Revert "[SPARK-51276][PYTHON] Enable spark.sql.execution.arrow.pyspark.enabled by default"

This reverts commit 9ac566d.

Author: HyukjinKwon

python/docs/source/migration_guide/pyspark_upgrade.rst

@@ -76,7 +76,6 @@ Upgrading from PySpark 3.5 to 4.0
 * In Spark 4.0, the data type ``YearMonthIntervalType`` in ``DataFrame.collect`` no longer returns the underlying integers. To restore the previous behavior, set ``PYSPARK_YM_INTERVAL_LEGACY`` environment variable to ``1``.
 * In Spark 4.0, items other than functions (e.g. ``DataFrame``, ``Column``, ``StructType``) have been removed from the wildcard import ``from pyspark.sql.functions import *``, you should import these items from proper modules (e.g. ``from pyspark.sql import DataFrame, Column``, ``from pyspark.sql.types import StructType``).
 * In Spark 4.0, ``spark.sql.execution.pythonUDF.arrow.enabled`` is enabled by default. If users have PyArrow and pandas installed in their local and Spark Cluster, it automatically optimizes the regular Python UDFs with Arrow. To turn off the Arrow optimization, set ``spark.sql.execution.pythonUDF.arrow.enabled`` to ``false``.
-* In Spark 4.0, ``spark.sql.execution.arrow.pyspark.enabled`` is enabled by default. If users have PyArrow and pandas installed in their local and Spark Cluster, it automatically makes use of Apache Arrow for columnar data transfers in PySpark. This optimization applies to ``pyspark.sql.DataFrame.toPandas`` and ``pyspark.sql.SparkSession.createDataFrame`` when its input is a Pandas DataFrame or a NumPy ndarray. To turn off the Arrow optimization, set ``spark.sql.execution.arrow.pyspark.enabled`` to ``false``.
 
 
 Upgrading from PySpark 3.3 to 3.4

python/pyspark/pandas/base.py

@@ -1191,7 +1191,6 @@ def _shift(
         return self._with_new_scol(col, field=self._internal.data_fields[0].copy(nullable=True))
 
     # TODO: Update Documentation for Bins Parameter when its supported
-    # TODO(SPARK-51287): Enable s.index.value_counts() tests
     def value_counts(
         self,
         normalize: bool = False,
@@ -1324,15 +1323,15 @@ def value_counts(
                     ('falcon', 'length')],
                    )
 
-        >>> s.index.value_counts().sort_index()  # doctest: +SKIP
+        >>> s.index.value_counts().sort_index()
         (cow, length)       1
         (cow, weight)       2
         (falcon, length)    2
         (falcon, weight)    1
         (lama, weight)      3
         Name: count, dtype: int64
 
-        >>> s.index.value_counts(normalize=True).sort_index()  # doctest: +SKIP
+        >>> s.index.value_counts(normalize=True).sort_index()
         (cow, length)       0.111111
         (cow, weight)       0.222222
         (falcon, length)    0.222222

python/pyspark/sql/tests/connect/test_connect_creation.py

@@ -219,11 +219,6 @@ def test_with_atom_type(self):
                 self.assert_eq(sdf.toPandas(), cdf.toPandas())
 
     def test_with_none_and_nan(self):
-        # TODO(SPARK-51286): Fix test_with_none_and_nan to to pass with Arrow enabled
-        with self.sql_conf({"spark.sql.execution.arrow.pyspark.enabled": False}):
-            self.check_with_none_and_nan()
-
-    def check_with_none_and_nan(self):
         # SPARK-41855: make createDataFrame support None and NaN
         # SPARK-41814: test with eqNullSafe
         data1 = [Row(id=1, value=float("NaN")), Row(id=2, value=42.0), Row(id=3, value=None)]

sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala

@@ -3271,7 +3271,7 @@ object SQLConf {
       .doc("(Deprecated since Spark 3.0, please set 'spark.sql.execution.arrow.pyspark.enabled'.)")
       .version("2.3.0")
       .booleanConf
-      .createWithDefault(true)
+      .createWithDefault(false)
 
   val ARROW_PYSPARK_EXECUTION_ENABLED =
     buildConf("spark.sql.execution.arrow.pyspark.enabled")