PySpark - Adding a Column from a list of values using a UDF

Question

I have to add column to a PySpark dataframe based on a list of values.

a= spark.createDataFrame([(\"Dog\", \"Cat\"), (\"Cat\", \"Dog\"), (\"Mouse\", \"Cat\"         


        

Answer 1

Hope this helps!

from pyspark.sql.functions import monotonically_increasing_id, row_number
from pyspark.sql import Window

#sample data
a= sqlContext.createDataFrame([("Dog", "Cat"), ("Cat", "Dog"), ("Mouse", "Cat")],
                               ["Animal", "Enemy"])
a.show()

#convert list to a dataframe
rating = [5,4,1]
b = sqlContext.createDataFrame([(l,) for l in rating], ['Rating'])

#add 'sequential' index and join both dataframe to get the final result
a = a.withColumn("row_idx", row_number().over(Window.orderBy(monotonically_increasing_id())))
b = b.withColumn("row_idx", row_number().over(Window.orderBy(monotonically_increasing_id())))

final_df = a.join(b, a.row_idx == b.row_idx).\
             drop("row_idx")
final_df.show()

Input:

+------+-----+
|Animal|Enemy|
+------+-----+
|   Dog|  Cat|
|   Cat|  Dog|
| Mouse|  Cat|
+------+-----+

Output is:

+------+-----+------+
|Animal|Enemy|Rating|
+------+-----+------+
|   Cat|  Dog|     4|
|   Dog|  Cat|     5|
| Mouse|  Cat|     1|
+------+-----+------+