def testUpdateAnomalyLikelihoods(self):
"""
A slight more complex test. This calls estimateAnomalyLikelihoods
to estimate the distribution on fake data, followed by several calls
to updateAnomalyLikelihoods.
"""
# ------------------------------------------
# Step 1. Generate an initial estimate using fake distribution of anomaly
# scores.
data1 = _generateSampleData(mean=0.2)[0:1000]
_, _, estimatorParams = an.estimateAnomalyLikelihoods(data1, averagingWindow=5)
# ------------------------------------------
# Step 2. Generate some new data with a higher average anomaly
# score. Using the estimator from step 1, to compute likelihoods. Now we
# should see a lot more anomalies.
data2 = _generateSampleData(mean=0.6)[0:300]
likelihoods2, avgRecordList2, estimatorParams2 = an.updateAnomalyLikelihoods(data2, estimatorParams)
self.assertEqual(len(likelihoods2), len(data2))
self.assertEqual(len(avgRecordList2), len(data2))
self.assertTrue(an.isValidEstimatorParams(estimatorParams))
# The new running total should be different
self.assertNotEqual(estimatorParams2["movingAverage"]["total"], estimatorParams["movingAverage"]["total"])
# We should have many more samples where likelihood is < 0.01, but not all
self.assertGreaterEqual(numpy.sum(likelihoods2 < 0.01), 25)
self.assertLessEqual(numpy.sum(likelihoods2 < 0.01), 250)
# ------------------------------------------
# Step 3. Generate some new data with the expected average anomaly score. We
# should see fewer anomalies than in Step 2.
data3 = _generateSampleData(mean=0.2)[0:1000]
likelihoods3, avgRecordList3, estimatorParams3 = an.updateAnomalyLikelihoods(data3, estimatorParams2)
self.assertEqual(len(likelihoods3), len(data3))
self.assertEqual(len(avgRecordList3), len(data3))
self.assertTrue(an.isValidEstimatorParams(estimatorParams3))
# The new running total should be different
self.assertNotEqual(estimatorParams3["movingAverage"]["total"], estimatorParams["movingAverage"]["total"])
self.assertNotEqual(estimatorParams3["movingAverage"]["total"], estimatorParams2["movingAverage"]["total"])
# We should have a small number samples where likelihood is < 0.02, but at
# least one
self.assertGreaterEqual(numpy.sum(likelihoods3 < 0.01), 1)
self.assertLessEqual(numpy.sum(likelihoods3 < 0.01), 100)
# ------------------------------------------
# Step 4. Validate that sending data incrementally is the same as sending
# in one batch
allData = data1
allData.extend(data2)
allData.extend(data3)
# Compute moving average of all the data and check it's the same
_, historicalValuesAll, totalAll = an._anomalyScoreMovingAverage(allData, windowSize=5)
self.assertEqual(sum(historicalValuesAll), sum(estimatorParams3["movingAverage"]["historicalValues"]))
self.assertEqual(totalAll, estimatorParams3["movingAverage"]["total"])
def testUpdateAnomalyLikelihoods(self):
"""
A slight more complex test. This calls estimateAnomalyLikelihoods
to estimate the distribution on fake data, followed by several calls
to updateAnomalyLikelihoods.
"""
#------------------------------------------
# Step 1. Generate an initial estimate using fake distribution of anomaly
# scores.
data1 = _generateSampleData(mean=0.2)[0:1000]
_, _, estimatorParams = (an.estimateAnomalyLikelihoods(
data1, averagingWindow=5))
#------------------------------------------
# Step 2. Generate some new data with a higher average anomaly
# score. Using the estimator from step 1, to compute likelihoods. Now we
# should see a lot more anomalies.
data2 = _generateSampleData(mean=0.6)[0:300]
likelihoods2, avgRecordList2, estimatorParams2 = (
an.updateAnomalyLikelihoods(data2, estimatorParams))
self.assertEqual(len(likelihoods2), len(data2))
self.assertEqual(len(avgRecordList2), len(data2))
self.assertTrue(an.isValidEstimatorParams(estimatorParams))
# The new running total should be different
self.assertNotEqual(estimatorParams2["movingAverage"]["total"],
estimatorParams["movingAverage"]["total"])
# We should have many more samples where likelihood is < 0.01, but not all
self.assertGreaterEqual(numpy.sum(likelihoods2 < 0.01), 25)
self.assertLessEqual(numpy.sum(likelihoods2 < 0.01), 250)
#------------------------------------------
# Step 3. Generate some new data with the expected average anomaly score. We
# should see fewer anomalies than in Step 2.
data3 = _generateSampleData(mean=0.2)[0:1000]
likelihoods3, avgRecordList3, estimatorParams3 = (
an.updateAnomalyLikelihoods(data3, estimatorParams2))
self.assertEqual(len(likelihoods3), len(data3))
self.assertEqual(len(avgRecordList3), len(data3))
self.assertTrue(an.isValidEstimatorParams(estimatorParams3))
# The new running total should be different
self.assertNotEqual(estimatorParams3["movingAverage"]["total"],
estimatorParams["movingAverage"]["total"])
self.assertNotEqual(estimatorParams3["movingAverage"]["total"],
estimatorParams2["movingAverage"]["total"])
# We should have a small number samples where likelihood is < 0.02, but at
# least one
self.assertGreaterEqual(numpy.sum(likelihoods3 < 0.01), 1)
self.assertLessEqual(numpy.sum(likelihoods3 < 0.01), 100)
#------------------------------------------
# Step 4. Validate that sending data incrementally is the same as sending
# in one batch
allData = data1
allData.extend(data2)
allData.extend(data3)
# Compute moving average of all the data and check it's the same
_, historicalValuesAll, totalAll = (an._anomalyScoreMovingAverage(
allData, windowSize=5))
self.assertEqual(
sum(historicalValuesAll),
sum(estimatorParams3["movingAverage"]["historicalValues"]))
self.assertEqual(totalAll, estimatorParams3["movingAverage"]["total"])