2]],
[3, datetime(2025, 2, 1).date(), datetime(2025, 2, 1), datetime(2025, 2, 3), Decimal("3.00"), [3, 4]],
[None, None, None, None, None, [None, 1]],
[
0,
datetime(2024, 12, 31).date(),
datetime(2025, 1, 4),
datetime(2025, 1, 7),
Decimal("0.99"),
[0, 1],
0.0,
],
[1, datetime(2025, 1, 1).date(), datetime(2025, 1, 3), datetime(2025, 1, 1), Decimal("1.00"), [1, 2], 0.3],
[3, datetime(2025, 2, 1).date(), datetime(2025, 2, 1), datetime(2025, 2, 3), Decimal("3.00"), [3, 4], 0.6],
[None, None, None, None, None, [None, 1], None],
],
schema_num,
)
Expand All @@ -886,22 +897,24 @@ def test_col_is_not_in_range(spark, set_utc_timezone):
is_not_in_range("d", "c", F.expr("cast(b as timestamp) + INTERVAL 2 DAY")),
is_not_in_range("e", 1, 3),
is_not_in_range(F.try_element_at("f", F.lit(1)), 1, 3),
is_not_in_range("g", 0.2, 0.5),
)

checked_schema = (
"a_in_range: string, b_in_range: string, c_in_range: string, d_in_range: string, e_in_range: string, "
"try_element_at_f_1_in_range: string"
"try_element_at_f_1_in_range: string, g_in_range: string"
)
expected = spark.createDataFrame(
[
[None, None, None, None, None, None],
[None, None, None, None, None, None, None],
[
"Value '1' in Column 'a' in range: [1, 3]",
"Value '2025-01-01' in Column 'b' in range: [2025-01-01, 2025-01-03]",
"Value '2025-01-03 00:00:00' in Column 'c' in range: [2025-01-01 00:00:00, 2025-01-03 00:00:00]",
None,
"Value '1.00' in Column 'e' in range: [1, 3]",
"Value '1' in Column 'try_element_at(f, 1)' in range: [1, 3]",
"Value '0.3' in Column 'g' in range: [0.2, 0.5]",
],
[
"Value '3' in Column 'a' in range: [1, 3]",
Expand All @@ -910,8 +923,9 @@ def test_col_is_not_in_range(spark, set_utc_timezone):
"Value '2025-02-03 00:00:00' in Column 'd' in range: [2025-02-01 00:00:00, 2025-02-03 00:00:00]",
"Value '3.00' in Column 'e' in range: [1, 3]",
"Value '3' in Column 'try_element_at(f, 1)' in range: [1, 3]",
None,
],
[None, None, None, None, None, None],
[None, None, None, None, None, None, None],
],
checked_schema,
)
Expand Down
23 changes: 23 additions & 0 deletions tests/unit/test_checks_validation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -433,3 +433,26 @@ def test_argument_type_list_mismatch_args():
"Item 1 in argument 'columns' should be of type 'str | pyspark.sql.column.Column' "
"for function 'is_unique' in the 'arguments' block" in str(status)
)


def test_is_in_range_float_arguments():
checks = [
{
"criticality": "warn",
"check": {"function": "is_in_range", "arguments": {"column": "a", "min_limit": 1.5, "max_limit": 2.5}},
},
{
"criticality": "warn",
"check": {"function": "is_in_range", "arguments": {"column": "b", "min_limit": 0.1, "max_limit": 0.9}},
},
{
"criticality": "warn",
"check": {"function": "is_not_in_range", "arguments": {"column": "c", "min_limit": 1.5, "max_limit": 2.5}},
},
{
"criticality": "warn",
"check": {"function": "is_not_in_range", "arguments": {"column": "c", "min_limit": 0.1, "max_limit": 0.9}},
},
]
status = DQEngine.validate_checks(checks)
assert not status.has_errors