Created
May 1, 2022 14:17
-
-
Save karpanGit/1003d96865f520e5997335052d528e2a to your computer and use it in GitHub Desktop.
pyspark, explode array, explode list, collect_list, collect_set
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
# simple example: explode array | |
import pyspark.sql.functions as F | |
df = [[1, 'mplah', ['a', 'b', 'c']], [2, 'mplah2', ['a2', 'b2', 'c2']], [3, 'mplah3', ['a3', 'b3', 'c3', 'd3']]] | |
df = spark.createDataFrame(df, schema=['x', 'y', 'z']) | |
df.printSchema() | |
res = df.select(F.col('x'), F.explode(F.col('z')).alias('z')) | |
res.show(truncate=False) | |
res = df.select(F.col('x'), F.posexplode(F.col('z')).alias('z_id', 'z')) | |
res.show(truncate=False) | |
# simple example: explode map | |
import pyspark.sql.functions as F | |
df = [[1, 'mplah', 'gogo'], [2, 'mplah2', 'gogo2'], [3, 'mplah3', 'gogo3']] | |
df = spark.createDataFrame(df, schema=['x', 'y', 'z']) | |
res = df.select(F.col('x'), F.create_map(F.col('y'), F.col('z')).alias('mapped')) | |
res.printSchema() | |
# root | |
# |-- x: long (nullable = true) | |
# |-- mapped: map (nullable = false) | |
# | |-- key: string | |
# | |-- value: string (valueContainsNull = true) | |
res.show() | |
# | x| mapped| | |
# +---+-----------------+ | |
# | 1| {mplah -> gogo}| | |
# | 2|{mplah2 -> gogo2}| | |
# | 3|{mplah3 -> gogo3}| | |
# +---+-----------------+ | |
res = res.select(F.col('x'), F.explode(F.col('mapped'))) | |
res.show() | |
# | x| key|value| | |
# +---+------+-----+ | |
# | 1| mplah| gogo| | |
# | 2|mplah2|gogo2| | |
# | 3|mplah3|gogo3| | |
# +---+------+-----+ | |
# simple example 2: explode map | |
import pyspark.sql.functions as F | |
df = [[1, ['A', 'B', 'C'], ['a', 'b', 'c']], [2, ['A2', 'B2', 'C2'], ['a2', 'b2', 'c2']], [3, ['A3', 'B3', 'C3', 'D3'], ['a3', 'b3', 'c3', 'd3']]] | |
df = spark.createDataFrame(df, schema=['x', 'y', 'z']) | |
res = df.select(F.col('x'), F.map_from_arrays(F.col('y'), F.col('z')).alias('mapped')) | |
res.show(truncate=False) | |
# |x |mapped | | |
# +---+----------------------------------------+ | |
# |1 |{A -> a, B -> b, C -> c} | | |
# |2 |{A2 -> a2, B2 -> b2, C2 -> c2} | | |
# |3 |{A3 -> a3, B3 -> b3, C3 -> c3, D3 -> d3}| | |
# +---+----------------------------------------+ | |
res = res.select(F.col('x'), F.explode(F.col('mapped'))) | |
res.show() | |
# | x|key|value| | |
# +---+---+-----+ | |
# | 1| A| a| | |
# | 1| B| b| | |
# | 1| C| c| | |
# | 2| A2| a2| | |
# | 2| B2| b2| | |
# | 2| C2| c2| | |
# | 3| A3| a3| | |
# | 3| B3| b3| | |
# | 3| C3| c3| | |
# | 3| D3| d3| | |
# +---+---+-----+ | |
# collect the results back into an array | |
res = res.groupby(F.col('x')).agg(F.collect_list(F.col('key')).alias('key'), F.collect_list(F.col('value')).alias('value')) | |
res.show() | |
# | x| key| value| | |
# +---+----------------+----------------+ | |
# | 1| [A, B, C]| [a, b, c]| | |
# | 2| [A2, B2, C2]| [a2, b2, c2]| | |
# | 3|[A3, B3, C3, D3]|[a3, b3, c3, d3]| | |
# +---+----------------+----------------+ | |
res = res.select(F.col('x'), F.map_from_arrays('key', 'value').alias('mapped')) | |
res.show(truncate=False) | |
# |x |mapped | | |
# +---+----------------------------------------+ | |
# |1 |{A -> a, B -> b, C -> c} | | |
# |2 |{A2 -> a2, B2 -> b2, C2 -> c2} | | |
# |3 |{A3 -> a3, B3 -> b3, C3 -> c3, D3 -> d3}| | |
# +---+----------------------------------------+ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment