根据分隔符拆分字符串列，并为Pyspark中的每个值创建列

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

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

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

# 使用split函数对字符串列进行拆分
df = df.withColumn("name_split", split(df["name"], ","))

# 创建新列
for i in range(2):  # 假设最多拆分出两个值
    col_name = f"value_{i+1}"
    df = df.withColumn(col_name, df["name_split"][i])

# 显示结果
df.show()

+---------------+-----------+--------+
|           name| name_split|value_1 |value_2 |
+---------------+-----------+--------+
|       John,Doe| [John, Doe]|   John |    Doe |
|     Jane,Smith|[Jane, Smith]|   Jane |  Smith |
|Michael,Johnson|[Michael, Johnson]|Michael| Johnson|
+---------------+-----------+--------+