parser.add_argument("-d", "--useDocs", action="store_true", help="Use document database to find relevant authors")
args = parser.parse_args()
averagePrecisionN = 20
ns = numpy.arange(5, 55, 5)
runLSI = not args.runLDA
knownAuthors = not args.useDocs
dataset = ArnetMinerDataset(runLSI=runLSI, knownAuthors=knownAuthors)
#dataset.dataFilename = dataset.dataDir + "DBLP-citation-100000.txt"
#dataset.dataFilename = dataset.dataDir + "DBLP-citation-1000000.txt"
#dataset.dataFilename = dataset.dataDir + "DBLP-citation-5000000.txt"
#dataset.dataFilename = dataset.dataDir + "DBLP-citation-7000000.txt"
dataset.dataFilename = dataset.dataDir + "DBLP-citation-Feb21.txt"
dataset.minDf = 10**-4
dataset.ks = [100, 200, 300, 400, 500, 600]
dataset.minDfs = [10**-3, 10**-4]
dataset.overwriteGraph = True
dataset.overwriteModel = True
dataset.overwriteVectoriser = True
if not knownAuthors:
dataset.modelSelection()
#Sav the outputList and the graph
fich = open("//home//idexlab//" + "TotalMeasuresBM25" + ".txt", "w")
fgraph = open("//home//idexlab//" + "GraphTotal" + ".txt", "w")
for field in dataset.fields:
logging.debug("Field = " + field)
if not knownAuthors:
