将字符串(或字符串列表)拆分为spark数据帧中的单个列

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

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

# 创建示例数据
data = [("John,Doe",), ("Jane,Smith",), ("Tom,Hanks",)]
df = spark.createDataFrame(data, ["name"])

# 使用split()函数拆分字符串列
df = df.withColumn("first_name", split(df["name"], ",")[0])
df = df.withColumn("last_name", split(df["name"], ",")[1])

# 显示结果
df.show()

+----------+---------+---------+
|      name|first_name|last_name|
+----------+---------+---------+
|  John,Doe|     John|      Doe|
|Jane,Smith|     Jane|    Smith|
| Tom,Hanks|      Tom|    Hanks|
+----------+---------+---------+