显示两个dataframe列之间的唯一值- pyspark

from pyspark.sql import SparkSession

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

# 创建示例DataFrame
data = [("Alice", 25, "New York"), ("Bob", 30, "London"), ("Alice", 25, "New York")]
df = spark.createDataFrame(data, ["Name", "Age", "City"])

# 显示两个列之间的唯一值
unique_values = df.select("Name", "City").distinct()

# 打印结果
unique_values.show()

+-----+--------+
| Name|    City|
+-----+--------+
|Alice|New York|
|  Bob|  London|
+-----+--------+