def test_recommender_aggregation(self): # Test different scoring aggregation methods query = RecommenderQuery() query.countPrefix = "patient_" query.queryItemIds = set([-2, -5]) #query.excludeItemIds = set(); #query.categoryIds = set(); #query.timeDeltaMax = None; # If set to one of the constants (DELTA_ZERO, DELTA_HOUR, etc.), will count item associations that occurred within that time delta as co-occurrent. If left blank, will just consider all items within a given patient as co-occurrent. query.limit = 3 # Just get top 3 ranks for simplicity query.maxRecommendedId = 0 # Artificial constraint to focus only on test data headers = ["clinical_item_id", "conditionalFreq", "freqRatio"] # Default weighted aggregation method expectedData = \ [ RowItemModel( [-4, 0.3, 22.5], headers ), RowItemModel( [-6, 0.16667, 7.142857], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) # Change to unweighted aggregation method query.aggregationMethod = "unweighted" expectedData = \ [ RowItemModel( [-4, 0.32857, 24.64286], headers ), RowItemModel( [-6, 0.16667, 7.142857], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) # Change to Serial Bayes aggregation method query.aggregationMethod = "SerialBayes" expectedData = \ [ RowItemModel( [-4, 0.89157, 66.867471], headers ), RowItemModel( [-6, 0.16667, 7.142857], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) # Naive Bayes aggregation query.aggregationMethod = "NaiveBayes" expectedData = \ [ RowItemModel( [-4, 3.75, 281.25], headers ), # Without truncating negative values #RowItemModel( [-4, 0.8, 58.59707], headers ), # With truncating negative values RowItemModel( [-6, 0.16667, 7.142857], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) # Apply value filter query.fieldFilters["freqRatio>"] = 10.0 expectedData = \ [ RowItemModel( [-6, 0.16667, 7.142857], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query)
def test_dataCache(self): # Test that repeating queries with cache turned on will not result in extra DB queries query = RecommenderQuery() query.countPrefix = "patient_" query.queryItemIds = set([-2, -5]) #query.excludeItemIds = set(); #query.categoryIds = set(); #query.timeDeltaMax = None; # If set to one of the constants (DELTA_ZERO, DELTA_HOUR, etc.), will count item associations that occurred within that time delta as co-occurrent. If left blank, will just consider all items within a given patient as co-occurrent. query.limit = 3 # Just get top 3 ranks for simplicity query.maxRecommendedId = 0 # Artificial constraint to focus only on test data headers = ["clinical_item_id", "conditionalFreq", "freqRatio"] # First query without cache self.recommender.dataManager.dataCache = None baselineData = self.recommender(query) baselineQueryCount = self.recommender.dataManager.queryCount # Redo query with cache self.recommender.dataManager.dataCache = dict() newData = self.recommender(query) newQueryCount = self.recommender.dataManager.queryCount self.assertEqualRecommendedData(baselineData, newData, query) # Ensure getting same results self.assertNotEqual(baselineQueryCount, newQueryCount) # Expect needed more queries since no prior cache baselineQueryCount = newQueryCount # Again, but should be no new query since have cached results last time newData = self.recommender(query) newQueryCount = self.recommender.dataManager.queryCount self.assertEqualRecommendedData(baselineData, newData, query) self.assertEqual(baselineQueryCount, newQueryCount) # Repeat multiple times, should still have no new query activity # prog = ProgressDots(10,1,"repeats"); for iRepeat in xrange(10): newData = self.recommender(query) newQueryCount = self.recommender.dataManager.queryCount self.assertEqualRecommendedData(baselineData, newData, query) self.assertEqual(baselineQueryCount, newQueryCount) # prog.update(); # prog.printStatus(); # Query for subset should still yield no new query query.queryItemIds = set([-2]) newData = self.recommender(query) newQueryCount = self.recommender.dataManager.queryCount baselineData = newData # New baseline for subset self.assertEqual(baselineQueryCount, newQueryCount) # Expect no queries for subsets # Repeat query for subset newData = self.recommender(query) newQueryCount = self.recommender.dataManager.queryCount self.assertEqualRecommendedData(baselineData, newData, query) self.assertEqual(baselineQueryCount, newQueryCount) # Expect no queries for subsets # Query for partial subset, partial new query.queryItemIds = set([-5, -6]) newData = self.recommender(query) newQueryCount = self.recommender.dataManager.queryCount baselineData = newData # New baseline for subset self.assertEqual(baselineQueryCount, newQueryCount) # Expect now new queries for subsets, because first query should have done mass-all query # Repeat for partial subset, no longer new newData = self.recommender(query) newQueryCount = self.recommender.dataManager.queryCount baselineData = newData # New baseline for subset self.assertEqualRecommendedData(baselineData, newData, query) self.assertEqual(baselineQueryCount, newQueryCount)
itemIdsByAdmitDxId[admitDxId].add(itemId) admitDxIdSectionGuidelineNameTuples.add( (admitDxId, sectionName, guidelineName)) recommender = ItemAssociationRecommender() for admitDxId, itemIds in itemIdsByAdmitDxId.iteritems(): print >> sys.stderr, admitDxId, len(itemIds) recQuery = RecommenderQuery() recQuery.excludeItemIds = recommender.defaultExcludedClinicalItemIds() recQuery.excludeCategoryIds = recommender.defaultExcludedClinicalItemCategoryIds( ) recQuery.queryItemIds = [admitDxId] recQuery.timeDeltaMax = timedelta(1) # Within one day recQuery.countPrefix = "patient_" recQuery.limit = TOP_ITEM_COUNT # Top results by P-value recQuery.sortField = "P-YatesChi2-NegLog" results = recommender(recQuery) #recommender.formatRecommenderResults(results); for result in results: itemIds.add(result["clinical_item_id"]) #print >> sys.stderr, result["description"]; print >> sys.stderr, admitDxId, len(itemIds) # Top results by PPV recQuery.sortField = "PPV" results = recommender(recQuery)