在pyspark中将字符串列表转换为二进制列表

from pyspark.sql import SparkSession
from pyspark.sql.functions import udf
from pyspark.sql.types import BinaryType

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据
data = [("apple",), ("banana",), ("cherry",)]
df = spark.createDataFrame(data, ["string_col"])

# 定义自定义函数
def convert_to_binary(string_list):
    binary_list = [string.encode('utf-8') for string in string_list]
    return binary_list

# 注册UDF
binary_udf = udf(convert_to_binary, ArrayType(BinaryType()))

# 使用UDF转换字符串列表为二进制列表
df = df.withColumn("binary_col", binary_udf(df.string_col))

# 显示结果
df.show(truncate=False)