将数据集[ Dataset[Column] ]展平为Dataset[Column]

import pandas as pd

# 假设我们有一个包含列的数据集
data = {
    'A': [1, 2, 3],
    'B': [4, 5, 6],
    'C': [7, 8, 9]
}

df = pd.DataFrame(data)

# 将数据集展平为一列
flattened_df = df.melt(var_name='Column', value_name='Value')

print(flattened_df)

  Column  Value
0      A      1
1      B      4
2      C      7
3      A      2
4      B      5
5      C      8
6      A      3
7      B      6
8      C      9

import org.apache.spark.sql.{SparkSession, functions => F}

val spark = SparkSession.builder()
  .appName("Flatten Dataset")
  .master("local[*]")
  .getOrCreate()

import spark.implicits._

// 假设我们有一个包含列的数据集
val data = Seq(
  (1, 4, 7),
  (2, 5, 8),
  (3, 6, 9)
)

val df = data.toDF("A", "B", "C")

// 将数据集展平为一列
val flattenedDF = df.selectExpr("stack(3, 'A', A, 'B', B, 'C', C) as (Column, Value)")

flattenedDF.show()

+-------+-----+
| Column|Value|
+-------+-----+
|      A|    1|
|      B|    4|
|      C|    7|
|      A|    2|
|      B|    5|
|      C|    8|
|      A|    3|
|      B|    6|
|      C|    9|
+-------+-----+