how to get the name of column with maximum value i

How do we get the name of the column pyspark dataframe ?

   Alice  Eleonora  Mike  Helen       MAX
0      2         7     8      6      Mike
1     11         5     9      4     Alice
2      6        15    12      3  Eleonora
3      5         3     7      8     Helen

I need something like this. name of the columns no the max values, i am able to get the max values, i need the name

You can chain conditions to find which columns is equal to the maximum value:

cond = "psf.when" + ".when".join(["(psf.col('" + c + "') == psf.col('max_value'), psf.lit('" + c + "'))" for c in df.columns])
import pyspark.sql.functions as psf
df.withColumn("max_value", psf.greatest(*df.columns))\
    .withColumn("MAX", eval(cond))\
    .show()

    +-----+--------+----+-----+---------+--------+
    |Alice|Eleonora|Mike|Helen|max_value|     MAX|
    +-----+--------+----+-----+---------+--------+
    |    2|       7|   8|    6|        8|    Mike|
    |   11|       5|   9|    4|       11|   Alice|
    |    6|      15|  12|    3|       15|Eleonora|
    |    5|       3|   7|    8|        8|   Helen|
    +-----+--------+----+-----+---------+--------+

OR: explode and filter

df.withColumn("max_value", psf.greatest(*df.columns))\
    .select("*", psf.posexplode(psf.create_map(list(chain(*[(psf.lit(c), psf.col(c)) for c in df.columns])))))\
    .filter("max_value = value")\
    .select(df.columns + [psf.col("key").alias("MAX")])\
    .show()

OR: using a UDF on a dictionary:

from pyspark.sql.types import *
argmax_udf = psf.udf(lambda m: max(m, key=m.get), StringType())
df.withColumn("map", psf.create_map(list(chain(*[(psf.lit(c), psf.col(c)) for c in df.columns]))))\
    .withColumn("MAX", argmax_udf("map"))\
    .drop("map")\
    .show()

OR: using a UDF with a parameter:

from pyspark.sql.types import *
def argmax(cols, *args):
    return [c for c, v in zip(cols, args) if v == max(args)][0]
argmax_udf = lambda cols: psf.udf(lambda *args: argmax(cols, *args), StringType())
df.withColumn("MAX", argmax_udf(df.columns)(*df.columns))\
    .show()