def Init(self):
cxBaseC.Init(self)
self.Searcher = IndriSearchCenterC()
self.hDocAnaData = {}
self.hDocText = {}
self.OutDir = ''
self.QInName = ""
def Init(self):
cxBaseC.Init(self)
self.InDir = ""
self.OutDir = ""
self.QRelCenter = AdhocQRelC()
self.hQueryQid = {} #query name -> qid
def Init(self):
cxBaseC.Init(self)
self.ObjCenter = FbObjCacheCenterC()
self.Inferener = LESInferencerC()
self.DocKgDir = ""
self.hQObj = {}
self.OrigQWeight = 0.5
def Init(self):
cxBaseC.Init(self)
self.QIn = ""
self.OutDir = ""
self.Word2VecInName = ""
self.Word2VecModel = None
self.Searcher = IndriSearchCenterC()
self.BinNumber = 100
def Init(self):
cxBaseC.Init(self)
self.Searcher = IndriSearchCenterC()
self.QueryNodePreFetchedCollector = QueryPreFetchedNodeCollectorC()
self.DocNodeFaccAnaCollector = DocNodeFaccAnaCollectorC()
self.lQueryNodeGroup = []
self.lDocNodeGroup = []
def Init(self):
cxBaseC.Init(self)
self.MSRAInDataPre = "/bos/data1/ClueWeb09-TopicModels/tokenize/split_48/part-"
self.PartNum = 48
self.DocUrlMappingDataPre = "/bos/tmp11/zhuyund/TopicModels/TopicModelURLDocNo/output_doc_text/url2extid_doc_text/url2extid.block."
self.OutPre = ""
self.ProcessScript = 'MSRALDAKeepWikiInFile.py'
self.lCmd = ['qsub', 'python']
def Init(self):
cxBaseC.Init(self)
self.RelCenter = AdhocQRelC()
self.InDir = ""
self.OutDir = ""
self.hNodeFeatureId = {} #the id of node features
self.hEdgeFeatureId = {} #the id of edge features
def Init(self):
cxBaseC.Init(self)
self.Evaluator = AdhocEvaC()
self.Searcher = IndriSearchCenterC()
self.Word2VecInName = ""
self.Word2VecModel = None
self.lLmName = []
self.LmClass = None
self.lOutName = []
self.QueryInName = ""
def Init(self):
cxBaseC.Init(self)
self.lObjObjFeatureGroup = []
self.ObjObjKGExtractor = ObjObjEdgeFeatureKGExtractorC()
self.ObjObjPreCalcExtractor = ObjObjEdgeFeaturePreCalcSimExtractorC()
self.ObjObjTextSimExtractor = ObjObjEdgeFeatureTextSimExtractorC()
self.ObjObjTypeSimExtractor = ObjObjEdgeFeatureTypeExtractorC()
self.ObjObjEmbSimExtractor = ObjObjEdgeFeatureEmbSimExtractorC()
self.NodeDir = ""
def Init(self):
cxBaseC.Init(self)
self.size = 300
self.min_count = 5
self.sample = 0
self.workers = 8
self.hs = 0
self.negative = 5
self.dm = 0 #skipgram
self.InName = ""
self.OutName = ""
def Init(self):
cxBaseC.Init(self)
self.Evaluator = AdhocEvaC()
self.Searcher = IndriSearchCenterC()
self.Word2VecInName = ""
self.Word2VecModel = None
self.cLmName = "kde"
self.LmClass = KernelDensityLmC
#lm conf input
self.ParaConf = cxConfC()
def Init(self):
cxBaseC.Init(self)
self.NodeDir = ""
self.Searcher = IndriSearchCenterC()
self.ObjCenter = FbObjCacheCenterC()
self.QDocFeatureExtractor = LeToRFeatureExtractCenterC()
self.QObjFeatureExtractor = FbQObjFeatureExtractCenterC()
self.DocObjFeatureExtractor = FbObjDocFeatureExtractCenterC()
self.ObjObjFeatureExtractor = ObjObjFeatureExtractCenterC()
def Init(self):
cxBaseC.Init(self)
self.hDocVec = {}
self.DocVecModel = None
self.hDocNoInternalId = {}
self.DistanceType = "abs"
self.QField = "topic"
self.DocVecInName = ""
self.OverWrite = False
self.DocVecInType = 'text'
self.DocNoInName = ""
self.hQidQuery = {} #used to map qid to query terms
def Init(self):
cxBaseC.Init(self)
# self.lGraphData = []
# self.lLabel = []
'''
hyperparameters
'''
self.Lambda = 1
self.Alpha = 0.2
self.b = 0.4
def Init(self):
cxBaseC.Init(self)
self.size = 300
self.min_count = 5
# self.sample = 0
self.workers = 8
# self.hs = 0
self.negative = 5
self.sg = 1 #skipgram
self.InName = ""
self.OutName = ""
self.window = 20
def Init(self):
cxBaseC.Init(self)
self.Searcher = IndriSearchCenterC()
self.ObjCenter = FbObjCacheCenterC()
self.Evaluator = AdhocEvaC()
self.Inferener = LESInferencerC()
self.QDocNodeDataDir = ""
self.OrigQWeight = 0.5
self.UseQObjOnly = True
def Init(self):
cxBaseC.Init(self)
self.Prepared = False
self.Word2VecInName = ""
self.Word2VecModel = None
self.lFeatureGroup = []
self.Searcher = IndriSearchCenterC()
self.GivenFeatureExtractor = LeToRGivenFeatureExtractorC()
self.EmbTermPairFeatureExtractor = EmbeddingTermPairFeatureExtractorC()
self.EmbLmFeatureExtractor = EmbeddingLmFeatureExtractorC()
self.QRelCenter = AdhocQRelC()
self.QRelIn = ""
def Init(self):
cxBaseC.Init(self)
self.lQObjFeatureGroup = []
self.lObjObjFeatureGroup = []
self.lDocObjFeatureGroup = []
self.QObjAnaExtractor = QueryObjEdgeFeatureAnaExtractorC()
self.DocObjFaccExtractor = DocObjEdgeFeatureFaccExtractorC()
self.ObjObjKGExtractor = ObjObjEdgeFeatureKGExtractorC()
self.ObjObjPreCalcExtractor = ObjObjEdgeFeaturePreCalcSimExtractorC()
self.ObjObjTextSimExtractor = ObjObjEdgeFeatureTextSimExtractorC()
self.Searcher = IndriSearchCenterC()
self.ObjCenter = FbObjCacheCenterC()
self.NodeDir = ""
def Init(self):
cxBaseC.Init(self)
self.FeatureName = 'ObjObjEdge'
def Init(self):
cxBaseC.Init(self)
self.DataDir = ""
self.QInName = ""
def Init(self):
cxBaseC.Init(self)
self.FaccDataCenter = FaccDataCenterC()
def Init(self):
cxBaseC.Init(self)
self.DocKgDir = ""
def Init(self):
cxBaseC.Init(self)
self.hQObj = {}
self.DocKgDir = ""
self.Inferencer = BoeLmC()
self.lInferenceWeight = [1, 0, 0]
def Init(self):
cxBaseC.Init(self)
self.GraphFormer = DocKGUnsupervisedFormerC() #virtual here
self.GraphSource = 'tagme'
self.OutDir = ""
def Init(self):
cxBaseC.Init(self)
self.Searcher = IndriSearchCenterC()
self.ObjCenter = FbObjCacheCenterC()
self.NeighborNum = 50
def Init(self):
cxBaseC.Init(self)
self.hQObj = {}
self.DocKgDir = ""
def Init(self):
cxBaseC.Init(self)
self.Prepared = False
return
