在Pyspark中使用when条件的Groupby

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

# 创建SparkSession
spark = SparkSession.builder.appName("Groupby with When Condition in Pyspark").getOrCreate()

# 创建示例数据
data = [("Alice", 25, "F"),
        ("Bob", 30, "M"),
        ("Catherine", 35, "F"),
        ("David", 40, "M"),
        ("Emma", 45, "F")]

df = spark.createDataFrame(data, ["Name", "Age", "Gender"])

# 使用when条件的Groupby
grouped_df = df.groupBy(when(df.Gender == "F", "Female").otherwise("Male").alias("Gender")).agg(count("Name").alias("Count"))

# 显示结果
grouped_df.show()