def main_buildTopicModel(argv):
bowInputFilename = SOURCE_DATA_DIR + INPUT_FILENAME
mod = TopicModel()
for numTopics in numTopicsOptions:
subargv = ["TopicModel", "-n", str(numTopics)]
subargv.extend([
bowInputFilename,
MODEL_DIR + "/topicModel." + os.path.basename(bowInputFilename) +
".%dTopic.model" % (numTopics),
])
mod.main(subargv)
return mod.model
def __init__(self, model, docCountByWordId=None):
"""Initialize module with prior generated model and word document counts from TopicModel module.
"""
BaseItemRecommender.__init__(self)
self.modeler = TopicModel()
# Utility instance to run off of
if docCountByWordId: # Specified both options
self.model = model
self.docCountByWordId = docCountByWordId
else: # If only the first one specified, interpret it as a base filename to load the objects from
filename = model
(self.model, self.docCountByWordId
) = self.modeler.loadModelAndDocCounts(filename)
# Cached lookup data. Don't repeat work for serial queries
self.itemsById = None
self.categoryIdByItemId = None
self.candidateItemIds = None
self.weightByItemIdByTopicId = None
def main_quickTest(argv):
modelFilename = argv[1]
modeler = TopicModel()
timer = time.time()
(model, docCountByWordId) = modeler.loadModelAndDocCounts(modelFilename)
timer = time.time() - timer
log.info("%.2f seconds to load", timer)
timer = time.time()
weightByItemIdByTopicId = modeler.generateWeightByItemIdByTopicId(
model, 100)
timer = time.time() - timer
log.info("%.2f seconds to generate weights", timer)
for i in xrange(3):
prog = ProgressDots()
for (topicId, weightByItemId) in weightByItemIdByTopicId.iteritems():
for (itemId, itemWeight) in weightByItemId.iteritems():
prog.update()
prog.printStatus()
"""
def setUp(self):
"""Prepare state for test cases"""
DBTestCase.setUp(self)
log.info("Populate the database with test data")
from stride.clinical_item.ClinicalItemDataLoader import ClinicalItemDataLoader
ClinicalItemDataLoader.build_clinical_item_psql_schemata()
self.clinicalItemCategoryIdStrList = list()
headers = ["clinical_item_category_id", "source_table"]
dataModels = \
[
RowItemModel( [-1, "Labs"], headers ),
RowItemModel( [-2, "Imaging"], headers ),
RowItemModel( [-3, "Meds"], headers ),
RowItemModel( [-4, "Nursing"], headers ),
RowItemModel( [-5, "Problems"], headers ),
RowItemModel( [-6, "Lab Results"], headers ),
]
for dataModel in dataModels:
(dataItemId,
isNew) = DBUtil.findOrInsertItem("clinical_item_category",
dataModel)
self.clinicalItemCategoryIdStrList.append(str(dataItemId))
headers = [
"clinical_item_id", "clinical_item_category_id", "name",
"analysis_status"
]
dataModels = \
[
RowItemModel( [1, -1, "CBC",1], headers ),
RowItemModel( [2, -1, "BMP",0], headers ), # Clear analysis status, so this will be ignored unless changed
RowItemModel( [3, -1, "Hepatic Panel",1], headers ),
RowItemModel( [4, -1, "Cardiac Enzymes",1], headers ),
RowItemModel( [5, -2, "CXR",1], headers ),
RowItemModel( [6, -2, "RUQ Ultrasound",1], headers ),
RowItemModel( [7, -2, "CT Abdomen/Pelvis",1], headers ),
RowItemModel( [8, -2, "CT PE Thorax",1], headers ),
RowItemModel( [9, -3, "Acetaminophen",1], headers ),
RowItemModel( [10, -3, "Carvedilol",1], headers ),
RowItemModel( [11, -3, "Enoxaparin",1], headers ),
RowItemModel( [12, -3, "Warfarin",1], headers ),
RowItemModel( [13, -3, "Ceftriaxone",1], headers ),
RowItemModel( [14, -4, "Foley Catheter",1], headers ),
RowItemModel( [15, -4, "Strict I&O",1], headers ),
RowItemModel( [16, -4, "Fall Precautions",1], headers ),
]
for dataModel in dataModels:
(dataItemId,
isNew) = DBUtil.findOrInsertItem("clinical_item", dataModel)
# Input file contents in Bag-of-Words formats
# Specifically avoid the use of items 6 or 7 in the training data
self.inputBOWFileStr = \
"""[[1,1],[2,2],[3,1],[4,4],[5,10],[8,5]]
[[3,4],[4,4],[9,3],[10,2],[12,6],[13,3],[15,5],[16,8]]
[[1,1],[2,2],[3,1],[4,4],[5,10],[8,5],[9,1],[10,2],[11,1],[12,4],[13,10],[14,1],[15,3],[16,5]]
[[1,4],[2,9],[9,1],[10,2],[11,7],[12,4],[13,2],[16,6]]
[[4,3],[5,31],[8,5],[12,6],[13,8],[16,5]]
"""
self.instance = TopicModel()