def test_recommender(self): # Run the recommender against the mock test data above and verify expected stats afterwards. query = RecommenderQuery() #query.queryItemIds = set(); #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.sortField = "tf" query.limit = 16 # Go ahead and query for all since short list and can get expected calculation results for all query.maxRecommendedId = 0 # Artificial constraint to focus only on test data log.debug( "Query with no item key input, just return ranks by general likelihood then." ) headers = ["clinical_item_id", "score"] expectedData = \ [ RowItemModel( [-2, 2.0/13], headers ), RowItemModel( [-5, 2.0/13], headers ), RowItemModel( [-6, 2.0/13], headers ), RowItemModel( [-1, 1.0/13], headers ), RowItemModel( [-3, 1.0/13], headers ), RowItemModel( [-7, 1.0/13], headers ), RowItemModel( [-8, 1.0/13], headers ), RowItemModel( [-10,1.0/13], headers ), RowItemModel( [-11,1.0/13], headers ), RowItemModel( [-12,1.0/13], headers ), RowItemModel( [-13,1.0/13], headers ), RowItemModel( [-14,1.0/13], headers ), RowItemModel( [-15,1.0/13], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) log.debug( "Query with key item inputs for which no data exists. Effecitvely ignore it then, so just return ranks by general likelihood." ) query.queryItemIds = set([-100]) expectedData = \ [ RowItemModel( [-2, 2.0/13], headers ), RowItemModel( [-5, 2.0/13], headers ), RowItemModel( [-6, 2.0/13], headers ), RowItemModel( [-1, 1.0/13], headers ), RowItemModel( [-3, 1.0/13], headers ), RowItemModel( [-7, 1.0/13], headers ), RowItemModel( [-8, 1.0/13], headers ), RowItemModel( [-10,1.0/13], headers ), RowItemModel( [-11,1.0/13], headers ), RowItemModel( [-12,1.0/13], headers ), RowItemModel( [-13,1.0/13], headers ), RowItemModel( [-14,1.0/13], headers ), RowItemModel( [-15,1.0/13], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) log.debug("Query with category filter on recommended results.") query.queryItemIds = set([-100]) query.excludeCategoryIds = set([-1, -4, -5, -6]) expectedData = \ [ #RowItemModel( [-2, 2.0/13], headers ), RowItemModel( [-5, 2.0/13], headers ), RowItemModel( [-6, 2.0/13], headers ), #RowItemModel( [-1, 1.0/13], headers ), #RowItemModel( [-3, 1.0/13], headers ), RowItemModel( [-7, 1.0/13], headers ), RowItemModel( [-8, 1.0/13], headers ), RowItemModel( [-10,1.0/13], headers ), RowItemModel( [-11,1.0/13], headers ), RowItemModel( [-12,1.0/13], headers ), RowItemModel( [-13,1.0/13], headers ), #RowItemModel( [-14,1.0/13], headers ), #RowItemModel( [-15,1.0/13], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) log.debug( "Query with category filter and specific exclusion filter on recommended results." ) query.queryItemIds = set([-100]) query.excludeItemIds = set([-6, -10]) query.excludeCategoryIds = set([-1, -4, -5, -6]) expectedData = \ [ #RowItemModel( [-2, 2.0/13], headers ), RowItemModel( [-5, 2.0/13], headers ), #RowItemModel( [-6, 2.0/13], headers ), #RowItemModel( [-1, 1.0/13], headers ), #RowItemModel( [-3, 1.0/13], headers ), RowItemModel( [-7, 1.0/13], headers ), RowItemModel( [-8, 1.0/13], headers ), #RowItemModel( [-10,1.0/13], headers ), RowItemModel( [-11,1.0/13], headers ), RowItemModel( [-12,1.0/13], headers ), RowItemModel( [-13,1.0/13], headers ), #RowItemModel( [-14,1.0/13], headers ), #RowItemModel( [-15,1.0/13], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) log.debug( "General query with a couple of input clinical items + one with no association data (should effectively be ignored)." ) query.queryItemIds = set([-2, -5, -100]) query.excludeItemIds = set() query.excludeCategoryIds = set() expectedData = \ [ RowItemModel( [-6, (1.0/6)*(2.0/2)+(1.0/4)*(1.0/2)], headers ), #RowItemModel( [-5, (1.0/6)*(2.0/2)+(1.0/4)*(1.0/2)], headers ), #RowItemModel( [-2, (1.0/6)*(1.0/2)+(1.0/6)*(2.0/2)], headers ), RowItemModel( [-3, (1.0/6)*(2.0/2)], headers ), RowItemModel( [-7, (1.0/6)*(2.0/2)], headers ), RowItemModel( [-8, (1.0/6)*(2.0/2)], headers ), RowItemModel( [-14,(1.0/4)*(1.0/2)], headers ), RowItemModel( [-15,(1.0/4)*(1.0/2)], headers ), RowItemModel( [-1, (1.0/6)*(1.0/2)], headers ), RowItemModel( [-10,(1.0/6)*(1.0/2)], headers ), RowItemModel( [-11,(1.0/6)*(1.0/2)], headers ), RowItemModel( [-12,(1.0/6)*(1.0/2)], headers ), RowItemModel( [-13,(1.0/6)*(1.0/2)], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) log.debug("General query with category limit") query.queryItemIds = set([-2, -5, -100]) query.excludeItemIds = set() query.excludeCategoryIds = set([-2, -4, -5, -6]) expectedData = \ [ #RowItemModel( [-6, (1.0/6)*(2.0/2)+(1.0/4)*(1.0/2)], headers ), #RowItemModel( [-5, (1.0/6)*(2.0/2)+(1.0/4)*(1.0/2)], headers ), #RowItemModel( [-2, (1.0/6)*(1.0/2)+(1.0/6)*(2.0/2)], headers ), RowItemModel( [-3, (1.0/6)*(2.0/2)], headers ), #RowItemModel( [-7, (1.0/6)*(2.0/2)], headers ), #RowItemModel( [-8, (1.0/6)*(2.0/2)], headers ), #RowItemModel( [-14,(1.0/4)*(1.0/2)], headers ), #RowItemModel( [-15,(1.0/4)*(1.0/2)], headers ), RowItemModel( [-1, (1.0/6)*(1.0/2)], headers ), RowItemModel( [-10,(1.0/6)*(1.0/2)], headers ), RowItemModel( [-11,(1.0/6)*(1.0/2)], headers ), RowItemModel( [-12,(1.0/6)*(1.0/2)], headers ), RowItemModel( [-13,(1.0/6)*(1.0/2)], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) log.debug("General query with specific exclusion") query.queryItemIds = set([-2, -5, -100]) query.excludeItemIds = set([-4, -3, -2]) query.excludeCategoryIds = set() expectedData = \ [ RowItemModel( [-6, (1.0/6)*(2.0/2)+(1.0/4)*(1.0/2)], headers ), #RowItemModel( [-5, (1.0/6)*(2.0/2)+(1.0/4)*(1.0/2)], headers ), #RowItemModel( [-2, (1.0/6)*(1.0/2)+(1.0/6)*(2.0/2)], headers ), #RowItemModel( [-3, (1.0/6)*(2.0/2)], headers ), RowItemModel( [-7, (1.0/6)*(2.0/2)], headers ), RowItemModel( [-8, (1.0/6)*(2.0/2)], headers ), RowItemModel( [-14,(1.0/4)*(1.0/2)], headers ), RowItemModel( [-15,(1.0/4)*(1.0/2)], headers ), RowItemModel( [-1, (1.0/6)*(1.0/2)], headers ), RowItemModel( [-10,(1.0/6)*(1.0/2)], headers ), RowItemModel( [-11,(1.0/6)*(1.0/2)], headers ), RowItemModel( [-12,(1.0/6)*(1.0/2)], headers ), RowItemModel( [-13,(1.0/6)*(1.0/2)], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query) log.debug("General query, sort by TF*IDF lift.") query.queryItemIds = set([-2, -5, -100]) query.excludeItemIds = set() query.excludeCategoryIds = set() query.sortField = "lift" expectedData = \ [ #RowItemModel( [-5, (13.0/2)*((1.0/6)*(2.0/2)+(1.0/4)*(1.0/2))], headers ), #RowItemModel( [-2, (13.0/2)*((1.0/6)*(1.0/2)+(1.0/6)*(2.0/2))], headers ), RowItemModel( [-3, (13.0/1)*((1.0/6)*(2.0/2))], headers ), RowItemModel( [-7, (13.0/1)*((1.0/6)*(2.0/2))], headers ), RowItemModel( [-8, (13.0/1)*((1.0/6)*(2.0/2))], headers ), RowItemModel( [-6, (13.0/2)*((1.0/6)*(2.0/2)+(1.0/4)*(1.0/2))], headers ), RowItemModel( [-14,(13.0/1)*((1.0/4)*(1.0/2))], headers ), RowItemModel( [-15,(13.0/1)*((1.0/4)*(1.0/2))], headers ), RowItemModel( [-1, (13.0/1)*((1.0/6)*(1.0/2))], headers ), RowItemModel( [-10,(13.0/1)*((1.0/6)*(1.0/2))], headers ), RowItemModel( [-11,(13.0/1)*((1.0/6)*(1.0/2))], headers ), RowItemModel( [-12,(13.0/1)*((1.0/6)*(1.0/2))], headers ), RowItemModel( [-13,(13.0/1)*((1.0/6)*(1.0/2))], headers ), ] recommendedData = self.recommender(query) self.assertEqualRecommendedData(expectedData, recommendedData, query)
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) for result in results: itemIds.add(result["clinical_item_id"]) print >> sys.stderr, admitDxId, len(itemIds)