def profileModelSelection(self):
dataset = ArnetMinerDataset(runLSI=False)
dataset.overwrite = True
dataset.overwriteVectoriser = True
dataset.overwriteModel = True
dataset.dataFilename = dataset.dataDir + "DBLP-citation-100000.txt"
ProfileUtils.profile('dataset.modelSelection()', globals(), locals())
def profileComputeLDA(self):
field = "Boosting"
dataset = ArnetMinerDataset(field)
dataset.overwrite = True
dataset.overwriteVectoriser = True
dataset.overwriteModel = True
dataset.maxRelevantAuthors = 100
dataset.k = 200
dataset.dataFilename = dataset.dataDir + "DBLP-citation-100000.txt"
ProfileUtils.profile('dataset.computeLDA()', globals(), locals())
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)
numpy.random.seed(21)
parser = argparse.ArgumentParser(description='Run reputation evaluation experiments')
parser.add_argument("-r", "--runLDA", action="store_true", help="Run Latent Dirchlet Allocation")
args = parser.parse_args()
averagePrecisionN = 50
similarityCutoff = 0.30
ns = numpy.arange(5, 105, 5)
runLSI = not args.runLDA
dataset = ArnetMinerDataset(runLSI=runLSI)
#dataset.dataFilename = dataset.dataDir + "DBLP-citation-100000.txt"
#dataset.dataFilename = dataset.dataDir + "DBLP-citation-1000000.txt"
dataset.dataFilename = dataset.dataDir + "DBLP-citation-1000000.txt"
#dataset.dataFilename = dataset.dataDir + "DBLP-citation-7000000.txt"
#dataset.dataFilename = dataset.dataDir + "DBLP-citation-Feb21.txt"
dataset.overwriteGraph = True
dataset.overwriteModel = True
dataset.overwriteVectoriser = True
dataset.vectoriseDocuments()
dataset.loadVectoriser()
X = scipy.io.mmread(dataset.docTermMatrixFilename + ".mtx")
X = X.tocsc()
X.data[:] = 1
print(numpy.max(X.data), numpy.min(X.data))
