在PySpark中有效地对不同的值求和并在求和中创建百分比

from pyspark.sql import SparkSession
from pyspark.sql.functions import sum, sumOverWindow

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

# 创建示例数据
data = [("A", 10), ("A", 20), ("B", 30), ("B", 40), ("C", 50)]
df = spark.createDataFrame(data, ["group", "value"])

# 使用groupBy和agg函数进行求和和百分比计算
result = df.groupBy("group").agg(sum("value").alias("total_value"))
result = result.withColumn("percentage", (result["total_value"] / sum("total_value").over(Window.partitionBy())).alias("percentage"))

# 显示结果
result.show()

+-----+-----------+-------------------+
|group|total_value|         percentage|
+-----+-----------+-------------------+
|    A|         30|0.23076923076923078|
|    B|         70| 0.5384615384615384|
|    C|         50| 0.3846153846153846|
+-----+-----------+-------------------+