Groupby和collect_list基于PySpark中的另一列维护顺序

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

spark = SparkSession.builder.getOrCreate()

# 创建示例数据集
data = [(1, 'A'), (2, 'B'), (3, 'A'), (4, 'B'), (5, 'C')]
df = spark.createDataFrame(data, ['id', 'category'])

# 使用Groupby操作按category列进行分组，并计算每个分组的记录数
grouped_df = df.groupby('category').count()

# 显示结果
grouped_df.show()

+--------+-----+
|category|count|
+--------+-----+
|       A|    2|
|       C|    1|
|       B|    2|
+--------+-----+

from pyspark.sql import SparkSession
from pyspark.sql.functions import collect_list

spark = SparkSession.builder.getOrCreate()

# 创建示例数据集
data = [(1, 'A'), (2, 'B'), (3, 'A'), (4, 'B'), (5, 'C')]
df = spark.createDataFrame(data, ['id', 'category'])

# 使用Groupby和collect_list操作按category列进行分组，并将id列的值收集到列表中
grouped_df = df.groupby('category').agg(collect_list('id').alias('id_list'))

# 显示结果
grouped_df.show()

+--------+---------+
|category|  id_list|
+--------+---------+
|       A|   [1, 3]|
|       C|      [5]|
|       B|   [2, 4]|
+--------+---------+