pyspark-使用最大值为一列创建从0到该值的行值循环，并为其重复其他列值

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, explode, lit, monotonically_increasing_id, when

spark = SparkSession.builder.appName("pyspark-example").getOrCreate()

data = [(1, "A"), (2, "B"), (3, "C")]
df = spark.createDataFrame(data, ["max_value", "other_column"])
df.show()

+---------+-------------+
|max_value|other_column|
+---------+-------------+
|        1|            A|
|        2|            B|
|        3|            C|
+---------+-------------+

df = df.withColumn("row_id", explode([lit(x) for x in range(0, col("max_value")+1)]))
df.show()

+---------+-------------+------+
|max_value|other_column|row_id|
+---------+-------------+------+
|        1|            A|     0|
|        1|            A|     1|
|        2|            B|     0|
|        2|            B|     1|
|        2|            B|     2|
|        3|            C|     0|
|        3|            C|     1|
|        3|            C|     2|
|        3|            C|     3|
+---------+-------------+------+

df = df.withColumn("repeated_column", when(col("row_id") == 0, col("other_column")).otherwise(None))
df.show()

+---------+-------------+------+---------------+
|max_value|other_column|row_id|repeated_column|
+---------+-------------+------+---------------+
|        1|            A|     0|              A|
|        1|            A|     1|           null|
|        2|            B|     0|              B|
|        2|            B|     1|           null|
|        2|            B|     2|           null|
|        3|            C|     0|              C|
|        3|            C|     1|           null|
|        3|            C|     2|           null|
|        3|            C|     3|           null|
+---------+-------------+------+---------------+