PySpark一次替换多个列中的值

from pyspark.sql import SparkSession
from pyspark.sql.functions import when

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

# 创建示例DataFrame
data = [("Alice", 25, "F"),
        ("Bob", 30, "M"),
        ("Charlie", 35, "M")]
df = spark.createDataFrame(data, ["name", "age", "gender"])

# 定义要替换的值和替换后的值
replace_dict = {"Alice": "Alex", "M": "Male"}

# 使用when函数和字典来替换多个列中的值
df = df.withColumn("name", when(df["name"].isin(replace_dict.keys()), replace_dict[df["name"]]).otherwise(df["name"]))
df = df.withColumn("gender", when(df["gender"].isin(replace_dict.keys()), replace_dict[df["gender"]]).otherwise(df["gender"]))

# 显示替换后的结果
df.show()