c177cdcf25c2292c6c1ff5679145da6dbebfa407,perfkitbenchmarker/scripts/spark_sql_runner.py,,main,#Any#,46
Before Change
results = []
for script in args.sql_scripts:
// Read script from object storage using rdd API
query = "\n".join(spark.sparkContext.textFile(script).collect())
try:
logging.info("Running %s", script)
start = time.time()
After Change
.getOrCreate())
table_metadata = []
if args.table_metadata:
table_metadata = json.loads(load_file(spark, args.table_metadata)).items()
for name, (fmt, options) in table_metadata:
logging.info("Loading %s", name)
spark.read.format(fmt).options(**options).load().createTempView(name)
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 4
Instances
Project Name: GoogleCloudPlatform/PerfKitBenchmarker
Commit Name: c177cdcf25c2292c6c1ff5679145da6dbebfa407
Time: 2021-03-10
Author: pclay@google.com
File Name: perfkitbenchmarker/scripts/spark_sql_runner.py
Class Name:
Method Name: main
Project Name: tensorflow/datasets
Commit Name: 3404c3e64990dc7290a944313f3dccca54512710
Time: 2019-12-06
Author: c.taneja09@gmail.com
File Name: tensorflow_datasets/image/food101.py
Class Name: Food101
Method Name: _generate_examples
Project Name: ilastik/ilastik
Commit Name: 630a400af2bffc27a173acf876d72a1a10cd2dbf
Time: 2014-05-08
Author: bergs@janelia.hhmi.org
File Name: ilastik/applets/base/appletSerializer.py
Class Name: SerialClassifierSlot
Method Name: _deserialize