如何在pyspark中进行均值(目标)编码

from pyspark.sql import SparkSession
from pyspark.sql.functions import mean, col
from pyspark.ml.feature import StringIndexer

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

data = spark.read.csv("path_to_dataset.csv", header=True, inferSchema=True)

indexer = StringIndexer(inputCol="target_feature", outputCol="target_index")
indexedData = indexer.fit(data).transform(data)

meanValues = indexedData.groupBy("target_index").agg(mean(col("target_variable")).alias("mean_value"))

encodedData = indexedData.join(meanValues, "target_index", "left")

encodedData = encodedData.drop("target_feature", "target_variable")