df = spark.createDataFrame([([31, 32, 33, 34, 35, 36, 37, 38, 39, 30, 31, 32],)], schema=['random_id_cesu8'])
df.withColumn('joined', F.array_join('random_id_cesu8', '').cast('float')).show()
Be careful with the data type because the range of long is not sufficient.