def testFindSimilarDocumentsLDA(self):
self.dataset = ArnetMinerDataset()
self.dataset.dataFilename = self.dataset.dataDir + "DBLP-citation-1000.txt"
self.dataset.overwrite = True
self.dataset.overwriteModel = True
self.dataset.overwriteVectoriser = True
self.dataset.k = 20
#Check document is correct as well as authors
self.dataset.findSimilarDocumentsLDA(self.field)
#Let's test order of ranking on larger dataset
print("Running on 10000 dataset using LDA")
dataset = ArnetMinerDataset()
dataset.minDf = 10**-5
dataset.dataFilename = dataset.dataDir + "DBLP-citation-10000.txt"
dataset.vectoriseDocuments()
relevantExperts = dataset.findSimilarDocumentsLDA("Neural Networks")
def testFindSimilarDocuments(self):
field = "Object"
self.dataset = ArnetMinerDataset()
self.dataset.dataFilename = self.dataset.dataDir + "DBLP-citation-test.txt"
#Check document is correct as well as authors
self.dataset.vectoriseDocuments()
relevantExperts = self.dataset.findSimilarDocumentsLSI(field)
self.assertEquals(['Jos\xc3\xa9 A. Blakeley'], relevantExperts)
#Let's test order of ranking on larger dataset
print("Running on 10000 dataset")
dataset = ArnetMinerDataset()
dataset.minDf = 10**-6
dataset.dataFilename = dataset.dataDir + "DBLP-citation-10000.txt"
dataset.vectoriseDocuments()
relevantExperts = dataset.findSimilarDocumentsLSI("Neural Networks")
self.assertEquals(['Christopher M. Bishop', 'Michael I. Jordan', 'Fred L. Kitchens', 'Ai Cheo', 'Cesare Alippi', 'Giovanni Vanini', 'C. C. Taylor', 'David J. Spiegelhalter', 'Donald Michie'], relevantExperts)
