HyukjinKwon commented on code in PR #38844:
URL: https://github.com/apache/spark/pull/38844#discussion_r1035441705
##########
python/pyspark/sql/connect/column.py:
##########
@@ -352,17 +365,307 @@ def __init__(self, expr: Expression) -> None:
__rpow__ = _bin_op("pow", reverse=True)
__ge__ = _bin_op(">=")
__le__ = _bin_op("<=")
- # __eq__ = _bin_op("==") # ignore [assignment]
+
+ _eqNullSafe_doc = """
+ Equality test that is safe for null values.
+ .. versionadded:: 2.3.0
+ Parameters
+ ----------
+ other
+ a value or :class:`Column`
+ Examples
+ --------
+ >>> from pyspark.sql import Row
+ >>> df1 = spark.createDataFrame([
+ ... Row(id=1, value='foo'),
+ ... Row(id=2, value=None)
+ ... ])
+ >>> df1.select(
+ ... df1['value'] == 'foo',
+ ... df1['value'].eqNullSafe('foo'),
+ ... df1['value'].eqNullSafe(None)
+ ... ).show()
+ +-------------+---------------+----------------+
+ |(value = foo)|(value <=> foo)|(value <=> NULL)|
+ +-------------+---------------+----------------+
+ | true| true| false|
+ | null| false| true|
+ +-------------+---------------+----------------+
+ >>> df2 = spark.createDataFrame([
+ ... Row(value = 'bar'),
+ ... Row(value = None)
+ ... ])
+ >>> df1.join(df2, df1["value"] == df2["value"]).count()
+ 0
+ >>> df1.join(df2, df1["value"].eqNullSafe(df2["value"])).count()
+ 1
+ >>> df2 = spark.createDataFrame([
+ ... Row(id=1, value=float('NaN')),
+ ... Row(id=2, value=42.0),
+ ... Row(id=3, value=None)
+ ... ])
+ >>> df2.select(
+ ... df2['value'].eqNullSafe(None),
+ ... df2['value'].eqNullSafe(float('NaN')),
+ ... df2['value'].eqNullSafe(42.0)
+ ... ).show()
+ +----------------+---------------+----------------+
+ |(value <=> NULL)|(value <=> NaN)|(value <=> 42.0)|
+ +----------------+---------------+----------------+
+ | false| true| false|
+ | false| false| true|
+ | true| false| false|
+ +----------------+---------------+----------------+
+ Notes
+ -----
+ Unlike Pandas, PySpark doesn't consider NaN values to be NULL. See the
+ `NaN Semantics
<https://spark.apache.org/docs/latest/sql-ref-datatypes.html#nan-semantics>`_
+ for details.
+ """
+ eqNullSafe = _bin_op("eqNullSafe", _eqNullSafe_doc)
+
+ __neg__ = _func_op("negate")
+
+ # `and`, `or`, `not` cannot be overloaded in Python,
+ # so use bitwise operators as boolean operators
+ __and__ = _bin_op("and")
+ __or__ = _bin_op("or")
+ __invert__ = _func_op("not")
+ __rand__ = _bin_op("and")
+ __ror__ = _bin_op("or")
+
+ # bitwise operators
+ _bitwiseOR_doc = """
+ Compute bitwise OR of this expression with another expression.
+ Parameters
Review Comment:
ditto for spaces
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
