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_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)
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)
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.limit = 3
# Just get top 3 ranks for simplicity
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"]
expectedData = \
[ RowItemModel( [-3], headers ),
RowItemModel( [-6], headers ),
RowItemModel( [-5], 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])
headers = ["clinical_item_id"]
expectedData = \
[ RowItemModel( [-3], headers ),
RowItemModel( [-6], headers ),
RowItemModel( [-5], 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])
headers = ["clinical_item_id"]
expectedData = \
[ RowItemModel( [-6], headers ),
RowItemModel( [-5], 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])
query.excludeCategoryIds = set([-1, -4, -5, -6])
headers = ["clinical_item_id"]
expectedData = \
[ RowItemModel( [-5], 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()
headers = ["clinical_item_id"]
expectedData = \
[ RowItemModel( [-4], headers ),
RowItemModel( [-6], headers ),
]
recommendedData = self.recommender(query)
self.assertEqualRecommendedData(expectedData, recommendedData, query)
log.debug(
"General query but set a limit on time delta worth counting item associations"
)
query.queryItemIds = set([-2, -5, -100])
query.excludeItemIds = set()
query.excludeCategoryIds = set()
query.timeDeltaMax = DELTA_HOUR
headers = ["clinical_item_id"]
expectedData = \
[ RowItemModel( [-6], headers ),
RowItemModel( [-4], 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])
query.timeDeltaMax = DELTA_HOUR
headers = ["clinical_item_id"]
expectedData = \
[ RowItemModel( [-4], 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()
query.timeDeltaMax = DELTA_HOUR
headers = ["clinical_item_id"]
expectedData = \
[ RowItemModel( [-6], headers ),
]
recommendedData = self.recommender(query)
self.assertEqualRecommendedData(expectedData, recommendedData, query)
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)
for result in results: