将数组列拆分为行pyspark

from pyspark.sql.functions import explode

new_df = df.select(explode(df.array_col).alias("new_col"))

new_df.show()

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 = [("Alice", [1, 2, 3]), ("Bob", [4, 5, 6])]
df = spark.createDataFrame(data, ["name", "array_col"])

# 将数组列拆分为行
new_df = df.select(explode(df.array_col).alias("new_col"))

# 查看结果
new_df.show()

+-------+
|new_col|
+-------+
|      1|
|      2|
|      3|
|      4|
|      5|
|      6|
+-------+