Get name / alias of column in PySpark

Question

I am defining a column object like this:

column = F.col('foo').alias('bar')

I know I can get the full expression using str(column). But how can I get the column's alias only?

In the example, I'm looking for a function get_column_name where get_column_name(column) returns the string bar.

Answer 1

One way is through regular expressions:

from pyspark.sql.functions import col
column = col('foo').alias('bar')
print(column)
#Column<foo AS `bar`>

import re
print(re.findall("(?<=AS `)\w+(?=`>$)", str(column)))[0]
#'bar'

Answer 2

Alternatively, we could use a wrapper function to tweak the behavior of Column.alias and Column.name methods to store the alias only in an AS attribute:

from pyspark.sql import Column, SparkSession
from pyspark.sql.functions import col, explode, array, struct, lit
SparkSession.builder.getOrCreate()

def alias_wrapper(self, *alias, **kwargs):
    renamed_col = Column._alias(self, *alias, **kwargs)
    renamed_col.AS = alias[0] if len(alias) == 1 else alias
    return renamed_col

Column._alias, Column.alias, Column.name, Column.AS = Column.alias, alias_wrapper, alias_wrapper, None

which then guarantees:

assert(col("foo").alias("bar").AS == "bar")
# `name` should act like `alias`
assert(col("foo").name("bar").AS == "bar")
# column without alias should have None in `AS`
assert(col("foo").AS is None)
# multialias should be handled
assert(explode(array(struct(lit(1), lit("a")))).alias("foo", "bar").AS == ("foo", "bar"))