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);
InMemoryMetricsRepository repository = new InMemoryMetricsRepository();
func(results, repository);
}
public void should_execute_anomaly_detection_example()
{
// Anomaly detection operates on metrics stored in a metric repository, so lets create one
InMemoryMetricsRepository metricsRepository = new InMemoryMetricsRepository();
// This is the key which we use to store the metrics for the dataset from yesterday
ResultKey yesterdayKeys =
new ResultKey(DateTime.Now.Ticks - 24 * 60 * 1000);
/* In this simple example, we assume that we compute metrics on a dataset every day and we want
* to ensure that they don't change drastically. For sake of simplicity, we just look at the
* size of the data */
/* Yesterday, the data had only two rows */
var yesterdaysDataset = LoadAnomalyDetectionData(new List <object[]>
{
new object[] { 1, "Thingy A", "awesome thing.", "high", 0 },
new object[] { 2, "Thingy B", "available at http://thingb.com", null, 0 }
});
/* We test for anomalies in the size of the data, it should not increase by more than 2x. Note
* that we store the resulting metrics in our repository */
new VerificationSuite()
.OnData(yesterdaysDataset)
.UseRepository(metricsRepository)
.SaveOrAppendResult(yesterdayKeys)
.AddAnomalyCheck(
new RelativeRateOfChangeStrategy(maxRateIncrease: 2.0),
Size()
)
.Run()
.Debug(_helper.WriteLine);
/* Todays data has five rows, so the data size more than doubled and our anomaly check should
* catch this */
var todaysDataset = LoadAnomalyDetectionData(new List <object[]>
{
new object[] { 1, "Thingy A", "awesome thing.", "high", 0 },
new object[] { 2, "Thingy B", "available at http://thingb.com", null, 0 },
new object[] { 3, null, null, "low", 5 },
new object[] { 4, "Thingy D", "checkout https://thingd.ca", "low", 10 },
new object[] { 5, "Thingy W", null, "high", 12 }
});
/* The key for today's result */
var todaysKey = new ResultKey(DateTime.Now.Ticks - 24 * 60 * 1000);
/* Repeat the anomaly check for today's data */
var verificationResult = new VerificationSuite()
.OnData(todaysDataset)
.UseRepository(metricsRepository)
.SaveOrAppendResult(todaysKey)
.AddAnomalyCheck(
new RelativeRateOfChangeStrategy(maxRateIncrease: 2.0),
Size()
)
.Run();
verificationResult.Status.ShouldBe(CheckStatus.Warning);
_helper.WriteLine("Anomaly detected in the Size() metric!");
/* Lets have a look at the actual metrics. */
metricsRepository
.Load()
.ForAnalyzers(new[] { Size() })
.GetSuccessMetricsAsDataFrame(_session)
.Show();
}
public void work_using_the_InMemoryMetricsRepository()
{
var repository = new InMemoryMetricsRepository();
TestAnomalyDetection(_session, repository);
}
