Created
May 19, 2022 18:17
-
-
Save canimus/3082e5218c9353f5bb9ed5459d0fb5a6 to your computer and use it in GitHub Desktop.
PySpark Map Transform for Null Counts
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
df.select( | |
F.array( | |
F.create_map( | |
F.lit("k1"), F.col("c1"), F.lit("k2"), F.col("c2"), F.lit("k3"), F.col("c3") | |
) | |
).alias("losing_bids") | |
).select( | |
F.transform( | |
"losing_bids", | |
lambda m: F.transform_values(m, lambda k, v: v.isNull().cast("integer")), | |
).alias("nulls_in_maps") | |
).select( | |
F.transform( | |
"nulls_in_maps", | |
lambda x: F.aggregate(F.map_values(x), F.lit(0.0), lambda acc, y: acc + y), | |
) | |
.getItem(0) | |
.cast("integer") | |
.alias("total_nulls") | |
).show( | |
truncate=False | |
) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment