def samples(bc, dask_client, nRals, **kwargs):
init_tables = kwargs.get("init_tables", False)
sql_table_filter_map = kwargs.get("sql_table_filter_map", {})
sql_table_batch_size_map = kwargs.get("sql_table_batch_size_map", {})
sql = kwargs.get("sql_connection", None)
for fileSchemaType in datasources(dask_client, nRals):
dstables = datasource_tables[fileSchemaType]
if init_tables:
print("Creating tables for", str(fileSchemaType))
table_names = list(dstables.values())
createSchema.create_tables(
bc,
"",
fileSchemaType,
tables=tables,
table_names=table_names,
sql_table_filter_map=sql_table_filter_map,
sql_table_batch_size_map=sql_table_batch_size_map,
sql_connection=sql,
)
print("All tables were created for", str(fileSchemaType))
i = 0
queries = [get_tpch_query(q, dstables) for q in tpch_queries]
for query in queries:
i = i + 1
istr = str(i) if i > 10 else "0" + str(i)
queryId = "TEST_" + istr
sampleId = str(fileSchemaType) + "." + queryId
yield sampleId, query, queryId, fileSchemaType
def samples(bc, dask_client, nRals, **kwargs):
init_tables = kwargs.get("init_tables", False)
dir_data_lc = kwargs.get("dir_data_lc", "")
for fileSchemaType in datasources(dask_client, nRals):
dstables = datasource_tables[fileSchemaType]
if init_tables:
print("Creating tables for", str(fileSchemaType))
cs.create_tables(bc, dir_data_lc, fileSchemaType, tables = tables, table_names=list(dstables.values()))
print("All tables were created for", str(fileSchemaType))
i = 0
queries = [get_tpch_query(q, dstables) for q in tpch_queries]
for query in queries:
i = i + 1
istr = str(i) if i > 10 else "0"+str(i)
queryId = "TEST_" + istr
sampleId = str(fileSchemaType) + "." + queryId
yield sampleId, query, queryId, fileSchemaType
def executionTest(queryType, setInd, config_options):
bc, dask_client = init_context(config_options)
tables = [
"nation",
"region",
"customer",
"lineitem",
"orders",
"supplier",
"part",
"partsupp",
]
data_types = [
DataType.DASK_CUDF,
DataType.CUDF,
DataType.CSV,
DataType.PARQUET,
] # TODO orc, json
# Create Tables ------------------------------------------------------
for fileSchemaType in data_types:
if skip_test(dask_client, nRals, fileSchemaType, queryType):
continue
cs.create_tables(bc, dir_data_file, fileSchemaType, tables=tables)
# Run Query ------------------------------------------------------
worder = 1 # Parameter to indicate if its necessary to order
# the resulsets before compare them
use_percentage = False
acceptable_difference = 0.001
print("==============================")
print(queryType)
print("Test set: " + str(setInd + 1) + " Options: " +
str(config_options))
print("==============================")
queryId = "TEST_01"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_02"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_03"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
0.1,
use_percentage,
fileSchemaType,
)
queryId = "TEST_04"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
queryId = "TEST_05"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_06"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
queryId = "TEST_07"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_08"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_09"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
queryId = "TEST_10"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_11"
query = tpch.get_tpch_query(queryId)
# runTest.run_query(
# bc,
# drill,
# query,
# queryId,
# queryType,
# worder,
# "",
# acceptable_difference,
# use_percentage,
# fileSchemaType,
# )
queryId = "TEST_12"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_13"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_14"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_15"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_16"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_17"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_18"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_19"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
queryId = "TEST_20"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
queryId = "TEST_21"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_22"
query = tpch.get_tpch_query(queryId)
# runTest.run_query(
# bc,
# drill,
# query,
# queryId,
# queryType,
# worder,
# "",
# acceptable_difference,
# use_percentage,
# fileSchemaType,
# )
if dask_client is not None:
dask_client.run(gc.collect)
dask_client.run_on_scheduler(gc.collect)
dask_client.close()
dask_client.shutdown()
del dask_client
del bc
def executionTest(queryType):
tables = [
"nation",
"region",
"customer",
"lineitem",
"orders",
"supplier",
"part",
"partsupp",
]
data_types = [
DataType.DASK_CUDF,
DataType.CUDF,
DataType.CSV,
DataType.PARQUET
] # TODO orc, json
# Create Tables ------------------------------------------------------
for fileSchemaType in data_types:
if skip_test(dask_client, nRals, fileSchemaType, queryType):
continue
cs.create_tables(bc, dir_data_file, fileSchemaType, tables=tables)
# Run Query ------------------------------------------------------
worder = 1 # Parameter to indicate if its necessary to order
# the resulsets before compare them
use_percentage = False
acceptable_difference = 0.001
print("==============================")
print(queryType)
print("==============================")
queryId = "TEST_01"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_02"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_03"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
0.1,
use_percentage,
fileSchemaType,
)
queryId = "TEST_04"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
queryId = "TEST_05"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_06"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
queryId = "TEST_07"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_08"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_09"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
queryId = "TEST_10"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_11"
query = tpch.get_tpch_query(queryId)
# runTest.run_query(
# bc,
# drill,
# query,
# queryId,
# queryType,
# worder,
# "",
# acceptable_difference,
# use_percentage,
# fileSchemaType,
# )
queryId = "TEST_12"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_13"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_14"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_15"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType
)
queryId = "TEST_16"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
'',
acceptable_difference,
use_percentage,
fileSchemaType
)
queryId = "TEST_17"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_18"
query = tpch.get_tpch_query(queryId)
if fileSchemaType == DataType.ORC:
runTest.run_query(
bc,
spark,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
else:
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
use_percentage,
fileSchemaType,
)
queryId = "TEST_19"
query = tpch.get_tpch_query(queryId)
runTest.run_query(
bc,
drill,
query,
queryId,
queryType,
worder,
"",
acceptable_difference,
True,
fileSchemaType,
)
# queryId = "TEST_20"
# query = tpch.get_tpch_query(queryId)
# runTest.run_query(
# bc,
# spark,
# query,
# queryId,
# queryType,
# worder,
# "",
# acceptable_difference,
# True,
# fileSchemaType,
# )
# queryId = "TEST_21"
# query = tpch.get_tpch_query(queryId)
# runTest.run_query(
# bc,
# spark,
# query,
# queryId,
# queryType,
# worder,
# "",
# acceptable_difference,
# use_percentage,
# fileSchemaType,
# )
queryId = "TEST_22"
query = tpch.get_tpch_query(queryId)
def executionGSTest(queryType):
authority = "tpch_gs"
bc.gs(authority,
project_id=gs_project_id,
bucket_name=gs_bucket_name,
use_default_adc_json_file=True,
adc_json_file='')
dir_data_lc = 'gcs://' + authority + '/100MB2Part/'
tables = [
'nation', 'region', 'supplier', 'customer', 'lineitem', 'orders',
'part', 'partsupp'
]
data_types = [DataType.PARQUET]
for fileSchemaType in data_types:
create_tables(bc, data_dir, fileSchemaType, tables=tables)
# Run Query -----------------------------------------------------------------------------
worder = 1 # Parameter to indicate if its necessary to order the resulsets before compare them
use_percentage = False
acceptable_difference = 0.01
print('==============================')
print(queryType)
print('==============================')
queryId = 'TEST_15'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, spark, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_16'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
queryId = 'TEST_17'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, spark, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_18'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_19'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_20'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, spark, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_21'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, spark, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_22'
#print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
def executionS3Test(queryType):
#Read Data TPCH------------------------------------------------------------------------------------------------------------
authority = "tpch_s3"
print(authority)
print(bucket_name)
hola = S3EncryptionType.NONE
print(hola)
print(access_key_id)
print(secret_key)
bc.s3(authority,
bucket_name=bucket_name,
encryption_type=S3EncryptionType.NONE,
access_key_id=access_key_id,
secret_key=secret_key)
dir_data_lc = "s3://" + authority + "/" + "DataSet100Mb2part/"
tables = [
'nation', 'region', 'supplier', 'customer', 'lineitem', 'orders',
'part', 'partsupp'
]
data_types = [DataType.PARQUET] # TODO json
for fileSchemaType in data_types:
create_tables(bc, data_dir, fileSchemaType, tables=tables)
# Run Query -----------------------------------------------------------------------------
worder = 1 # Parameter to indicate if its necessary to order the resulsets before compare them
use_percentage = False
acceptable_difference = 0.01
print('==============================')
print(queryType)
print('==============================')
queryId = 'TEST_08'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_09'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
queryId = 'TEST_10'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_11'
#print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
#result = run_query(bc, drill, query, queryId, queryType, worder, '', acceptable_difference, use_percentage, fileSchemaType)
queryId = 'TEST_12'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_13'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_14'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
def executionLocalTest(queryType):
#Read Data TPCH------------------------------------------------------------------------------------------------------------
tables = [
'nation', 'region', 'supplier', 'customer', 'lineitem', 'orders',
'part', 'partsupp'
]
data_types = [DataType.PARQUET] # TODO json
for fileSchemaType in data_types:
create_tables(bc, data_dir, fileSchemaType, tables=tables)
# Run Query -----------------------------------------------------------------------------
worder = 1 # Parameter to indicate if its necessary to order the resulsets before compare them
use_percentage = False
acceptable_difference = 0.01
print('==============================')
print(queryType)
print('==============================')
queryId = 'TEST_01'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_02'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_03'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, spark, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_04'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
queryId = 'TEST_05'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_06'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, spark, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result
queryId = 'TEST_07'
print("Executing " + queryId + " ... ")
query = tpch.get_tpch_query(queryId)
result = run_query(bc, drill, query, queryId, queryType, worder,
'', acceptable_difference, use_percentage,
fileSchemaType)
log_dict[queryId] = result