Pyspark dataframe -获取两列变量的计数

from pyspark.sql import SparkSession

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

# 创建DataFrame
data = [("Alice", 25, "Female"),
        ("Bob", 30, "Male"),
        ("Charlie", 35, "Male"),
        ("Alice", 40, "Female"),
        ("Bob", 45, "Male")]

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

# 获取两列变量的计数
count_df = df.groupBy("Name", "Gender").count()

# 显示结果
count_df.show()

+-------+------+-----+
|   Name|Gender|count|
+-------+------+-----+
|    Bob|  Male|    2|
|  Alice|Female|    2|
|Charlie|  Male|    1|
+-------+------+-----+