如果withColumn不存在，则使用它创建新列

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

# 创建 SparkSession
spark = SparkSession.builder.appName("example").getOrCreate()

# 示例数据
data = [
    (1, "Alice", 25),
    (2, "Bob", 35),
    (3, "Charlie", 45)
]
columns = ["id", "name", "age"]

# 创建 DataFrame
df = spark.createDataFrame(data, columns)

# 使用 withColumn 添加新列
df_with_age_group = df.withColumn(
    "age_group",
    when(df.age < 30, "Young")
    .when(df.age >= 30 & (df.age < 40), "Middle-aged")
    .otherwise("Senior")
)

# 显示结果
df_with_age_group.show()

# 检查表达式
new_column_expr = when(df.age < 30, "Young").otherwise("Old")
print(new_column_expr)

# 确保列名唯一
df_with_new_column = df.withColumn("new_age_group", new_column_expr)