如何按列对数据进行分组- Pyspark？

from pyspark.sql import SparkSession
from pyspark.sql.functions import col

spark = SparkSession.builder.appName("GroupByExample").getOrCreate()

data = spark.read.csv("path/to/data.csv", header=True, inferSchema=True)

grouped_data = data.groupBy("column_name")

result = grouped_data.agg({"column_name": "aggregate_function"})

result.show()

from pyspark.sql import SparkSession
from pyspark.sql.functions import col

# 创建SparkSession对象
spark = SparkSession.builder.appName("GroupByExample").getOrCreate()

# 加载数据集
data = spark.read.csv("path/to/data.csv", header=True, inferSchema=True)

# 按列进行分组
grouped_data = data.groupBy("column_name")

# 对分组后的数据进行聚合操作
result = grouped_data.agg({"column_name": "aggregate_function"})

# 显示结果
result.show()