nchammas commented on a change in pull request #27406:
[SPARK-30681][PYSPARK][SQL] Add higher order functions API to PySpark
URL: https://github.com/apache/spark/pull/27406#discussion_r373159937
##########
File path: python/pyspark/sql/functions.py
##########
@@ -2840,6 +2840,359 @@ def from_csv(col, schema, options={}):
return Column(jc)
+def _invoke_higher_order_function(name):
+ """
+ Given name of the expression corresponding to a higher order SQL function,
+ return a function that takes
+
+ - a list of columns
+ - a list of functions (*Column) -> Column
+
+ invokes expression, and wraps result in a Column
+ (first Scala one, then Python).
+ """
+
+ def _(cols, funs):
+ sc = SparkContext._active_spark_context
+ expressions = sc._jvm.org.apache.spark.sql.catalyst.expressions
+ expr = getattr(expressions, name)
+
+ jcols = [_to_java_column(col).expr() for col in cols]
+ jfuns = [_create_lambda(f) for f in funs]
+
+ return Column(sc._jvm.Column(expr(*jcols + jfuns)))
+
+ return _
+
+
+@since(3.0)
+def transform(col, f):
+ """
+ Returns an array of elements after applying a transformation to each
element in the input array.
+
+ :param col: name of column or expression
+ :param f: a function that is applied to each element of the input array.
+ Can take one of the following forms:
+
+ - Unary ``(x: Column) -> Column: ...``
+ - Binary ``(x: Column, i: Column) -> Column...``, where the second
argument is
+ a 0-based index of the element.
+
+ and an use methods of :class:`pyspark.sql.Column`, functions defined in
+ :py:mod:`pyspark.sql.functions` and Scala ``UserDefinedFunctions``.
+ Python ``UserDefinedFunctions`` are not supported
+ (`SPARK-27052 <https://issues.apache.org/jira/browse/SPARK-27052>`__).
+
+ :return: a :class:`pyspark.sql.Column`
+
+ >>> df = spark.createDataFrame([(1, [1, 2, 3, 4])],("key", "values"))
+ >>> df.select(transform("values", lambda x: x * 2).alias("doubled")).show()
+ +------------+
+ | doubled|
+ +------------+
+ |[2, 4, 6, 8]|
+ +------------+
+
+ >>> def alternate(x, i):
+ ... return when(i % 2 == 0, x).otherwise(-x)
+ >>> df.select(transform("values", alternate).alias("alternated")).show()
+ +--------------+
+ | alternated|
+ +--------------+
+ |[1, -2, 3, -4]|
+ +--------------+
+ """
+ return _invoke_higher_order_function("ArrayTransform")([col], [f])
+
+
+@since(3.0)
+def exists(col, f):
+ """
+ Returns whether a predicate holds for one or more elements in the array.
+
+ :param col: name of column or expression
+ :param f: an function ``(x: Column) -> Column: ...`` returning the
Boolean expression.
+ Can use methods of :class:`pyspark.sql.Column`, functions defined in
+ :py:mod:`pyspark.sql.functions` and Scala ``UserDefinedFunctions``.
+ Python ``UserDefinedFunctions`` are not supported
+ (`SPARK-27052 <https://issues.apache.org/jira/browse/SPARK-27052>`__).
+ :return: a :class:`pyspark.sql.Column`
+
+ >>> df = spark.createDataFrame([(1, [1, 2, 3, 4]), (2, [3, -1,
0])],("key", "values"))
+ >>> df.select(exists("values", lambda x: x <
0).alias("any_negative")).show()
+ +------------+
+ |any_negative|
+ +------------+
+ | false|
+ | true|
+ +------------+
+ """
+ return _invoke_higher_order_function("ArrayExists")([col], [f])
+
+
+@since(3.0)
+def forall(col, f):
+ """
+ Returns whether a predicate holds for every element in the array.
+
+ :param col: name of column or expression
+ :param f: an function ``(x: Column) -> Column: ...`` returning the
Boolean expression.
+ Can use methods of :class:`pyspark.sql.Column`, functions defined in
+ :py:mod:`pyspark.sql.functions` and Scala ``UserDefinedFunctions``.
+ Python ``UserDefinedFunctions`` are not supported
+ (`SPARK-27052 <https://issues.apache.org/jira/browse/SPARK-27052>`__).
+ :return: a :class:`pyspark.sql.Column`
+
+ >>> df = spark.createDataFrame(
+ ... [(1, ["bar"]), (2, ["foo", "bar"]), (3, ["foobar", "foo"])],
+ ... ("key", "values")
+ ... )
+ >>> df.select(forall("values", lambda x:
x.rlike("foo")).alias("all_foo")).show()
+ +-------+
+ |all_foo|
+ +-------+
+ | false|
+ | false|
+ | true|
+ +-------+
+ """
+ return _invoke_higher_order_function("ArrayForAll")([col], [f])
+
+
+@since(3.0)
+def filter(col, f):
+ """
+ Returns an array of elements for which a predicate holds in a given array.
+
+ :param col: name of column or expression
+ :param f: A function that returns the Boolean expression.
+ Can take one of the following forms:
+
+ - Unary ``(x: Column) -> Column: ...``
+ - Binary ``(x: Column, i: Column) -> Column...``, where the second
argument is
+ a 0-based index of the element.
+
+ and can use methods of :class:`pyspark.sql.Column`, functions defined
in
+ :py:mod:`pyspark.sql.functions` and Scala ``UserDefinedFunctions``.
+ Python ``UserDefinedFunctions`` are not supported
+ (`SPARK-27052 <https://issues.apache.org/jira/browse/SPARK-27052>`__).
+
+ :return: a :class:`pyspark.sql.Column`
+
+ >>> df = spark.createDataFrame(
+ ... [(1, ["2018-09-20", "2019-02-03", "2019-07-01", "2020-06-01"])],
+ ... ("key", "values")
+ ... )
+ >>> def after_second_quarter(x):
+ ... return month(to_date(x)) > 6
Review comment:
Just curious: Do we have doc tests, and do they import all the functions for
this to work?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
