8000 [PySpark] - Add `expr` function by mariotaddeucci · Pull Request #16468 · duckdb/duckdb · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
8000

[PySpark] - Add expr function #16468

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 2 commits into from
Mar 11, 2025
+49 −1
Merged

[PySpark] - Add expr function #16468

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9e10dd2
[PySpark] - Add expr function
mariotaddeucci Mar 1, 2025
8d5cab1
Fix unittest for pyspark expression function
mariotaddeucci Mar 3, 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
34 changes: 33 additions & 1 deletion tools/pythonpkg/duckdb/experimental/spark/sql/functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,8 @@
ConstantExpression,
Expression,
FunctionExpression,
LambdaExpression
LambdaExpression,
SQLExpression,
)
if TYPE_CHECKING:
from .dataframe import DataFrame
Expand Down Expand Up @@ -6056,6 +6057,37 @@ def instr(str: "ColumnOrName", substr: str) -> Column:
"""
return _invoke_function("instr", _to_column_expr(str), ConstantExpression(substr))

def expr(str: str) -> Column:
"""Parses the expression string into the column that it represents

.. versionadded:: 1.5.0

.. versionchanged:: 3.4.0
Supports Spark Connect.

Parameters
----------
str : str
expression defined in string.

Returns
-------
:class:`~pyspark.sql.Column`
column representing the expression.

Examples
--------
>>> df = spark.createDataFrame([["Alice"], ["Bob"]], ["name"])
>>> df.select("name", expr("length(name)")).show()
+-----+------------+
| name|length(name)|
+-----+------------+
|Alice| 5|
| Bob| 3|
+-----+------------+
"""
return Column(SQLExpression(str))

def broadcast(df: "DataFrame") -> "DataFrame":
"""
The broadcast function in Spark is used to optimize joins by broadcasting a smaller
Expand Down
16 changes: 16 additions & 0 deletions tools/pythonpkg/tests/fast/spark/test_spark_functions_expr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
import pytest
from spark_namespace.sql import functions as F
from spark_namespace.sql.types import Row

_ = pytest.importorskip("duckdb.experimental.spark")


class TestSparkFunctionsExpr(object):
def test_expr(self, spark):
df = spark.createDataFrame([["Alice"], ["Bob"]], ["name"])
res = df.select("name", F.expr("length(name)").alias("str_len")).collect()

assert res == [
Row(name="Alice", str_len=5),
Row(name="Bob", str_len=3),
]
Loading
0