Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings
This repository was archived by the owner on May 7, 2026. It is now read-only.

Commit 5c43efb

Browse filesBrowse files
tswasttswast
authored
feat: Add bigframes.bigquery.rand() function (#2501)
This change adds `bigframes.bigquery.rand()` which wraps the BigQuery `RAND()` function. It includes a warning about non-determinism in the docstring. Additionally, `SqlScalarOp` has been updated to accept an `is_deterministic` argument, which is set to `False` for `rand()`. Fixes customer request for this function. 🦕 Co-authored-by: tswast <247555+tswast@users.noreply.github.com>
1 parent ce686c1 commit 5c43efb
Copy full SHA for 5c43efb

5 files changed

+133Lines changed: 133 additions & 0 deletions

File tree

Expand file treeCollapse file tree
Open diff view settings
Filter options
Expand file treeCollapse file tree
Open diff view settings
Collapse file

‎bigframes/bigquery/__init__.py‎

Copy file name to clipboardExpand all lines: bigframes/bigquery/__init__.py
+5Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -58,6 +58,7 @@
5858
to_json,
5959
to_json_string,
6060
)
61+
from bigframes.bigquery._operations.mathematical import rand
6162
from bigframes.bigquery._operations.search import create_vector_index, vector_search
6263
from bigframes.bigquery._operations.sql import sql_scalar
6364
from bigframes.bigquery._operations.struct import struct
@@ -99,6 +100,8 @@
99100
parse_json,
100101
to_json,
101102
to_json_string,
103+
# mathematical ops
104+
rand,
102105
# search ops
103106
create_vector_index,
104107
vector_search,
@@ -154,6 +157,8 @@
154157
"parse_json",
155158
"to_json",
156159
"to_json_string",
160+
# mathematical ops
161+
"rand",
157162
# search ops
158163
"create_vector_index",
159164
"vector_search",
Collapse file

‎bigframes/bigquery/_operations/mathematical.py‎

Copy file name to clipboard
+53Lines changed: 53 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,53 @@
1+
# Copyright 2025 Google LLC
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
from __future__ import annotations
16+
17+
from bigframes import dtypes
18+
from bigframes import operations as ops
19+
import bigframes.core.col
20+
import bigframes.core.expression
21+
22+
23+
def rand() -> bigframes.core.col.Expression:
24+
"""
25+
Generates a pseudo-random value of type FLOAT64 in the range of [0, 1),
26+
inclusive of 0 and exclusive of 1.
27+
28+
.. warning::
29+
This method introduces non-determinism to the expression. Reading the
30+
same column twice may result in different results. The value might
31+
change. Do not use this value or any value derived from it as a join
32+
key.
33+
34+
**Examples:**
35+
36+
>>> import bigframes.pandas as bpd
37+
>>> import bigframes.bigquery as bbq
38+
>>> df = bpd.DataFrame({"a": [1, 2, 3]})
39+
>>> df['random'] = bbq.rand()
40+
>>> # Resulting column 'random' will contain random floats between 0 and 1.
41+
42+
Returns:
43+
bigframes.pandas.api.typing.Expression:
44+
An expression that can be used in
45+
:func:`~bigframes.pandas.DataFrame.assign` and other methods. See
46+
:func:`bigframes.pandas.col`.
47+
"""
48+
op = ops.SqlScalarOp(
49+
_output_type=dtypes.FLOAT_DTYPE,
50+
sql_template="RAND()",
51+
is_deterministic=False,
52+
)
53+
return bigframes.core.col.Expression(bigframes.core.expression.OpExpression(op, ()))
Collapse file

‎bigframes/operations/generic_ops.py‎

Copy file name to clipboardExpand all lines: bigframes/operations/generic_ops.py
+5Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -443,10 +443,15 @@ class SqlScalarOp(base_ops.NaryOp):
443443
name: typing.ClassVar[str] = "sql_scalar"
444444
_output_type: dtypes.ExpressionType
445445
sql_template: str
446+
is_deterministic: bool = True
446447

447448
def output_type(self, *input_types: dtypes.ExpressionType) -> dtypes.ExpressionType:
448449
return self._output_type
449450

451+
@property
452+
def deterministic(self) -> bool:
453+
return self.is_deterministic
454+
450455

451456
@dataclasses.dataclass(frozen=True)
452457
class PyUdfOp(base_ops.NaryOp):
Collapse file

‎tests/system/small/bigquery/test_mathematical.py‎

Copy file name to clipboard
+37Lines changed: 37 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,37 @@
1+
# Copyright 2025 Google LLC
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
import bigframes.bigquery as bbq
16+
17+
18+
def test_rand(scalars_df_index):
19+
df = scalars_df_index
20+
21+
# Apply rand
22+
df = df.assign(random=bbq.rand())
23+
result = df["random"]
24+
25+
# Eagerly evaluate
26+
result_pd = result.to_pandas()
27+
28+
# Check length
29+
assert len(result_pd) == len(df)
30+
31+
# Check values in [0, 1)
32+
assert (result_pd >= 0).all()
33+
assert (result_pd < 1).all()
34+
35+
# Check not all values are equal (unlikely collision for random)
36+
if len(result_pd) > 1:
37+
assert result_pd.nunique() > 1
Collapse file

‎tests/unit/bigquery/test_mathematical.py‎

Copy file name to clipboard
+33Lines changed: 33 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,33 @@
1+
# Copyright 2025 Google LLC
2+
#
3+
# Licensed under the Apache License, Version 2.0 (the "License");
4+
# you may not use this file except in compliance with the License.
5+
# You may obtain a copy of the License at
6+
#
7+
# http://www.apache.org/licenses/LICENSE-2.0
8+
#
9+
# Unless required by applicable law or agreed to in writing, software
10+
# distributed under the License is distributed on an "AS IS" BASIS,
11+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12+
# See the License for the specific language governing permissions and
13+
# limitations under the License.
14+
15+
import bigframes.bigquery as bbq
16+
import bigframes.core.col as col
17+
import bigframes.core.expression as ex
18+
import bigframes.dtypes as dtypes
19+
import bigframes.operations as ops
20+
21+
22+
def test_rand_returns_expression():
23+
expr = bbq.rand()
24+
25+
assert isinstance(expr, col.Expression)
26+
node = expr._value
27+
assert isinstance(node, ex.OpExpression)
28+
op = node.op
29+
assert isinstance(op, ops.SqlScalarOp)
30+
assert op.sql_template == "RAND()"
31+
assert op._output_type == dtypes.FLOAT_DTYPE
32+
assert not op.is_deterministic
33+
assert len(node.inputs) == 0

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.