如何有条件地替换Apache Spark数据集中的值？

from pyspark.sql import SparkSession

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

# 创建一个DataFrame
data = [("Alice", 25), ("Bob", 30), ("Charlie", 35)]
df = spark.createDataFrame(data, ["Name", "Age"])

# 替换Age列中的值为新值
new_value = 40
df = df.withColumn("Age", new_value)

# 显示替换后的结果
df.show()

from pyspark.sql import SparkSession
from pyspark.sql.functions import when

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

# 创建一个DataFrame
data = [("Alice", 25), ("Bob", 30), ("Charlie", 35)]
df = spark.createDataFrame(data, ["Name", "Age"])

# 根据条件替换Age列中的值
condition = df["Age"] > 30
new_value = 40
df = df.withColumn("Age", when(condition, new_value).otherwise(df["Age"]))

# 显示替换后的结果
df.show()