Pyspark:将具有多个值的单个列拆分为单独的列

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

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

# 创建示例数据集
data = [("Alice", "Math,Physics"),
        ("Bob", "English,History"),
        ("Charlie", "Math,Chemistry")]

df = spark.createDataFrame(data, ["Name", "Subjects"])

# 使用split函数将Subjects列拆分为单独的列
df = df.withColumn("Subject1", split(df.Subjects, ",")[0])
df = df.withColumn("Subject2", split(df.Subjects, ",")[1])

# 显示结果
df.show()

+-------+---------------+--------+---------+
|   Name|       Subjects|Subject1|Subject2 |
+-------+---------------+--------+---------+
|  Alice|  Math,Physics  | Math   | Physics |
|    Bob|  English,History| English| History |
|Charlie|  Math,Chemistry| Math   | Chemistry|
+-------+---------------+--------+---------+