将大型数组列拆分为多个列- Pyspark

from pyspark.sql import SparkSession
from pyspark.sql.functions import explode

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据
data = [("John", [1, 2, 3]), ("Alice", [4, 5, 6]), ("Bob", [7, 8, 9])]
df = spark.createDataFrame(data, ["name", "array_col"])

# 使用explode函数拆分数组列
df_exploded = df.select("name", explode("array_col").alias("array_element"))

# 显示结果
df_exploded.show()

+-----+-------------+
| name|array_element|
+-----+-------------+
| John|            1|
| John|            2|
| John|            3|
|Alice|            4|
|Alice|            5|
|Alice|            6|
|  Bob|            7|
|  Bob|            8|
|  Bob|            9|
+-----+-------------+