outputFiles/07clusterDocs
pedigree="outputFiles/05creatSOM+TS=20120916-142354-404217-pedigree.html"
outputFiles/05creatSOM
- ~ = "outputFiles"
- metaHeaders =
"TITLE:"
"DATE-HEADER:"
"SOURCE:"
"LENGTH:"
"GEOGRAPHIC:"
"SECTION:"
"SUBJECT:"
"PUBLICATION-TYPE:"
"GRAPHIC:"
- docs2exclude = [empty string]
- cols2exclude = [empty string]
- minSumCols = 0.2
- nTrainingMatrices = 3
- inputMatrix = "~/04ldacol+TS=20120916-142354-387370+nIter=500.mat"
pedigree = "~/04ldacol+TS=20120916-142354-387370-pedigree.html"
pedigree="outputFiles/04ldacol+TS=20120916-142354-387370-pedigree.html"
outputFiles/04ldacol
pedigree="outputFiles/03redTMT+TS=20120916-142354-352082-pedigree.html"
outputFiles/03redTMT.mat
- ~ = "outputFiles"
- stopList = "../wordlists/ENstoplist.txt"
- minWordCount = 10
- classDocs = [empty string]
- codes2keep = [empty array]
- logFile = "outputFiles/00errors_log.tab"
- inputTMT = "~/02TMT+TS=20120916-142354-315426.mat"
pedigree = "~/02TMT+TS=20120916-142354-315426-pedigree.html"
pedigree="outputFiles/02TMT+TS=20120916-142354-315426-pedigree.html"
outputFiles/02TMT.mat
pedigree="outputFiles/01dictionary+TS=20120916-142353-937932-pedigree.html"
outputFiles/01dictionary.txt
- ~ = "outputFiles"
- substitutionsScript = "tvtSubstitutions"
- extractDateScript = "extractDateUS"
- validationScript = "validateDocument"
- dataHeaders =
"TITLE:"
"HEADLINE:"
"TITLE2:"
"SUBHEAD:"
"HIGHLIGHT:"
"TXT"
"CAPTION:"
"CUTLINES:"
"TEXTOFGRAPHIC:"
- metaHeaders =
"TITLE:"
"DATE-HEADER:"
"SOURCE:"
"LENGTH:"
"GEOGRAPHIC:"
"SECTION:"
"SUBJECT:"
"PUBLICATION-TYPE:"
"GRAPHIC:"
- dateHeaders = "DATE-HEADER:"
- logFile = "outputFiles/00errors_log.tab"
pedigree="outputFiles/09metaClasses+TS=20120916-142354-521972-pedigree.html"
outputFiles/09metaClasses
- ~ = "outputFiles"
- metaHeaders =
"TITLE:"
"DATE-HEADER:"
"SOURCE:"
"LENGTH:"
"GEOGRAPHIC:"
"SECTION:"
"SUBJECT:"
"PUBLICATION-TYPE:"
"GRAPHIC:"
- nSamples = Inf
- metafieldName = "SOURCE:"
- metafieldRegexp = "^(USA TODAY|The New York Times)$"
- metafieldRegexpRep =
"^USA TODAY"
"^The New York Times"
"^[^+].*$"
- inputData = "~/05creatSOM+TS=20120916-142354-404217"
pedigree = "~/05creatSOM+TS=20120916-142354-404217-pedigree.html"
pedigree="outputFiles/05creatSOM+TS=20120916-142354-404217-pedigree.html"
outputFiles/05creatSOM
- ~ = "outputFiles"
- metaHeaders =
"TITLE:"
"DATE-HEADER:"
"SOURCE:"
"LENGTH:"
"GEOGRAPHIC:"
"SECTION:"
"SUBJECT:"
"PUBLICATION-TYPE:"
"GRAPHIC:"
- docs2exclude = [empty string]
- cols2exclude = [empty string]
- minSumCols = 0.2
- nTrainingMatrices = 3
- inputMatrix = "~/04ldacol+TS=20120916-142354-387370+nIter=500.mat"
pedigree = "~/04ldacol+TS=20120916-142354-387370-pedigree.html"
pedigree="outputFiles/04ldacol+TS=20120916-142354-387370-pedigree.html"
outputFiles/04ldacol
pedigree="outputFiles/03redTMT+TS=20120916-142354-352082-pedigree.html"
outputFiles/03redTMT.mat
- ~ = "outputFiles"
- stopList = "../wordlists/ENstoplist.txt"
- minWordCount = 10
- classDocs = [empty string]
- codes2keep = [empty array]
- logFile = "outputFiles/00errors_log.tab"
- inputTMT = "~/02TMT+TS=20120916-142354-315426.mat"
pedigree = "~/02TMT+TS=20120916-142354-315426-pedigree.html"
pedigree="outputFiles/02TMT+TS=20120916-142354-315426-pedigree.html"
outputFiles/02TMT.mat
pedigree="outputFiles/01dictionary+TS=20120916-142353-937932-pedigree.html"
outputFiles/01dictionary.txt
- ~ = "outputFiles"
- substitutionsScript = "tvtSubstitutions"
- extractDateScript = "extractDateUS"
- validationScript = "validateDocument"
- dataHeaders =
"TITLE:"
"HEADLINE:"
"TITLE2:"
"SUBHEAD:"
"HIGHLIGHT:"
"TXT"
"CAPTION:"
"CUTLINES:"
"TEXTOFGRAPHIC:"
- metaHeaders =
"TITLE:"
"DATE-HEADER:"
"SOURCE:"
"LENGTH:"
"GEOGRAPHIC:"
"SECTION:"
"SUBJECT:"
"PUBLICATION-TYPE:"
"GRAPHIC:"
- dateHeaders = "DATE-HEADER:"
- logFile = "outputFiles/00errors_log.tab"