private void FillRepositoryWithPreviousResults(IMetricsRepository repository)
{
Enumerable.Range(1, 31)
.ToList()
.ForEach(pastDay =>
{
var pastResultsEU = new Dictionary <IAnalyzer <IMetric>, IMetric>
{
{ Initializers.Size(), new DoubleMetric(MetricEntity.Dataset, "*", "Size", Math.Floor(pastDay / 3.0)) },
{ Initializers.Mean("sales"), new DoubleMetric(MetricEntity.Column, "sales", "Mean", pastDay * 7) }
};
var pastResultsNA = new Dictionary <IAnalyzer <IMetric>, IMetric>
{
{ Initializers.Size(), new DoubleMetric(MetricEntity.Dataset, "*", "Size", pastDay) },
{ Initializers.Mean("sales"), new DoubleMetric(MetricEntity.Column, "sales", "Mean", pastDay * 9) }
};
var analyzerContextEU = new AnalyzerContext(pastResultsEU);
var analyzerContextNA = new AnalyzerContext(pastResultsNA);
long dateTime = CreateDate(2018, 7, pastDay);
repository.Save(new ResultKey(dateTime, new Dictionary <string, string> {
{ "marketplace", "EU" }
}),
analyzerContextEU);
repository.Save(new ResultKey(dateTime, new Dictionary <string, string> {
{ "marketplace", "NA" }
}),
analyzerContextNA);
});
}
private VerificationResult CreateAnomalyChecksAndRunEverything(
DataFrame data,
IMetricsRepository repository,
Check otherCheck,
IEnumerable <IAnalyzer <IMetric> > additionalRequiredAnalyzers)
{
// We only want to use historic data with the EU tag for the anomaly checks since the new
// data point is from the EU marketplace
var filterEU = new Dictionary <string, string> {
{ "marketplace", "EU" }
};
// We only want to use data points before the date time associated with the current
// data point and only ones that are from 2018
var afterDateTime = CreateDate(2018, 1, 1);
var beforeDateTime = CreateDate(2018, 8, 1);
// Config for the size anomaly check
var sizeAnomalyCheckConfig = new AnomalyCheckConfig(CheckLevel.Error, "Size only increases",
filterEU, afterDateTime, beforeDateTime);
var sizeAnomalyDetectionStrategy = new AbsoluteChangeStrategy(0);
// Config for the mean sales anomaly check
var meanSalesAnomalyCheckConfig = new AnomalyCheckConfig(
CheckLevel.Warning,
"Sales mean within 2 standard deviations",
filterEU,
afterDateTime,
beforeDateTime
);
var meanSalesAnomalyDetectionStrategy = new OnlineNormalStrategy(upperDeviationFactor: 2, lowerDeviationFactor: Option <double> .None,
ignoreAnomalies: false);
// ResultKey to be used when saving the results of this run
var currentRunResultKey =
new ResultKey(CreateDate(2018, 8, 1), new Dictionary <string, string> {
{ "marketplace", "EU" }
});
return(new VerificationSuite()
.OnData(data)
.AddCheck(otherCheck)
.AddRequiredAnalyzers(additionalRequiredAnalyzers)
.UseRepository(repository)
// Add the Size anomaly check
.AddAnomalyCheck(sizeAnomalyDetectionStrategy, Initializers.Size(), sizeAnomalyCheckConfig)
// Add the Mean sales anomaly check
.AddAnomalyCheck(meanSalesAnomalyDetectionStrategy, Initializers.Mean("sales"),
meanSalesAnomalyCheckConfig)
// Save new data point in the repository after we calculated everything
.SaveOrAppendResult(currentRunResultKey)
.Run());
}
private static void Evaluate(SparkSession session, Action <AnalyzerContext, IMetricsRepository> func)
{
DataFrame data = FixtureSupport.GetDFFull(session);
AnalyzerContext results = CreateAnalysis().Run(data, Option <IStateLoader> .None,
Option <IStatePersister> .None);
IMetricsRepository repository = CreateRepository();
func(results, repository);
}
public MetricsStore(
IMetricsRepository <Metric> metricRepository,
ILogger <MetricsStore> logger,
IDbQueryConfiguration dbQuery,
ICacheManager cacheManager)
{
_metricRepository = metricRepository;
_cacheManager = cacheManager;
_dbQuery = dbQuery;
_logger = logger;
}
private void TestAnomalyDetection(
SparkSession session,
IMetricsRepository repository)
{
var data = GetTestData(session);
// Fill repository with some fake results from previous runs for July 2018
FillRepositoryWithPreviousResults(repository);
// Some other checks and analyzers we are interested in not related to the anomaly detection
var(otherCheck, additionalRequiredAnalyzers) = GetNormalCheckAndRequiredAnalyzers();
// This method is where the interesting stuff happens
var verificationResult = CreateAnomalyChecksAndRunEverything(data, repository, otherCheck,
additionalRequiredAnalyzers);
PrintConstraintResults(verificationResult);
AssertAnomalyCheckResultsAreCorrect(verificationResult);
}
public QueueConsumerServiceTests()
{
var logger = new Mock <ILogger>();
var loggerFactory = new Mock <ILoggerFactory>();
loggerFactory.Setup(c => c.CreateLogger(It.IsAny <string>())).Returns(logger.Object);
_loggerFactory = loggerFactory.Object;
var metricsRepo = new Mock <IMetricsRepository>();
_metricsRepo = metricsRepo.Object;
var model = new Mock <IModel>();
var connection = new Mock <IConnection>();
connection.Setup(c => c.CreateModel()).Returns(model.Object);
var connectonFactory = new Mock <ConnectionFactory>();
connectonFactory.Setup(c => c.CreateConnection()).Returns(connection.Object);
_connectionFactory = connectonFactory.Object;
}
/// <summary>
/// Set a metrics repository associated with the current data to enable features like reusing previously computed results and storing the results of the current run.
/// </summary>
/// <param name="metricsRepository">A metrics repository to store and load results associated with the run</param>
/// <returns></returns>
public VerificationRunBuilderWithRepository UseRepository(IMetricsRepository metricsRepository) =>
new VerificationRunBuilderWithRepository(this,
new Option <IMetricsRepository>(metricsRepository));
public QueueConsumerService(ILoggerFactory loggerFactory, IMetricsRepository metricsRepository)
{
_metricsRepository = metricsRepository;
_logger = loggerFactory.CreateLogger <QueueConsumerService>();
}
public ServiceBusMetricsController(IMetricsRepository <ServiceBusModel> serviceBusMetricsRepository)
{
_serviceBusMetricsRepository = serviceBusMetricsRepository;
}
public MetricsModel(IMetricsRepository metricsRepo)
{
_metricsRepo = metricsRepo;
}
public MetricGetHandler(IMetricsRepository repository = null)
{
_repository = repository ?? new MetricRepository();
}
public QueueMetricsController(IMetricsRepository <QueueMetricModel> queuesMetricRepository)
{
_queuesMetricRepository = queuesMetricRepository;
}
public MetricsService(IMetricsRepository metricsRepository)
{
_metricsRepository = metricsRepository;
}
public MetricsService(IMetricsRepository metricsRepo, IUnitOfWork unitOfWork)
{
_metricsRepo = metricsRepo;
_unitOfWork = unitOfWork;
}
public MetricsController(IMetricsRepository metricsRepository)
{
_metricsRepository = metricsRepository;
}
