将Pyspark Dataframe列从数组转换为新列

from pyspark.sql.functions import explode
from pyspark.sql.functions import col

df = df.withColumn('new_column', explode(col('array_column')))

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

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

# 创建示例Dataframe
data = [("John", ["apple", "banana", "orange"]),
        ("Mike", ["grape", "kiwi", "melon"]),
        ("Lisa", ["mango", "pineapple", "strawberry"])]

df = spark.createDataFrame(data, ["name", "fruits"])

# 将数组列展开为多行
df = df.withColumn('new_column', explode(col('fruits')))

# 显示结果
df.show()

+----+----------------+-----------+
|name|fruits          |new_column |
+----+----------------+-----------+
|John|[apple, banana, orange]|apple      |
|John|[apple, banana, orange]|banana     |
|John|[apple, banana, orange]|orange     |
|Mike|[grape, kiwi, melon]  |grape      |
|Mike|[grape, kiwi, melon]  |kiwi       |
|Mike|[grape, kiwi, melon]  |melon      |
|Lisa|[mango, pineapple, strawberry]|mango      |
|Lisa|[mango, pineapple, strawberry]|pineapple  |
|Lisa|[mango, pineapple, strawberry]|strawberry |
+----+----------------+-----------+