def main():
omniscript_path = os.path.dirname(__file__)
args = None
omnisci_server = None
parser = argparse.ArgumentParser(
description="Run internal tests from ibis project")
optional = parser._action_groups.pop()
required = parser.add_argument_group("required arguments")
parser._action_groups.append(optional)
required.add_argument(
"-f",
"--file",
dest="file",
required=True,
help="A datafile that should be loaded",
)
optional.add_argument("-dnd",
action="store_true",
help="Do not delete old table.")
optional.add_argument(
"-dni",
action="store_true",
help="Do not create new table and import any data from CSV files.",
)
optional.add_argument(
"-val",
action="store_true",
help=
"validate queries results (by comparison with Pandas queries results).",
)
optional.add_argument(
"-o",
"--optimizer",
choices=["intel", "stock"],
dest="optimizer",
default="intel",
help="Which optimizer is used",
)
# MySQL database parameters
optional.add_argument(
"-db-server",
dest="db_server",
default="localhost",
help="Host name of MySQL server.",
)
optional.add_argument(
"-db-port",
dest="db_port",
default=3306,
type=int,
help="Port number of MySQL server.",
)
optional.add_argument(
"-db-user",
dest="db_user",
default="",
help="Username to use to connect to MySQL database. "
"If user name is specified, script attempts to store results in MySQL "
"database using other -db-* parameters.",
)
optional.add_argument(
"-db-pass",
dest="db_password",
default="omniscidb",
help="Password to use to connect to MySQL database.",
)
optional.add_argument(
"-db-name",
dest="db_name",
default="omniscidb",
help="MySQL database to use to store benchmark results.",
)
optional.add_argument(
"-db-table",
dest="db_table",
help="Table to use to store results for this benchmark.",
)
# Omnisci server parameters
optional.add_argument(
"-e",
"--executable",
dest="omnisci_executable",
required=False,
help="Path to omnisci_server executable.",
)
optional.add_argument(
"-w",
"--workdir",
dest="omnisci_cwd",
help="Path to omnisci working directory. "
"By default parent directory of executable location is used. "
"Data directory is used in this location.",
)
optional.add_argument(
"-port",
"--omnisci_port",
dest="omnisci_port",
default=6274,
type=int,
help="TCP port number to run omnisci_server on.",
)
optional.add_argument(
"-u",
"--user",
dest="user",
default="admin",
help="User name to use on omniscidb server.",
)
optional.add_argument(
"-p",
"--password",
dest="password",
default="HyperInteractive",
help="User password to use on omniscidb server.",
)
optional.add_argument(
"-n",
"--name",
dest="name",
default="census_database",
help="Database name to use in omniscidb server.",
)
optional.add_argument(
"-t",
"--table",
dest="table",
default="census_table",
help="Table name name to use in omniscidb server.",
)
optional.add_argument(
"-commit_omnisci",
dest="commit_omnisci",
default="1234567890123456789012345678901234567890",
help="Omnisci commit hash to use for benchmark.",
)
optional.add_argument(
"-commit_ibis",
dest="commit_ibis",
default="1234567890123456789012345678901234567890",
help="Ibis commit hash to use for benchmark.",
)
optional.add_argument(
"-no_ibis",
action="store_true",
help="Do not run Ibis benchmark, run only Pandas (or Modin) version")
optional.add_argument(
"-pandas_mode",
choices=["pandas", "modin_on_ray", "modin_on_dask"],
default="pandas",
help=
"Specifies which version of Pandas to use: plain Pandas, Modin runing on Ray or on Dask"
)
optional.add_argument(
"-ray_tmpdir",
default="/tmp",
help=
"Location where to keep Ray plasma store. It should have enough space to keep -ray_memory"
)
optional.add_argument(
"-ray_memory",
default=200 * 1024 * 1024 * 1024,
help="Size of memory to allocate for Ray plasma store")
optional.add_argument(
"-no_ml",
action="store_true",
help="Do not run machine learning benchmark, only ETL part")
args = parser.parse_args()
args.file = args.file.replace("'", "")
# ML specific
N_RUNS = 50
TRAIN_SIZE = 0.9
RANDOM_STATE = 777
columns_names = [
"YEAR0",
"DATANUM",
"SERIAL",
"CBSERIAL",
"HHWT",
"CPI99",
"GQ",
"QGQ",
"PERNUM",
"PERWT",
"SEX",
"AGE",
"EDUC",
"EDUCD",
"INCTOT",
"SEX_HEAD",
"SEX_MOM",
"SEX_POP",
"SEX_SP",
"SEX_MOM2",
"SEX_POP2",
"AGE_HEAD",
"AGE_MOM",
"AGE_POP",
"AGE_SP",
"AGE_MOM2",
"AGE_POP2",
"EDUC_HEAD",
"EDUC_MOM",
"EDUC_POP",
"EDUC_SP",
"EDUC_MOM2",
"EDUC_POP2",
"EDUCD_HEAD",
"EDUCD_MOM",
"EDUCD_POP",
"EDUCD_SP",
"EDUCD_MOM2",
"EDUCD_POP2",
"INCTOT_HEAD",
"INCTOT_MOM",
"INCTOT_POP",
"INCTOT_SP",
"INCTOT_MOM2",
"INCTOT_POP2",
]
columns_types = [
"int64",
"int64",
"int64",
"float64",
"int64",
"float64",
"int64",
"float64",
"int64",
"int64",
"int64",
"int64",
"int64",
"int64",
"int64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
"float64",
]
try:
if not args.no_ibis:
if args.omnisci_executable is None:
parser.error(
"Omnisci executable should be specified with -e/--executable"
)
omnisci_server = OmnisciServer(
omnisci_executable=args.omnisci_executable,
omnisci_port=args.omnisci_port,
database_name=args.name,
user=args.user,
password=args.password,
)
omnisci_server.launch()
from server_worker import OmnisciServerWorker
omnisci_server_worker = OmnisciServerWorker(omnisci_server)
X_ibis, y_ibis, etl_times_ibis = etl_ibis(
filename=args.file,
columns_names=columns_names,
columns_types=columns_types,
database_name=args.name,
table_name=args.table,
omnisci_server_worker=omnisci_server_worker,
delete_old_database=not args.dnd,
create_new_table=not args.dni,
)
omnisci_server.terminate()
omnisci_server = None
print_times(etl_times_ibis, name='Ibis')
if not args.no_ml:
mse_mean, cod_mean, mse_dev, cod_dev, ml_times = ml(
X_ibis, y_ibis, RANDOM_STATE, N_RUNS, TRAIN_SIZE,
args.optimizer)
print_times(ml_times)
print("mean MSE ± deviation: {:.9f} ± {:.9f}".format(
mse_mean, mse_dev))
print("mean COD ± deviation: {:.9f} ± {:.9f}".format(
cod_mean, cod_dev))
import_pandas_into_module_namespace(main.__globals__, args.pandas_mode,
args.ray_tmpdir, args.ray_memory)
X, y, etl_times = etl_pandas(args.file,
columns_names=columns_names,
columns_types=columns_types)
print_times(etl_times, name=args.pandas_mode)
if not args.no_ml:
mse_mean, cod_mean, mse_dev, cod_dev, ml_times = ml(
X, y, RANDOM_STATE, N_RUNS, TRAIN_SIZE, args.optimizer)
print_times(ml_times)
print("mean MSE ± deviation: {:.9f} ± {:.9f}".format(
mse_mean, mse_dev))
print("mean COD ± deviation: {:.9f} ± {:.9f}".format(
cod_mean, cod_dev))
if args.val:
compare_dataframes(ibis_df=(X_ibis, y_ibis), pandas_df=(X, y))
except Exception as err:
print("Failed: ", err)
sys.exit(1)
finally:
if omnisci_server:
omnisci_server.terminate()
def main():
args = None
omnisci_server = None
port_default_value = -1
benchmarks = {
"ny_taxi": "taxi",
"santander": "santander",
"census": "census",
"plasticc": "plasticc",
"mortgage": "mortgage",
"h2o": "h2o",
}
benchmarks_with_ibis_queries = [
"ny_taxi", "santander", "census", "plasticc", "mortgage"
]
ignore_fields_for_bd_report_etl = ["t_connect"]
ignore_fields_for_bd_report_ml = []
ignore_fields_for_results_unit_conversion = [
"Backend",
"dfiles_num",
"dataset_size",
"query_name",
]
parser = argparse.ArgumentParser(
description="Run internal tests from ibis project")
optional = parser._action_groups.pop()
required = parser.add_argument_group("required arguments")
parser._action_groups.append(optional)
required.add_argument(
"-bench_name",
dest="bench_name",
choices=sorted(benchmarks.keys()),
help="Benchmark name.",
required=True,
)
required.add_argument(
"-data_file",
dest="data_file",
help="A datafile that should be loaded.",
required=True,
)
optional.add_argument(
"-dfiles_num",
dest="dfiles_num",
default=None,
type=int,
help="Number of datafiles to input into database for processing.",
)
optional.add_argument(
"-iterations",
dest="iterations",
default=1,
type=int,
help=
"Number of iterations to run every query. Best result is selected.",
)
optional.add_argument("-dnd",
default=False,
type=str_arg_to_bool,
help="Do not delete old table.")
optional.add_argument(
"-dni",
default=False,
type=str_arg_to_bool,
help="Do not create new table and import any data from CSV files.",
)
optional.add_argument(
"-validation",
dest="validation",
default=False,
type=str_arg_to_bool,
help=
"validate queries results (by comparison with Pandas queries results).",
)
optional.add_argument(
"-import_mode",
dest="import_mode",
default="fsi",
help="measure 'COPY FROM' import, FSI import, import through pandas",
)
optional.add_argument(
"-optimizer",
choices=["intel", "stock"],
dest="optimizer",
default=None,
help="Which optimizer is used",
)
optional.add_argument(
"-no_ibis",
default=False,
type=str_arg_to_bool,
help="Do not run Ibis benchmark, run only Pandas (or Modin) version",
)
optional.add_argument(
"-no_pandas",
default=False,
type=str_arg_to_bool,
help="Do not run Pandas version of benchmark",
)
optional.add_argument(
"-pandas_mode",
choices=[
"Pandas", "Modin_on_ray", "Modin_on_dask", "Modin_on_python",
"Modin_on_omnisci"
],
default="Pandas",
help=
"Specifies which version of Pandas to use: plain Pandas, Modin runing on Ray or on Dask",
)
optional.add_argument(
"-ray_tmpdir",
default="/tmp",
help=
"Location where to keep Ray plasma store. It should have enough space to keep -ray_memory",
)
optional.add_argument(
"-ray_memory",
default=200 * 1024 * 1024 * 1024,
type=int,
help="Size of memory to allocate for Ray plasma store",
)
optional.add_argument(
"-no_ml",
default=None,
type=str_arg_to_bool,
help="Do not run machine learning benchmark, only ETL part",
)
optional.add_argument(
"-gpu_memory",
dest="gpu_memory",
type=int,
help="specify the memory of your gpu"
"(This controls the lines to be used. Also work for CPU version. )",
default=None,
)
optional.add_argument(
"-extended_functionality",
dest="extended_functionality",
default=False,
type=str_arg_to_bool,
help=
"Extends functionality of H2O benchmark by adding 'chk' functions and verbose local reporting of results",
)
# MySQL database parameters
optional.add_argument(
"-db_server",
dest="db_server",
default="localhost",
help="Host name of MySQL server.",
)
optional.add_argument(
"-db_port",
dest="db_port",
default=3306,
type=int,
help="Port number of MySQL server.",
)
optional.add_argument(
"-db_user",
dest="db_user",
help="Username to use to connect to MySQL database. "
"If user name is specified, script attempts to store results in MySQL "
"database using other -db-* parameters.",
)
optional.add_argument(
"-db_pass",
dest="db_pass",
default="omniscidb",
help="Password to use to connect to MySQL database.",
)
optional.add_argument(
"-db_name",
dest="db_name",
default="omniscidb",
help="MySQL database to use to store benchmark results.",
)
optional.add_argument(
"-db_table_etl",
dest="db_table_etl",
help="Table to use to store ETL results for this benchmark.",
)
optional.add_argument(
"-db_table_ml",
dest="db_table_ml",
help="Table to use to store ML results for this benchmark.",
)
# Omnisci server parameters
optional.add_argument(
"-executable",
dest="executable",
help="Path to omnisci_server executable.",
)
optional.add_argument(
"-omnisci_cwd",
dest="omnisci_cwd",
help="Path to omnisci working directory. "
"By default parent directory of executable location is used. "
"Data directory is used in this location.",
)
optional.add_argument(
"-port",
dest="port",
default=port_default_value,
type=int,
help="TCP port number to run omnisci_server on.",
)
optional.add_argument(
"-http_port",
dest="http_port",
default=port_default_value,
type=int,
help="HTTP port number to run omnisci_server on.",
)
optional.add_argument(
"-calcite_port",
dest="calcite_port",
default=port_default_value,
type=int,
help="Calcite port number to run omnisci_server on.",
)
optional.add_argument(
"-user",
dest="user",
default="admin",
help="User name to use on omniscidb server.",
)
optional.add_argument(
"-password",
dest="password",
default="HyperInteractive",
help="User password to use on omniscidb server.",
)
optional.add_argument(
"-database_name",
dest="database_name",
default="omnisci",
help="Database name to use in omniscidb server.",
)
optional.add_argument(
"-table",
dest="table",
default="benchmark_table",
help="Table name name to use in omniscidb server.",
)
optional.add_argument(
"-ipc_conn",
dest="ipc_conn",
default=True,
type=str_arg_to_bool,
help="Table name name to use in omniscidb server.",
)
optional.add_argument(
"-debug_timer",
dest="debug_timer",
default=False,
type=str_arg_to_bool,
help="Enable fine-grained query execution timers for debug.",
)
optional.add_argument(
"-columnar_output",
dest="columnar_output",
default=True,
type=str_arg_to_bool,
help=
"Allows OmniSci Core to directly materialize intermediate projections \
and the final ResultSet in Columnar format where appropriate.",
)
optional.add_argument(
"-lazy_fetch",
dest="lazy_fetch",
default=None,
type=str_arg_to_bool,
help="[lazy_fetch help message]",
)
optional.add_argument(
"-multifrag_rs",
dest="multifrag_rs",
default=None,
type=str_arg_to_bool,
help="[multifrag_rs help message]",
)
optional.add_argument(
"-fragments_size",
dest="fragments_size",
default=None,
nargs="*",
type=int,
help=
"Number of rows per fragment that is a unit of the table for query processing. \
Should be specified for each table in workload",
)
optional.add_argument(
"-omnisci_run_kwargs",
dest="omnisci_run_kwargs",
default={},
metavar="KEY1=VAL1,KEY2=VAL2...",
action=KeyValueListParser,
help="options to start omnisci server",
)
# Additional information
optional.add_argument(
"-commit_omnisci",
dest="commit_omnisci",
default="1234567890123456789012345678901234567890",
help="Omnisci commit hash used for benchmark.",
)
optional.add_argument(
"-commit_ibis",
dest="commit_ibis",
default="1234567890123456789012345678901234567890",
help="Ibis commit hash used for benchmark.",
)
optional.add_argument(
"-commit_omniscripts",
dest="commit_omniscripts",
default="1234567890123456789012345678901234567890",
help="Omniscripts commit hash used for benchmark.",
)
optional.add_argument(
"-commit_modin",
dest="commit_modin",
default="1234567890123456789012345678901234567890",
help="Modin commit hash used for benchmark.",
)
optional.add_argument(
"-debug_mode",
dest="debug_mode",
default=False,
type=str_arg_to_bool,
help="Enable debug mode.",
)
try:
os.environ["PYTHONIOENCODING"] = "UTF-8"
os.environ["PYTHONUNBUFFERED"] = "1"
omnisci_server_worker = None
omnisci_server = None
args = parser.parse_args()
launch_omnisci_server = (not args.no_ibis and args.bench_name
in benchmarks_with_ibis_queries)
if args.port == port_default_value:
args.port = find_free_port()
if args.http_port == port_default_value:
args.http_port = find_free_port()
if args.calcite_port == port_default_value:
args.calcite_port = find_free_port()
run_benchmark = __import__(benchmarks[args.bench_name]).run_benchmark
parameters = {
"data_file": args.data_file,
"dfiles_num": args.dfiles_num,
"no_ml": args.no_ml,
"no_ibis": args.no_ibis,
"optimizer": args.optimizer,
"pandas_mode": args.pandas_mode,
"ray_tmpdir": args.ray_tmpdir,
"ray_memory": args.ray_memory,
"gpu_memory": args.gpu_memory,
"validation": args.validation,
"no_pandas": args.no_pandas,
"debug_mode": args.debug_mode,
"extended_functionality": args.extended_functionality,
}
if launch_omnisci_server:
if args.executable is None:
parser.error(
"Omnisci executable should be specified with -e/--executable for Ibis part"
)
from server import OmnisciServer
omnisci_server = OmnisciServer(
omnisci_executable=args.executable,
omnisci_port=args.port,
http_port=args.http_port,
calcite_port=args.calcite_port,
database_name=args.database_name,
omnisci_cwd=args.omnisci_cwd,
user=args.user,
password=args.password,
debug_timer=args.debug_timer,
columnar_output=args.columnar_output,
lazy_fetch=args.lazy_fetch,
multifrag_rs=args.multifrag_rs,
omnisci_run_kwargs=args.omnisci_run_kwargs,
)
parameters["database_name"] = args.database_name
parameters["table"] = args.table
parameters["dnd"] = args.dnd
parameters["dni"] = args.dni
parameters["import_mode"] = args.import_mode
parameters["fragments_size"] = args.fragments_size
if parameters["validation"] and (parameters["no_pandas"]
or parameters["no_ibis"]):
parameters["validation"] = False
print(
"WARNING: validation was turned off as it requires both sides to compare."
)
etl_results = []
ml_results = []
print(parameters)
run_id = int(round(time.time()))
for iter_num in range(1, args.iterations + 1):
print(f"Iteration #{iter_num}")
if launch_omnisci_server:
from server_worker import OmnisciServerWorker
omnisci_server_worker = OmnisciServerWorker(omnisci_server)
parameters["omnisci_server_worker"] = omnisci_server_worker
parameters["ipc_connection"] = args.ipc_conn
omnisci_server.launch()
parameters = {
key:
os.path.expandvars(value) if isinstance(value, str) else value
for key, value in parameters.items()
}
benchmark_results = run_benchmark(parameters)
if launch_omnisci_server:
omnisci_server_worker.terminate()
omnisci_server.terminate()
additional_fields_for_reporting = {
"ETL": {
"Iteration": iter_num,
"run_id": run_id
},
"ML": {
"Iteration": iter_num,
"run_id": run_id
},
}
etl_ml_results = refactor_results_for_reporting(
benchmark_results=benchmark_results,
ignore_fields_for_results_unit_conversion=
ignore_fields_for_results_unit_conversion,
additional_fields=additional_fields_for_reporting,
reporting_unit="ms",
)
etl_results = list(etl_ml_results["ETL"])
ml_results = list(etl_ml_results["ML"])
# Reporting to MySQL database
if args.db_user is not None:
if iter_num == 1:
db = mysql.connector.connect(
host=args.db_server,
port=args.db_port,
user=args.db_user,
passwd=args.db_pass,
db=args.db_name,
)
reporting_init_fields = {
"OmnisciCommitHash": args.commit_omnisci,
"IbisCommitHash": args.commit_ibis,
"OmniscriptsCommitHash": args.commit_omniscripts,
"ModinCommitHash": args.commit_modin,
}
reporting_fields_benchmark_etl = {
x: "VARCHAR(500) NOT NULL"
for x in etl_results[0]
}
if len(etl_results) != 1:
reporting_fields_benchmark_etl.update({
x: "VARCHAR(500) NOT NULL"
for x in etl_results[1]
})
db_reporter_etl = DbReport(
db,
args.db_table_etl,
reporting_fields_benchmark_etl,
reporting_init_fields,
)
if len(ml_results) != 0:
reporting_fields_benchmark_ml = {
x: "VARCHAR(500) NOT NULL"
for x in ml_results[0]
}
if len(ml_results) != 1:
reporting_fields_benchmark_ml.update({
x: "VARCHAR(500) NOT NULL"
for x in ml_results[1]
})
db_reporter_ml = DbReport(
db,
args.db_table_ml,
reporting_fields_benchmark_ml,
reporting_init_fields,
)
if iter_num == args.iterations:
for result_etl in etl_results:
remove_fields_from_dict(
result_etl, ignore_fields_for_bd_report_etl)
db_reporter_etl.submit(result_etl)
if len(ml_results) != 0:
for result_ml in ml_results:
remove_fields_from_dict(
result_ml, ignore_fields_for_bd_report_ml)
db_reporter_ml.submit(result_ml)
finally:
if omnisci_server_worker:
omnisci_server_worker.terminate()
if omnisci_server:
omnisci_server.terminate()
def main():
args = None
omnisci_server_worker = None
train_final, test_final = None, None
parser, args, skip_rows = get_args()
try:
if not args.no_ibis:
sys.path.append(os.path.join(os.path.dirname(__file__), ".."))
from server import OmnisciServer
if args.omnisci_executable is None:
parser.error(
"Omnisci executable should be specified with -e/--executable"
)
omnisci_server = OmnisciServer(
omnisci_executable=args.omnisci_executable,
omnisci_port=args.omnisci_port,
database_name=args.name,
omnisci_cwd=args.omnisci_cwd,
user=args.user,
password=args.password,
)
omnisci_server.launch()
from server_worker import OmnisciServerWorker
omnisci_server_worker = OmnisciServerWorker(omnisci_server)
train_final, test_final, etl_times = etl_all_ibis(
filename=args.dataset_path,
database_name=args.name,
omnisci_server_worker=omnisci_server_worker,
delete_old_database=not args.dnd,
create_new_table=not args.dni,
skip_rows=skip_rows,
validation=args.val,
)
ml_data, etl_times = split_step(train_final, test_final, etl_times)
print_times(etl_times)
omnisci_server_worker.terminate()
omnisci_server_worker = None
if not args.no_ml:
print("using ml with dataframes from ibis")
ml_times = ml(ml_data)
print_times(ml_times)
ptrain_final, ptest_final, petl_times = etl_all_pandas(
args.dataset_path, skip_rows
)
ml_data, petl_times = split_step(ptrain_final, ptest_final, petl_times)
print_times(petl_times)
if not args.no_ml:
print("using ml with dataframes from pandas")
ml_times = ml(ml_data)
print_times(ml_times)
if args.val and (not train_final is None) and (not test_final is None):
print("validating result ...")
compare_dataframes((train_final, test_final), (ptrain_final, ptest_final))
finally:
if omnisci_server_worker:
omnisci_server_worker.terminate()
def main():
omniscript_path = os.path.dirname(__file__)
args = None
omnisci_server = None
port_default_value = -1
benchmarks = ["ny_taxi", "santander", "census", "plasticc"]
parser = argparse.ArgumentParser(
description="Run internal tests from ibis project")
optional = parser._action_groups.pop()
required = parser.add_argument_group("required arguments")
parser._action_groups.append(optional)
required.add_argument(
"-bench_name",
dest="bench_name",
choices=benchmarks,
help="Benchmark name.",
required=True,
)
required.add_argument(
"-data_file",
dest="data_file",
help="A datafile that should be loaded.",
required=True,
)
optional.add_argument(
"-dfiles_num",
dest="dfiles_num",
default=1,
type=int,
help="Number of datafiles to input into database for processing.",
)
optional.add_argument(
"-iterations",
dest="iterations",
default=1,
type=int,
help=
"Number of iterations to run every query. Best result is selected.",
)
optional.add_argument("-dnd",
default=False,
type=str_arg_to_bool,
help="Do not delete old table.")
optional.add_argument(
"-dni",
default=False,
type=str_arg_to_bool,
help="Do not create new table and import any data from CSV files.",
)
optional.add_argument(
"-validation",
dest="validation",
default=False,
type=str_arg_to_bool,
help=
"validate queries results (by comparison with Pandas queries results).",
)
optional.add_argument(
"-optimizer",
choices=["intel", "stock"],
dest="optimizer",
default="intel",
help="Which optimizer is used",
)
optional.add_argument(
"-no_ibis",
default=False,
type=str_arg_to_bool,
help="Do not run Ibis benchmark, run only Pandas (or Modin) version",
)
optional.add_argument(
"-pandas_mode",
choices=["Pandas", "Modin_on_ray", "Modin_on_dask", "Modin_on_python"],
default="Pandas",
help=
"Specifies which version of Pandas to use: plain Pandas, Modin runing on Ray or on Dask",
)
optional.add_argument(
"-ray_tmpdir",
default="/tmp",
help=
"Location where to keep Ray plasma store. It should have enough space to keep -ray_memory",
)
optional.add_argument(
"-ray_memory",
default=200 * 1024 * 1024 * 1024,
help="Size of memory to allocate for Ray plasma store",
)
optional.add_argument(
"-no_ml",
default=False,
type=str_arg_to_bool,
help="Do not run machine learning benchmark, only ETL part",
)
optional.add_argument(
"-gpu_memory",
dest="gpu_memory",
type=int,
help=
"specify the memory of your gpu, default 16. (This controls the lines to be used. Also work for CPU version. )",
default=16,
)
# MySQL database parameters
optional.add_argument(
"-db_server",
dest="db_server",
default="localhost",
help="Host name of MySQL server.",
)
optional.add_argument(
"-db_port",
dest="db_port",
default=3306,
type=int,
help="Port number of MySQL server.",
)
optional.add_argument(
"-db_user",
dest="db_user",
help="Username to use to connect to MySQL database. "
"If user name is specified, script attempts to store results in MySQL "
"database using other -db-* parameters.",
)
optional.add_argument(
"-db_pass",
dest="db_pass",
default="omniscidb",
help="Password to use to connect to MySQL database.",
)
optional.add_argument(
"-db_name",
dest="db_name",
default="omniscidb",
help="MySQL database to use to store benchmark results.",
)
optional.add_argument(
"-db_table_etl",
dest="db_table_etl",
help="Table to use to store ETL results for this benchmark.",
)
optional.add_argument(
"-db_table_ml",
dest="db_table_ml",
help="Table to use to store ML results for this benchmark.",
)
# Omnisci server parameters
optional.add_argument(
"-executable",
dest="executable",
help="Path to omnisci_server executable.",
)
optional.add_argument(
"-omnisci_cwd",
dest="omnisci_cwd",
help="Path to omnisci working directory. "
"By default parent directory of executable location is used. "
"Data directory is used in this location.",
)
optional.add_argument(
"-port",
dest="port",
default=port_default_value,
type=int,
help="TCP port number to run omnisci_server on.",
)
optional.add_argument(
"-http_port",
dest="http_port",
default=port_default_value,
type=int,
help="HTTP port number to run omnisci_server on.",
)
optional.add_argument(
"-calcite_port",
dest="calcite_port",
default=port_default_value,
type=int,
help="Calcite port number to run omnisci_server on.",
)
optional.add_argument(
"-user",
dest="user",
default="admin",
help="User name to use on omniscidb server.",
)
optional.add_argument(
"-password",
dest="password",
default="HyperInteractive",
help="User password to use on omniscidb server.",
)
optional.add_argument(
"-database_name",
dest="database_name",
default="omnisci",
help="Database name to use in omniscidb server.",
)
optional.add_argument(
"-table",
dest="table",
default="benchmark_table",
help="Table name name to use in omniscidb server.",
)
optional.add_argument(
"-ipc_conn",
dest="ipc_connection",
default=True,
type=str_arg_to_bool,
help="Table name name to use in omniscidb server.",
)
# Additional information
optional.add_argument(
"-commit_omnisci",
dest="commit_omnisci",
default="1234567890123456789012345678901234567890",
help="Omnisci commit hash to use for benchmark.",
)
optional.add_argument(
"-commit_ibis",
dest="commit_ibis",
default="1234567890123456789012345678901234567890",
help="Ibis commit hash to use for benchmark.",
)
try:
os.environ["PYTHONIOENCODING"] = "UTF-8"
os.environ["PYTHONUNBUFFERED"] = "1"
omnisci_server_worker = None
args = parser.parse_args()
if args.port == port_default_value:
args.port = find_free_port()
if args.http_port == port_default_value:
args.http_port = find_free_port()
if args.calcite_port == port_default_value:
args.calcite_port = find_free_port()
if args.bench_name == "ny_taxi":
from taxi import run_benchmark
elif args.bench_name == "santander":
from santander import run_benchmark
elif args.bench_name == "census":
from census import run_benchmark
elif args.bench_name == "plasticc":
from plasticc import run_benchmark
parameters = {
"data_file": args.data_file,
"dfiles_num": args.dfiles_num,
"no_ml": args.no_ml,
"no_ibis": args.no_ibis,
"optimizer": args.optimizer,
"pandas_mode": args.pandas_mode,
"ray_tmpdir": args.ray_tmpdir,
"ray_memory": args.ray_memory,
"gpu_memory": args.gpu_memory,
}
if not args.no_ibis:
if args.executable is None:
parser.error(
"Omnisci executable should be specified with -e/--executable for Ibis part"
)
omnisci_server = OmnisciServer(
omnisci_executable=args.executable,
omnisci_port=args.port,
http_port=args.http_port,
calcite_port=args.calcite_port,
database_name=args.database_name,
user=args.user,
password=args.password,
)
parameters["database_name"] = args.database_name
parameters["table"] = args.table
parameters["dnd"] = args.dnd
parameters["dni"] = args.dni
parameters["validation"] = args.validation
etl_results = []
ml_results = []
print(parameters)
run_id = int(round(time.time()))
for iter_num in range(1, args.iterations + 1):
print(f"Iteration #{iter_num}")
if not args.no_ibis:
omnisci_server_worker = OmnisciServerWorker(omnisci_server)
parameters["omnisci_server_worker"] = omnisci_server_worker
parameters["ipc_connection"] = args.ipc_connection
omnisci_server.launch()
result = run_benchmark(parameters)
if not args.no_ibis:
omnisci_server.terminate()
for backend_res in result["ETL"]:
if backend_res:
backend_res["Iteration"] = iter_num
backend_res["run_id"] = run_id
etl_results.append(backend_res)
for backend_res in result["ML"]:
if backend_res:
backend_res["Iteration"] = iter_num
backend_res["run_id"] = run_id
ml_results.append(backend_res)
# Reporting to MySQL database
if args.db_user is not None:
if iter_num == 1:
db = mysql.connector.connect(
host=args.db_server,
port=args.db_port,
user=args.db_user,
passwd=args.db_pass,
db=args.db_name,
)
reporting_init_fields = {
"OmnisciCommitHash": args.commit_omnisci,
"IbisCommitHash": args.commit_ibis
}
reporting_fields_benchmark_etl = {
x: "VARCHAR(500) NOT NULL"
for x in etl_results[0]
}
if len(etl_results) is not 1:
reporting_fields_benchmark_etl.update({
x: "VARCHAR(500) NOT NULL"
for x in etl_results[1]
})
db_reporter_etl = DbReport(db, args.db_table_etl,
reporting_fields_benchmark_etl,
reporting_init_fields)
if len(ml_results) is not 0:
reporting_fields_benchmark_ml = {
x: "VARCHAR(500) NOT NULL"
for x in ml_results[0]
}
if len(ml_results) is not 1:
reporting_fields_benchmark_ml.update({
x: "VARCHAR(500) NOT NULL"
for x in ml_results[1]
})
db_reporter_ml = DbReport(
db, args.db_table_ml,
reporting_fields_benchmark_ml,
reporting_init_fields)
for result_etl in etl_results:
db_reporter_etl.submit(result_etl)
if len(ml_results) is not 0:
for result_ml in ml_results:
db_reporter_ml.submit(result_ml)
except Exception:
traceback.print_exc(file=sys.stdout)
sys.exit(1)
finally:
if omnisci_server_worker:
omnisci_server_worker.terminate()
def etl_ibis(args, run_import_queries, columns_names, columns_types, validation=False):
filename = args.file
database_name = args.name
table_name = args.table
delete_old_database = not args.dnd
create_new_table = not args.dni
run_import_queries = str_arg_to_bool(run_import_queries)
validation = str_arg_to_bool(validation)
tmp_table_name = "tmp_table"
etl_times = {"t_groupby_merge_where": 0.0, "t_train_test_split": 0.0, "t_etl": 0.0}
if run_import_queries:
etl_times_import = {
"t_readcsv_by_ibis": 0.0,
"t_readcsv_by_COPY": 0.0,
"t_readcsv_by_FSI": 0.0,
}
etl_times.update(etl_times_import)
omnisci_server = OmnisciServer(
omnisci_executable=args.omnisci_executable,
omnisci_port=args.omnisci_port,
database_name=args.name,
user=args.user,
password=args.password,
debug_timer=True,
columnar_output=args.server_columnar_output,
lazy_fetch=args.server_lazy_fetch,
)
omnisci_server.launch()
import ibis
from server_worker import OmnisciServerWorker
omnisci_server_worker = OmnisciServerWorker(omnisci_server)
omnisci_server_worker.create_database(
database_name, delete_if_exists=delete_old_database
)
time.sleep(2)
omnisci_server_worker.connect_to_server()
if run_import_queries:
# SQL statemnts preparation for data file import queries
connect_to_db_sql_template = "\c {0} admin HyperInteractive"
create_table_sql_template = """
CREATE TABLE {0} ({1});
"""
import_by_COPY_sql_template = """
COPY {0} FROM '{1}' WITH (header='{2}');
"""
import_by_FSI_sql_template = """
CREATE TEMPORARY TABLE {0} ({1}) WITH (storage_type='CSV:{2}');
"""
drop_table_sql_template = """
DROP TABLE IF EXISTS {0};
"""
import_query_cols_list = (
["ID_code TEXT ENCODING NONE, \n", "target SMALLINT, \n"]
+ ["var_%s DOUBLE, \n" % i for i in range(199)]
+ ["var_199 DOUBLE"]
)
import_query_cols_str = "".join(import_query_cols_list)
connect_to_db_sql = connect_to_db_sql_template.format(database_name)
create_table_sql = create_table_sql_template.format(
tmp_table_name, import_query_cols_str
)
import_by_COPY_sql = import_by_COPY_sql_template.format(
tmp_table_name, filename, "true"
)
import_by_FSI_sql = import_by_FSI_sql_template.format(
tmp_table_name, import_query_cols_str, filename
)
# data file import by ibis
columns_types_import_query = ["string", "int64"] + [
"float64" for _ in range(200)
]
schema_table_import = ibis.Schema(
names=columns_names, types=columns_types_import_query
)
omnisci_server_worker.get_conn().create_table(
table_name=tmp_table_name,
schema=schema_table_import,
database=database_name,
fragment_size=args.fragment_size,
)
table_import_query = omnisci_server_worker.database(database_name).table(tmp_table_name)
t0 = timer()
table_import_query.read_csv(filename, delimiter=",")
etl_times["t_readcsv_by_ibis"] = timer() - t0
# data file import by FSI
omnisci_server_worker.drop_table(tmp_table_name)
t0 = timer()
omnisci_server_worker.execute_sql_query(import_by_FSI_sql)
etl_times["t_readcsv_by_FSI"] = timer() - t0
omnisci_server_worker.drop_table(tmp_table_name)
# data file import by SQL COPY statement
omnisci_server_worker.execute_sql_query(create_table_sql)
t0 = timer()
omnisci_server_worker.execute_sql_query(import_by_COPY_sql)
etl_times["t_readcsv_by_COPY"] = timer() - t0
omnisci_server_worker.drop_table(tmp_table_name)
if create_new_table:
# Create table and import data for ETL queries
schema_table = ibis.Schema(names=columns_names, types=columns_types)
omnisci_server_worker.get_conn().create_table(
table_name=table_name,
schema=schema_table,
database=database_name,
fragment_size=args.fragment_size,
)
table_import = omnisci_server_worker.database(database_name).table(table_name)
table_import.read_csv(filename, delimiter=",")
if args.server_conn_type == "regular":
omnisci_server_worker.connect_to_server()
elif args.server_conn_type == "ipc":
omnisci_server_worker.ipc_connect_to_server()
else:
print("Wrong connection type is specified!")
sys.exit(0)
db = omnisci_server_worker.database(database_name)
table = db.table(table_name)
# group_by/count, merge (join) and filtration queries
# We are making 400 columns and then insert them into original table thus avoiding
# nested sql requests
t0 = timer()
count_cols = []
orig_cols = ["ID_code", "target"] + ['var_%s'%i for i in range(200)]
cast_cols = []
cast_cols.append(table["target"].cast("int64").name("target0"))
gt1_cols = []
for i in range(200):
col = "var_%d" % i
col_count = "var_%d_count" % i
col_gt1 = "var_%d_gt1" % i
w = ibis.window(group_by=col)
count_cols.append(table[col].count().over(w).name(col_count))
gt1_cols.append(
ibis.case()
.when(
table[col].count().over(w).name(col_count) > 1,
table[col].cast("float32"),
)
.else_(ibis.null())
.end()
.name("var_%d_gt1" % i)
)
cast_cols.append(table[col].cast("float32").name(col))
table = table.mutate(count_cols)
table = table.drop(orig_cols)
table = table.mutate(gt1_cols)
table = table.mutate(cast_cols)
table_df = table.execute()
etl_times["t_groupby_merge_where"] = timer() - t0
# rows split query
t0 = timer()
training_part, validation_part = table_df[:-10000], table_df[-10000:]
etl_times["t_train_test_split"] = timer() - t0
etl_times["t_etl"] = etl_times["t_groupby_merge_where"] + etl_times["t_train_test_split"]
x_train = training_part.drop(['target0'],axis=1)
y_train = training_part['target0']
x_valid = validation_part.drop(['target0'],axis=1)
y_valid = validation_part['target0']
omnisci_server.terminate()
omnisci_server = None
return x_train, y_train, x_valid, y_valid, etl_times
def main():
args = None
omnisci_server = None
parser, args, skip_rows = get_args()
try:
if not args.no_ibis:
sys.path.append(os.path.join(os.path.dirname(__file__), ".."))
from server import OmnisciServer
if args.omnisci_executable is None:
parser.error(
"Omnisci executable should be specified with -e/--executable"
)
omnisci_server = OmnisciServer(
omnisci_executable=args.omnisci_executable,
omnisci_port=args.omnisci_port,
database_name=args.name,
omnisci_cwd=args.omnisci_cwd,
user=args.user,
password=args.password,
)
omnisci_server.launch()
from server_worker import OmnisciServerWorker
omnisci_server_worker = OmnisciServerWorker(omnisci_server)
(
X_train,
y_train,
X_test,
y_test,
Xt,
classes,
class_weights,
etl_times,
) = etl_all_ibis(
filename=args.dataset_path,
database_name=args.name,
omnisci_server_worker=omnisci_server_worker,
delete_old_database=not args.dnd,
create_new_table=not args.dni,
skip_rows=skip_rows,
)
print_times(etl_times)
omnisci_server.terminate()
omnisci_server = None
if not args.no_ml:
print("using ml with dataframes from ibis")
ml_times = ml(X_train, y_train, X_test, y_test, Xt, classes,
class_weights)
print_times(ml_times)
(
X_train,
y_train,
X_test,
y_test,
Xt,
classes,
class_weights,
etl_times,
) = etl_all_pandas(args.dataset_path, skip_rows)
print_times(etl_times)
if not args.no_ml:
print("using ml with dataframes from pandas")
ml_times = ml(X_train, y_train, X_test, y_test, Xt, classes,
class_weights)
print_times(ml_times)
if args.val:
# this isn't work so easy
# compare_dataframes(ibis_df=(X_train_ibis, y_train_ibis), pandas_df=(X, y))
print("validate by ml results")
except Exception as err:
print("Failed: ", err)
sys.exit(1)
finally:
if omnisci_server:
omnisci_server.terminate()
print("Bad number of data files specified", args.df)
sys.exit(1)
if args.i < 1:
print("Bad number of iterations specified", args.i)
database_name = args.n
omnisci_server = OmnisciServer(
omnisci_executable=args.e,
omnisci_port=args.port,
database_name=database_name,
user=args.u,
password=args.p,
)
omnisci_server.launch()
omnisci_server_worker = OmnisciServerWorker(omnisci_server)
time.sleep(2)
omnisci_server_worker.connect_to_server()
taxibench_columns_names = [
"trip_id",
"vendor_id",
"pickup_datetime",
"dropoff_datetime",
"store_and_fwd_flag",
"rate_code_id",
"pickup_longitude",
"pickup_latitude",
"dropoff_longitude",
"dropoff_latitude",
args = parser.parse_args()
if args.df <= 0:
print("Bad number of data files specified", args.df)
sys.exit(1)
if args.i < 1:
print("Bad number of iterations specified", args.i)
database_name = args.n
omnisci_server = OmnisciServer(omnisci_executable=args.e,
omnisci_port=args.port,
database_name=database_name,
user=args.u,
password=args.p)
omnisci_server.launch()
omnisci_server_worker = OmnisciServerWorker(omnisci_server)
time.sleep(2)
conn = omnisci_server_worker.connect_to_server()
taxibench_columns_names = [
"trip_id", "vendor_id", "pickup_datetime", "dropoff_datetime",
"store_and_fwd_flag", "rate_code_id", "pickup_longitude",
"pickup_latitude", "dropoff_longitude", "dropoff_latitude",
"passenger_count", "trip_distance", "fare_amount", "extra", "mta_tax",
"tip_amount", "tolls_amount", "ehail_fee", "improvement_surcharge",
"total_amount", "payment_type", "trip_type", "pickup", "dropoff",
"cab_type", "precipitation", "snow_depth", "snowfall",
"max_temperature", "min_temperature", "average_wind_speed",
"pickup_nyct2010_gid", "pickup_ctlabel", "pickup_borocode",
"pickup_boroname", "pickup_ct2010", "pickup_boroct2010",
"var_" + str(index) for index in range(200)
]
datafile_columns_types = ["string", "int64"
] + ["float64" for _ in range(200)]
schema_train = ibis.Schema(names=datafile_columns_names,
types=datafile_columns_types)
database_name = args.n
omnisci_server = OmnisciServer(omnisci_executable=args.e,
omnisci_port=args.port,
database_name=database_name,
user=args.u,
password=args.p)
omnisci_server.launch()
omnisci_server_worker = OmnisciServerWorker(omnisci_server)
time.sleep(2)
conn = omnisci_server_worker.connect_to_server()
db_reporter = None
if args.db_user is not "":
print("Connecting to database")
db = mysql.connector.connect(host=args.db_server,
port=args.db_port,
user=args.db_user,
passwd=args.db_pass,
db=args.db_name)
db_reporter = DbReport(
db, args.db_table, {
'QueryName': 'VARCHAR(500) NOT NULL',