This is an automated email from the ASF dual-hosted git repository.
ruifengz pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new c0416713e8e1 [SPARK-53943][PYTHON][DOCS] Add examples for function
unwrap_udt
c0416713e8e1 is described below
commit c0416713e8e1e5fb81f218feb339cfbeacb61b72
Author: Ruifeng Zheng <[email protected]>
AuthorDate: Fri Oct 17 18:03:47 2025 +0800
[SPARK-53943][PYTHON][DOCS] Add examples for function unwrap_udt
### What changes were proposed in this pull request?
Add examples for function unwrap_udt
### Why are the changes needed?
to improve doc
### Does this PR introduce _any_ user-facing change?
yes, doc-only
### How was this patch tested?
doctests
### Was this patch authored or co-authored using generative AI tooling?
no
Closes #52647 from zhengruifeng/doc_unwrap_udt.
Authored-by: Ruifeng Zheng <[email protected]>
Signed-off-by: Ruifeng Zheng <[email protected]>
---
python/pyspark/sql/functions/builtin.py | 51 +++++++++++++++++++++++++++++++--
1 file changed, 48 insertions(+), 3 deletions(-)
diff --git a/python/pyspark/sql/functions/builtin.py
b/python/pyspark/sql/functions/builtin.py
index 85115f132d44..99fb7ee1ec5e 100644
--- a/python/pyspark/sql/functions/builtin.py
+++ b/python/pyspark/sql/functions/builtin.py
@@ -25765,9 +25765,54 @@ def unwrap_udt(col: "ColumnOrName") -> Column:
.. versionadded:: 3.4.0
- Notes
- -----
- Supports Spark Connect.
+ Parameters
+ ----------
+ col : :class:`~pyspark.sql.Column` or column name
+
+ Returns
+ -------
+ :class:`~pyspark.sql.Column`
+ The underlying representation.
+
+ Examples
+ --------
+ Example 1: Unwrap ML-specific UDT - VectorUDT
+
+ >>> from pyspark.sql import functions as sf
+ >>> from pyspark.ml.linalg import Vectors
+ >>> vec1 = Vectors.dense(1, 2, 3)
+ >>> vec2 = Vectors.sparse(4, {1: 1.0, 3: 5.5})
+ >>> df = spark.createDataFrame([(vec1,), (vec2,)], ["vec"])
+ >>> df.select(sf.unwrap_udt("vec")).printSchema()
+ root
+ |-- unwrap_udt(vec): struct (nullable = true)
+ | |-- type: byte (nullable = false)
+ | |-- size: integer (nullable = true)
+ | |-- indices: array (nullable = true)
+ | | |-- element: integer (containsNull = false)
+ | |-- values: array (nullable = true)
+ | | |-- element: double (containsNull = false)
+
+ Example 2: Unwrap ML-specific UDT - MatrixUDT
+
+ >>> from pyspark.sql import functions as sf
+ >>> from pyspark.ml.linalg import Matrices
+ >>> mat1 = Matrices.dense(2, 2, range(4))
+ >>> mat2 = Matrices.sparse(2, 2, [0, 2, 3], [0, 1, 1], [2, 3, 4])
+ >>> df = spark.createDataFrame([(mat1,), (mat2,)], ["mat"])
+ >>> df.select(sf.unwrap_udt("mat")).printSchema()
+ root
+ |-- unwrap_udt(mat): struct (nullable = true)
+ | |-- type: byte (nullable = false)
+ | |-- numRows: integer (nullable = false)
+ | |-- numCols: integer (nullable = false)
+ | |-- colPtrs: array (nullable = true)
+ | | |-- element: integer (containsNull = false)
+ | |-- rowIndices: array (nullable = true)
+ | | |-- element: integer (containsNull = false)
+ | |-- values: array (nullable = true)
+ | | |-- element: double (containsNull = false)
+ | |-- isTransposed: boolean (nullable = false)
"""
from pyspark.sql.classic.column import _to_java_column
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
