Last active
March 2, 2018 07:35
-
-
Save vsmelov/25cc93e2091c4cbc5deb8aaf156d3298 to your computer and use it in GitHub Desktop.
decorator for cache function result to parquet
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
def cache2parquet(func): | |
""" decorator for cache function result to parquet | |
i.e. | |
# define: | |
@cache2parquet | |
def smart_and_slow_calculations(spark, **other_kwargs): | |
# some smart and slow code | |
return df | |
# use: | |
spark = SparkSession.builder.getOrCreate() | |
df = smart_and_slow_calculations(spark=spark, param1=42) | |
Notice! One of kwargs must be 'spark' with using spark context | |
""" | |
import os | |
import functools | |
dump_path = '_{}.dump'.format(func.__name__) | |
@functools.wraps(func) | |
def wrapped(*args, **kwargs): | |
if os.path.exists(dump_path): | |
return kwargs['spark'].read.parquet(dump_path) | |
else: | |
df = func(*args, **kwargs) | |
df.write.parquet(dump_path) | |
return df | |
return wrapped |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment