根据spark dataframe中的列值查找累积平均值

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

spark = SparkSession.builder.appName("Cumulative Average").getOrCreate()

df = spark.read.format("csv").option("header", "true").load("data.csv")

windowSpec = Window.orderBy("column_name").rowsBetween(Window.unboundedPreceding, Window.currentRow)

df = df.withColumn("cumulative_avg", avg(col("column_name")).over(windowSpec))

df.show()