将每个组的合计作为新行添加到Pyspark中的dataframe中

from pyspark.sql import SparkSession
from pyspark.sql.functions import sum

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

# 创建示例DataFrame
data = [("A", 10), ("A", 20), ("B", 30), ("B", 40), ("C", 50)]
df = spark.createDataFrame(data, ["Group", "Value"])
df.show()

+-----+-----+
|Group|Value|
+-----+-----+
|    A|   10|
|    A|   20|
|    B|   30|
|    B|   40|
|    C|   50|
+-----+-----+

# 使用groupBy和agg计算每个组的合计
df_with_total = df.groupBy("Group").agg(sum("Value").alias("Total"))

# 将合计添加为新行到DataFrame中
df_with_total = df.union(df_with_total)

# 显示包含合计的新DataFrame
df_with_total.show()

+-----+-----+
|Group|Value|
+-----+-----+
|    A|   10|
|    A|   20|
|    B|   30|
|    B|   40|
|    C|   50|
|    A|   30|
|    B|   70|
|    C|   50|
+-----+-----+