如何计算pyspark数据帧中值的条件概率？

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

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

data = spark.read.csv("path/to/dataset.csv", header=True, inferSchema=True)

condition_col = "condition_column"
target_col = "target_column"

# 计算条件列的频次
condition_counts = data.groupBy(condition_col).count()

# 计算条件和目标列的联合频次
joint_counts = data.groupBy(condition_col, target_col).count()

# 计算条件概率
conditional_probabilities = joint_counts.join(condition_counts, condition_col).withColumn("probability", col("count") / col("count"))

# 显示结果
conditional_probabilities.show()