对pyspark数据框值进行分类

from pyspark.sql import SparkSession

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

# 创建示例数据框
data = [("Alice", 25, "Female"),
        ("Bob", 30, "Male"),
        ("Charlie", 35, "Male"),
        ("David", 40, "Male"),
        ("Eva", 45, "Female")]

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

# 对Gender列的值进行分类
result = df.groupBy("Gender").agg({"Gender": "count"})

# 打印结果
result.show()

+------+------------+
|Gender|count(Gender)|
+------+------------+
|Female|           2|
|  Male|           3|
+------+------------+