pyspark来拆分数组并获取键值

from pyspark.sql import SparkSession
from pyspark.sql.functions import split

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

# 创建示例数据集
data = [("Alice", "apple,banana,orange"),
        ("Bob", "grape,kiwi"),
        ("Charlie", "watermelon")]

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

# 使用split函数拆分数组并获取键值
df = df.withColumn("fruit_list", split(df.fruits, ","))

# 展示结果
df.show(truncate=False)

+-------+------------------+------------------+
|name   |fruits            |fruit_list        |
+-------+------------------+------------------+
|Alice  |apple,banana,orange|[apple, banana, orange]|
|Bob    |grape,kiwi        |[grape, kiwi]     |
|Charlie|watermelon        |[watermelon]      |
+-------+------------------+------------------+