You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@arrow.apache.org by ap...@apache.org on 2018/08/07 15:42:49 UTC

[arrow] branch master updated: ARROW-2992: [Python] Fix Parquet benchmark

This is an automated email from the ASF dual-hosted git repository.

apitrou pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow.git


The following commit(s) were added to refs/heads/master by this push:
     new e4f2713  ARROW-2992: [Python] Fix Parquet benchmark
e4f2713 is described below

commit e4f27131cf0b70fc1d166fda0db25362e1b187d1
Author: Antoine Pitrou <an...@python.org>
AuthorDate: Tue Aug 7 17:42:43 2018 +0200

    ARROW-2992: [Python] Fix Parquet benchmark
    
    Author: Antoine Pitrou <an...@python.org>
    
    Closes #2389 from pitrou/ARROW-2992-fix-parquet-benchmark and squashes the following commits:
    
    9083dc3 <Antoine Pitrou> ARROW-2992:  Fix Parquet benchmark
---
 python/benchmarks/parquet.py | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/python/benchmarks/parquet.py b/python/benchmarks/parquet.py
index 39b59ad..5623095 100644
--- a/python/benchmarks/parquet.py
+++ b/python/benchmarks/parquet.py
@@ -15,7 +15,6 @@
 # specific language governing permissions and limitations
 # under the License.
 
-from concurrent.futures import ThreadPoolExecutor
 import pandas as pd
 import random
 import shutil
@@ -32,7 +31,7 @@ class ParquetManifestCreation(object):
     tmpdir = None
 
     param_names = ('num_partitions', 'num_threads')
-    params = [(10, 100, 1000), (1, 8, 'default')]
+    params = [(10, 100, 1000), (1, 8)]
 
     def setup(self, num_partitions, num_threads):
         self.tmpdir = tempfile.mkdtemp('benchmark_parquet')
@@ -47,8 +46,4 @@ class ParquetManifestCreation(object):
         shutil.rmtree(self.tmpdir)
 
     def time_manifest_creation(self, num_partitions, num_threads):
-        if num_threads != 'default':
-            thread_pool = ThreadPoolExecutor(num_threads)
-        else:
-            thread_pool = None
-        pq.ParquetManifest(self.tmpdir, thread_pool=thread_pool)
+        pq.ParquetManifest(self.tmpdir, metadata_nthreads=num_threads)