在Pyspark中查找每个id的模态值

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

spark = SparkSession.builder.appName("ModalValue").getOrCreate()

data = [(1, 2), (1, 3), (2, 2), (2, 4), (2, 4), (3, 1), (3, 1), (3, 2)]
df = spark.createDataFrame(data, ["id", "value"])

windowSpec = Window.partitionBy("id").orderBy(desc("count"))
modal_df = df.groupBy("id", "value").count().withColumn("rank", dense_rank().over(windowSpec)).filter(col("rank") == 1).drop("rank")

modal_df.show()