Comparing columns in Pyspark

We can use greatest

Creating DataFrame

df = spark.createDataFrame(
    [[1,2,3], [2,1,2], [3,4,5]], 
    ['col_1','col_2','col_3']
)
df.show()
+-----+-----+-----+
|col_1|col_2|col_3|
+-----+-----+-----+
|    1|    2|    3|
|    2|    1|    2|
|    3|    4|    5|
+-----+-----+-----+

---

Solution

from pyspark.sql.functions import greatest
df2 = df.withColumn('max_by_rows', greatest('col_1', 'col_2', 'col_3'))

#Only if you need col
#from pyspark.sql.functions import col
#df2 = df.withColumn('max', greatest(col('col_1'), col('col_2'), col('col_3')))
df2.show()

+-----+-----+-----+-----------+
|col_1|col_2|col_3|max_by_rows|
+-----+-----+-----+-----------+
|    1|    2|    3|          3|
|    2|    1|    2|          2|
|    3|    4|    5|          5|
+-----+-----+-----+-----------+

You can reduce using SQL expressions over a list of columns:

from pyspark.sql.functions import max as max_, col, when
from functools import reduce

def row_max(*cols):
    return reduce(
        lambda x, y: when(x > y, x).otherwise(y),
        [col(c) if isinstance(c, str) else c for c in cols]
    )

df = (sc.parallelize([(1, 2, 3), (2, 1, 2), (3, 4, 5)])
    .toDF(["a", "b", "c"]))

df.select(row_max("a", "b", "c").alias("max")))

Spark 1.5+ also provides least, greatest

from pyspark.sql.functions import greatest

df.select(greatest("a", "b", "c"))

If you want to keep name of the max you can use `structs:

from pyspark.sql.functions import struct, lit

def row_max_with_name(*cols):
    cols_ = [struct(col(c).alias("value"), lit(c).alias("col")) for c in cols]
    return greatest(*cols_).alias("greatest({0})".format(",".join(cols)))

 maxs = df.select(row_max_with_name("a", "b", "c").alias("maxs"))

And finally you can use above to find select "top" column:

from pyspark.sql.functions import max

((_, c), ) = (maxs
    .groupBy(col("maxs")["col"].alias("col"))
    .count()
    .agg(max(struct(col("count"), col("col"))))
    .first())

df.select(c)