创建另一个列，用于检查pyspark中的不同值

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

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

# 创建示例数据集
data = [("Alice", 25), ("Bob", 30), ("Alice", 35), ("Bob", 40), ("Charlie", 45)]
df = spark.createDataFrame(data, ["Name", "Age"])

# 使用withColumn函数创建一个新列来检查不同值
df_with_diff_values = df.withColumn("DifferentValues", col("Name").distinct())

# 显示结果
df_with_diff_values.show()

+-------+---+----------------+
|   Name|Age|DifferentValues |
+-------+---+----------------+
|  Alice| 25|  [Alice, Bob]  |
|    Bob| 30|  [Alice, Bob]  |
|  Alice| 35|  [Alice, Bob]  |
|    Bob| 40|  [Alice, Bob]  |
|Charlie| 45|[Charlie, Alice, Bob]|
+-------+---+----------------+