3ade0b9fe3
Generate random data with integers. The approach is as follows: - There is one collection for each different cardinality. All collections contain the same fields. - Each field contains the data generated from a certain data distribution. The data could be anything - same type, mixed types, same mathematical distribution (e.g. normal), or a mixed distribution. - The committed configuration file, and the corresponding data file are reduced to only two small collections. For actual experiments one needs to add more data sizes, and re-generate the data locally. This is done so that Evergreen tests can run fast, and to reduce the size of the git repository. - All data is saved in a single JavaScript file: jstests/query_golden/libs/data/ce_accuracy_test.data, with a corresponding schema file jstests/query_golden/libs/data/ce_accuracy_test.schema. - The data file is a JavaScript file that can be loaded directly inside a JS test. When loading this file, it creates a global variable dataSet. The reason is that this is the only way to load an external JSON file that doesn't need to install external tools in Evergreen.
121 lines
5.6 KiB
Python
121 lines
5.6 KiB
Python
# Copyright (C) 2022-present MongoDB, Inc.
|
|
#
|
|
# This program is free software: you can redistribute it and/or modify
|
|
# it under the terms of the Server Side Public License, version 1,
|
|
# as published by MongoDB, Inc.
|
|
#
|
|
# This program is distributed in the hope that it will be useful,
|
|
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
# Server Side Public License for more details.
|
|
#
|
|
# You should have received a copy of the Server Side Public License
|
|
# along with this program. If not, see
|
|
# <http://www.mongodb.com/licensing/server-side-public-license>.
|
|
#
|
|
# As a special exception, the copyright holders give permission to link the
|
|
# code of portions of this program with the OpenSSL library under certain
|
|
# conditions as described in each individual source file and distribute
|
|
# linked combinations including the program with the OpenSSL library. You
|
|
# must comply with the Server Side Public License in all respects for
|
|
# all of the code used other than as permitted herein. If you modify file(s)
|
|
# with this exception, you may extend this exception to your version of the
|
|
# file(s), but you are not obligated to do so. If you do not wish to do so,
|
|
# delete this exception statement from your version. If you delete this
|
|
# exception statement from all source files in the program, then also delete
|
|
# it in the license file.
|
|
#
|
|
"""Configuration of data generation for CE accuracy testing."""
|
|
|
|
from pathlib import Path
|
|
import random
|
|
import config
|
|
from random_generator import RangeGenerator, DataType, RandomDistribution, ArrayRandomDistribution
|
|
|
|
__all__ = ['database_config', 'data_generator_config']
|
|
|
|
################################################################################
|
|
# Data distributions
|
|
################################################################################
|
|
|
|
# Ranges
|
|
|
|
# 1K unique numbers with different distances
|
|
range_int_1000_1 = RangeGenerator(DataType.INTEGER, 0, 1000, 1)
|
|
range_int_1000_10 = RangeGenerator(DataType.INTEGER, 0, 10000, 10)
|
|
range_int_1000_100 = RangeGenerator(DataType.INTEGER, 0, 100000, 100)
|
|
range_int_1000_1000 = RangeGenerator(DataType.INTEGER, 0, 1000000, 1000)
|
|
# 10K unique numbers with different distances
|
|
range_int_10000_1 = RangeGenerator(DataType.INTEGER, 0, 10000, 1)
|
|
range_int_10000_10 = RangeGenerator(DataType.INTEGER, 0, 100000, 10)
|
|
range_int_10000_100 = RangeGenerator(DataType.INTEGER, 0, 1000000, 100)
|
|
range_int_10000_1000 = RangeGenerator(DataType.INTEGER, 0, 10000000, 1000)
|
|
int_ranges = [
|
|
range_int_1000_1, range_int_1000_10, range_int_1000_100, range_int_1000_1000, range_int_10000_1,
|
|
range_int_10000_10, range_int_10000_100, range_int_10000_1000
|
|
]
|
|
|
|
# Various integer distributions
|
|
int_distributions = {}
|
|
for int_range in int_ranges:
|
|
int_distributions[
|
|
f'uniform_int_{int_range.interval_end - int_range.interval_begin}_{int_range.step}'] = RandomDistribution.uniform(
|
|
int_range)
|
|
int_distributions[
|
|
f'normal_int_{int_range.interval_end - int_range.interval_begin}_{int_range.step}'] = RandomDistribution.normal(
|
|
int_range)
|
|
int_distributions[
|
|
f'chi2_int_{int_range.interval_end - int_range.interval_begin}_{int_range.step}'] = RandomDistribution.noncentral_chisquare(
|
|
int_range)
|
|
|
|
# Mixes of distributions with different NDV and value distances
|
|
|
|
uniform_int_mix_1 = [
|
|
int_distributions['uniform_int_1000_1'], int_distributions['uniform_int_100000_100'],
|
|
int_distributions['uniform_int_10000000_1000']
|
|
]
|
|
int_distributions['mixed_int_uniform_1'] = RandomDistribution.mixed(children=uniform_int_mix_1,
|
|
weight=[0.1, 0.1, 0.1])
|
|
|
|
unf_norm_chi_int_mix_1 = [
|
|
int_distributions['uniform_int_10000_10'], int_distributions['uniform_int_1000000_100'],
|
|
int_distributions['normal_int_10000_10'], int_distributions['normal_int_1000000_100'],
|
|
int_distributions['chi2_int_10000_10'], int_distributions['chi2_int_10000000_1000']
|
|
]
|
|
|
|
int_distributions['mixed_int_unf_norm_chi_1'] = RandomDistribution.mixed(
|
|
children=unf_norm_chi_int_mix_1, weight=[1, 1, 1, 1, 1, 1])
|
|
|
|
################################################################################
|
|
# Collection templates
|
|
################################################################################
|
|
#collection_cardinalities = [100, 1000, 10000, 100000]
|
|
collection_cardinalities = [100, 1000]
|
|
|
|
field_templates = []
|
|
|
|
for dist in int_distributions:
|
|
field_templates.append(
|
|
config.FieldTemplate(name=f'{dist}', data_type=config.DataType.INTEGER,
|
|
distribution=int_distributions[dist], indexed=True))
|
|
|
|
ce_data = config.CollectionTemplate(name="ce_data", fields=field_templates, compound_indexes=[],
|
|
cardinalities=collection_cardinalities)
|
|
|
|
################################################################################
|
|
# Database settings
|
|
################################################################################
|
|
|
|
database_config = config.DatabaseConfig(
|
|
connection_string='mongodb://localhost', database_name='ce_accuracy_test', dump_path=Path(
|
|
'..', '..', 'jstests', 'query_golden', 'libs', 'data'),
|
|
restore_from_dump=config.RestoreMode.NEVER, dump_on_exit=False)
|
|
|
|
################################################################################
|
|
# Data Generator settings
|
|
################################################################################
|
|
|
|
data_generator_config = config.DataGeneratorConfig(
|
|
enabled=True, create_indexes=False, batch_size=10000, collection_templates=[ce_data],
|
|
write_mode=config.WriteMode.REPLACE, collection_name_with_card=True)
|