如何使用python从spark数据帧中获取交叉表的行百分比？

from pyspark.sql import SparkSession
from pyspark.sql.functions import col

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

data = [("Alice", "A", 1), ("Bob", "A", 2), ("Alice", "B", 3), ("Bob", "B", 4)]
df = spark.createDataFrame(data, ["Name", "Category", "Value"])

cross_tab = df.crosstab("Name", "Category")

row_sums = cross_tab.select("Name_Category", sum([col(c) for c in cross_tab.columns[1:]]).alias("RowSum"))

cross_tab_with_row_sums = cross_tab.join(row_sums, cross_tab.Name_Category == row_sums.Name_Category, "inner").drop(row_sums.Name_Category)

cross_tab_percentage = cross_tab_with_row_sums.select(cross_tab_with_row_sums.Name_Category, *[col(c) / col("RowSum") * 100 for c in cross_tab_with_row_sums.columns[1:]])

cross_tab_percentage.show()