How to melt Spark DataFrame?

Question

Is there an equivalent of Pandas Melt Function in Apache Spark in PySpark or at least in Scala?

I was running a sample dataset till now in python and now I want to u

Answer 1

Voted for user6910411's answer. It works as expected, however, it cannot handle None values well. thus I refactored his melt function to the following:

from pyspark.sql.functions import array, col, explode, lit
from pyspark.sql.functions import create_map
from pyspark.sql import DataFrame
from typing import Iterable 
from itertools import chain

def melt(
        df: DataFrame, 
        id_vars: Iterable[str], value_vars: Iterable[str], 
        var_name: str="variable", value_name: str="value") -> DataFrame:
    """Convert :class:`DataFrame` from wide to long format."""

    # Create map
    _vars_and_vals = create_map(
        list(chain.from_iterable([
            [lit(c), col(c)] for c in value_vars]
        ))
    )

    _tmp = df.select(*id_vars, explode(_vars_and_vals)) \
        .withColumnRenamed('key', var_name) \
        .withColumnRenamed('value', value_name)

    return _tmp

Test is with the following dataframe:

import pandas as pd

pdf = pd.DataFrame({'A': {0: 'a', 1: 'b', 2: 'c'},
                   'B': {0: 1, 1: 3, 2: 5},
                   'C': {0: 2, 1: 4, 2: 6},
                   'D': {1: 7, 2: 9}})

pd.melt(pdf, id_vars=['A'], value_vars=['B', 'C', 'D'])

A   variable    value
0   a   B   1.0
1   b   B   3.0
2   c   B   5.0
3   a   C   2.0
4   b   C   4.0
5   c   C   6.0
6   a   D   NaN
7   b   D   7.0
8   c   D   9.0

sdf = spark.createDataFrame(pdf)
melt(sdf, id_vars=['A'], value_vars=['B', 'C', 'D']).show()
+---+--------+-----+
|  A|variable|value|
+---+--------+-----+
|  a|       B|  1.0|
|  a|       C|  2.0|
|  a|       D|  NaN|
|  b|       B|  3.0|
|  b|       C|  4.0|
|  b|       D|  7.0|
|  c|       B|  5.0|
|  c|       C|  6.0|
|  c|       D|  9.0|
+---+--------+-----+