在pyspark dataframe中添加一个组合两列的新列

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

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

# 创建示例DataFrame
data = [("John", "Doe"), ("Alice", "Smith"), ("Mike", "Johnson")]
df = spark.createDataFrame(data, ["first_name", "last_name"])

# 添加一个组合两列的新列
df = df.withColumn("full_name", concat(df.first_name, df.last_name))

# 显示DataFrame
df.show()

+----------+---------+-------------+
|first_name|last_name|    full_name|
+----------+---------+-------------+
|      John|      Doe|     JohnDoe|
|     Alice|    Smith|  AliceSmith|
|      Mike|  Johnson|MikeJohnson|
+----------+---------+-------------+