Subset one array column with another (boolean) array column

Question

I have a Dataframe like this (in Pyspark 2.3.1):

from pyspark.sql import Row

my_data = spark.createDataFrame([
  Row(a=[9, 3, 4], b=['a', 'b', 'c'], mask=[True, False, False]),
  Row(a=[7, 2, 6, 4], b=['w', 'x', 'y', 'z'], mask=[True, False, True, False])
])
my_data.show(truncate=False)
#+------------+------------+--------------------------+
#|a           |b           |mask                      |
#+------------+------------+--------------------------+
#|[9, 3, 4]   |[a, b, c]   |[true, false, false]      |
#|[7, 2, 6, 4]|[w, x, y, z]|[true, false, true, false]|
#+------------+------------+--------------------------+

Now I'd like to use the mask column in order to subset the a and b columns:

my_desired_output = spark.createDataFrame([
  Row(a=[9], b=['a']),
  Row(a=[7, 6], b=['w', 'y'])
])
my_desired_output.show(truncate=False)
#+------+------+
#|a     |b     |
#+------+------+
#|[9]   |[a]   |
#|[7, 6]|[w, y]|
#+------+------+

What's the "idiomatic" way to achieve this? The current solution I have involves map-ing over the underlying RDD and subsetting with Numpy, which seems inelegant:

import numpy as np

def subset_with_mask(row):
    mask = np.asarray(row.mask)
    a_masked = np.asarray(row.a)[mask].tolist()
    b_masked = np.asarray(row.b)[mask].tolist()
    return Row(a=a_masked, b=b_masked)

my_desired_output = spark.createDataFrame(my_data.rdd.map(subset_with_mask))

Is this the best way to go, or is there something better (less verbose and/or more efficient) I can do using Spark SQL tools?

Answer 1

One option is to use a UDF, which you can optionally specialize by the data type in the array:

import numpy as np
import pyspark.sql.functions as F
import pyspark.sql.types as T

def _mask_list(lst, mask):
    return np.asarray(lst)[mask].tolist()

mask_array_int = F.udf(_mask_list, T.ArrayType(T.IntegerType()))
mask_array_str = F.udf(_mask_list, T.ArrayType(T.StringType()))

my_desired_output = my_data
my_desired_output = my_desired_output.withColumn(
    'a', mask_array_int(F.col('a'), F.col('mask'))
)
my_desired_output = my_desired_output.withColumn(
    'b', mask_array_str(F.col('b'), F.col('mask'))
)