如何在pyspark中使用pandas_udf拆分dataframe中的字符串

from pyspark.sql import SparkSession
from pyspark.sql.functions import pandas_udf, split
from pyspark.sql.types import ArrayType, StringType
import pandas as pd

spark = SparkSession.builder.appName("Pandas UDF Example").getOrCreate()

data = [("John,Doe"), ("Jane,Smith"), ("Mike,Johnson")]
df = spark.createDataFrame(data, ["name"])

@pandas_udf(ArrayType(StringType()))
def split_name(s):
    return pd.Series(s.str.split(','))

# 注意：pandas_udf要求返回的pandas Series对象，因此我们使用pd.Series来返回拆分后的结果

df = df.withColumn("split_name", split_name(df["name"]))

df.show(truncate=False)

from pyspark.sql import SparkSession
from pyspark.sql.functions import pandas_udf, split
from pyspark.sql.types import ArrayType, StringType
import pandas as pd

spark = SparkSession.builder.appName("Pandas UDF Example").getOrCreate()

data = [("John,Doe"), ("Jane,Smith"), ("Mike,Johnson")]
df = spark.createDataFrame(data, ["name"])

@pandas_udf(ArrayType(StringType()))
def split_name(s):
    return pd.Series(s.str.split(','))

df = df.withColumn("split_name", split_name(df["name"]))

df.show(truncate=False)