如何统计pyspark dataframe中一列列表中元素的出现频率？

from pyspark.sql import functions as F

df = df.withColumn('column_name', F.explode('column_name'))

result = df.groupBy('column_name').count()

result = result.orderBy('count', ascending=False)

result.show()

from pyspark.sql import SparkSession
from pyspark.sql import functions as F

# 创建SparkSession
spark = SparkSession.builder.appName('frequency_count').getOrCreate()

# 创建示例DataFrame
data = [("A", ["apple", "banana", "apple"]),
        ("B", ["orange", "orange", "grape"]),
        ("C", ["apple", "banana", "orange", "grape"]),
        ("D", ["apple", "apple", "grape"]),
        ("E", ["orange", "orange", "orange"])]

df = spark.createDataFrame(data, ["id", "column_name"])

# 使用explode函数将一列列表中的元素拆分为多行
df = df.withColumn('column_name', F.explode('column_name'))

# 使用groupBy和count函数对元素进行分组和计数
result = df.groupBy('column_name').count()

# 按照出现频率进行排序
result = result.orderBy('count', ascending=False)

# 打印结果
result.show()