使用窗口PySpark多列

from pyspark.sql import SparkSession
from pyspark.sql.window import Window
from pyspark.sql.functions import rank, col

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

# 创建示例数据集
data = [("Alice", "Math", 90),
        ("Alice", "English", 85),
        ("Bob", "Math", 80),
        ("Bob", "English", 95),
        ("Bob", "Science", 70)]

df = spark.createDataFrame(data, ["Name", "Subject", "Score"])

# 定义窗口
windowSpec = Window.partitionBy("Name").orderBy(col("Score").desc())

# 使用窗口函数对多列进行计算和分析
df.withColumn("Rank", rank().over(windowSpec)).show()

# 输出结果：
# +-----+-------+-----+----+
# | Name|Subject|Score|Rank|
# +-----+-------+-----+----+
# |Alice|   Math|   90|   1|
# |Alice|English|   85|   2|
# |  Bob|English|   95|   1|
# |  Bob|   Math|   80|   2|
# |  Bob|Science|   70|   3|
# +-----+-------+-----+----+