将多个列的值存储在新列下的pyspark dataframe中

from pyspark.sql import SparkSession
from pyspark.sql.functions import concat, col

spark = SparkSession.builder.getOrCreate()

data = [("John", "Doe", 25),
        ("Jane", "Smith", 30),
        ("Tom", "Brown", 35)]
df = spark.createDataFrame(data, ["first_name", "last_name", "age"])
df.show()

+----------+---------+---+
|first_name|last_name|age|
+----------+---------+---+
|      John|      Doe| 25|
|      Jane|    Smith| 30|
|       Tom|    Brown| 35|
+----------+---------+---+

df_new = df.withColumn("full_name", concat(col("first_name"), col("last_name")))
df_new.show()

+----------+---------+---+---------+
|first_name|last_name|age|full_name|
+----------+---------+---+---------+
|      John|      Doe| 25| JohnDoe |
|      Jane|    Smith| 30|JaneSmith|
|       Tom|    Brown| 35|TomBrown |
+----------+---------+---+---------+