pyspark中的最后一次出现索引

from pyspark.sql.functions import expr

data = [("apple",), ("banana",), ("apple",), ("orange",)]
df = spark.createDataFrame(data, ["fruit"])

df.withColumn("last_index", expr("last_index('apple', fruit)")).show()

+------+----------+
| fruit|last_index|
+------+----------+
| apple|         2|
|banana|        -1|
| apple|         2|
|orange|        -1|
+------+----------+

from pyspark.sql.functions import expr

data = [([1, 2, 3, 2],), ([4, 5, 6],), ([1, 2, 3, 2],), ([7, 8, 9],)]
df = spark.createDataFrame(data, ["numbers"])

df.withColumn("last_index", expr("array_position(numbers, 2)")).show()

+------------+----------+
|     numbers|last_index|
+------------+----------+
|[1, 2, 3, 2]|         4|
|   [4, 5, 6]|        -1|
|[1, 2, 3, 2]|         4|
|   [7, 8, 9]|        -1|
+------------+----------+