def do_test_query(self, query):
jvm_session = _get_jvm_session(spark)
jvm = _get_jvm(spark)
tests = {
"q1": jvm.com.nvidia.spark.rapids.tests.tpch.Q1Like,
"q2": jvm.com.nvidia.spark.rapids.tests.tpch.Q2Like,
"q3": jvm.com.nvidia.spark.rapids.tests.tpch.Q3Like,
"q4": jvm.com.nvidia.spark.rapids.tests.tpch.Q4Like,
"q5": jvm.com.nvidia.spark.rapids.tests.tpch.Q5Like,
"q6": jvm.com.nvidia.spark.rapids.tests.tpch.Q6Like,
"q7": jvm.com.nvidia.spark.rapids.tests.tpch.Q7Like,
"q8": jvm.com.nvidia.spark.rapids.tests.tpch.Q8Like,
"q9": jvm.com.nvidia.spark.rapids.tests.tpch.Q9Like,
"q10": jvm.com.nvidia.spark.rapids.tests.tpch.Q10Like,
"q11": jvm.com.nvidia.spark.rapids.tests.tpch.Q11Like,
"q12": jvm.com.nvidia.spark.rapids.tests.tpch.Q12Like,
"q13": jvm.com.nvidia.spark.rapids.tests.tpch.Q13Like,
"q14": jvm.com.nvidia.spark.rapids.tests.tpch.Q14Like,
"q15": jvm.com.nvidia.spark.rapids.tests.tpch.Q15Like,
"q16": jvm.com.nvidia.spark.rapids.tests.tpch.Q16Like,
"q17": jvm.com.nvidia.spark.rapids.tests.tpch.Q17Like,
"q18": jvm.com.nvidia.spark.rapids.tests.tpch.Q18Like,
"q19": jvm.com.nvidia.spark.rapids.tests.tpch.Q19Like,
"q20": jvm.com.nvidia.spark.rapids.tests.tpch.Q20Like,
"q21": jvm.com.nvidia.spark.rapids.tests.tpch.Q21Like,
"q22": jvm.com.nvidia.spark.rapids.tests.tpch.Q22Like
}
df = tests.get(query).apply(jvm_session)
return DataFrame(df, spark.getActiveSession())
def do_test_query(self, query):
jvm_session = _get_jvm_session(spark)
jvm = _get_jvm(spark)
tests = {
"q5": jvm.com.nvidia.spark.rapids.tests.tpcxbb.Q5Like,
"q16": jvm.com.nvidia.spark.rapids.tests.tpcxbb.Q16Like,
"q21": jvm.com.nvidia.spark.rapids.tests.tpcxbb.Q21Like,
"q22": jvm.com.nvidia.spark.rapids.tests.tpcxbb.Q22Like
}
df = tests.get(query).apply(jvm_session)
return DataFrame(df, spark.getActiveSession())
def do_test_query(self, spark):
jvm_session = _get_jvm_session(spark)
jvm = _get_jvm(spark)
acq = self.mortgage_acq_path
perf = self.mortgage_perf_path
run = jvm.com.nvidia.spark.rapids.tests.mortgage.Run
if self.mortgage_format == 'csv':
df = run.csv(jvm_session, perf, acq)
elif self.mortgage_format == 'parquet':
df = run.parquet(jvm_session, perf, acq)
elif self.mortgage_format == 'orc':
df = run.orc(jvm_session, perf, acq)
else:
raise AssertionError('Not Supported Format {}'.format(
self.mortgage_format))
return DataFrame(df, spark.getActiveSession())