如何在PySpark或Pandas中实现列中间行的大写

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, expr, upper

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

# 创建示例数据
data = [("John Doe", 25), ("Jane Smith", 30), ("Bob Johnson", 35)]
df = spark.createDataFrame(data, ["name", "age"])

# 使用withColumn和upper函数将name列中间行的文本转换为大写
df = df.withColumn("name_upper", expr("substring(name, 1, instr(name, ' ')) || upper(substring(name, instr(name, ' ')+1)) || substring(name, instr(name, ' ')+length(substring_index(name, ' ', -1))))")

# 显示结果
df.show()

import pandas as pd

# 创建示例数据
data = {"name": ["John Doe", "Jane Smith", "Bob Johnson"], "age": [25, 30, 35]}
df = pd.DataFrame(data)

# 使用str.replace和str.upper函数将name列中间行的文本转换为大写
df["name"] = df["name"].str.replace(r'(\w+)\s(\w+)', lambda x: x.group(1) + ' ' + x.group(2).upper())

# 显示结果
print(df)