您可以指定一个行号，并根据行号是否等于1将Dataframe分成两部分。

from pyspark.sql import functions as F, Window

df2 = df.withColumn(
    'rn', 
    F.row_number().over(Window.partitionBy('GUID').orderBy(F.monotonically_increasing_id()))
)
df2.show()
+----+----+---+
|name|GUID| rn|
+----+----+---+
|   a|   1|  1|
|   c|   1|  2|
|   a|   3|  1|
|   b|   2|  1|
|   a|   2|  2|
|   c|   4|  1|
+----+----+---+

df2_part1 = df2.filter('rn = 1').drop('rn')
df2_part2 = df2.filter('rn != 1').drop('rn')

df2_part1.show()
+----+----+
|name|GUID|
+----+----+
|   a|   1|
|   a|   3|
|   b|   2|
|   c|   4|
+----+----+

df2_part2.show()
+----+----+
|name|GUID|
+----+----+
|   c|   1|
|   a|   2|
+----+----+