def TrainUsingSVM(xmls, annotatedxmlloc):
svm = SVMImpl()
trainer = Utils.Trainer.Trainer()
tableslist = list()
for xml in xmls:
tableslist.append(trainer.readAnnotatedxmlforTableDecomposition(annotatedxmlloc + xml + "_TD_ANNOTATED"))
svm.domaintrainforTableDecomposition(tableslist)
return svm
def TrainUsingSVM(xmls, preprocessor, trainer, xmlloc, annotatedxmlloc):
svm = SVMImpl()
annotatedxmllist = list()
for xmlname in xmls:
fontdict = preprocessor.getFontDictionary(ET.parse(xmlloc + xmlname + ".xml")) #list(pages), pages -> list(cols), col -> list(<Sparse/NonSparse, tag>)
annotatedxml = trainer.readAnnotatedXml(annotatedxmlloc + xmlname + "_annotated")
annotatedxmllist.append([annotatedxml, fontdict])
svm.domaintrain(annotatedxmllist)
return svm
def TrainUsingSVM(xmls, annotatedxmlloc):
svm = SVMImpl()
trainer = Utils.Trainer.Trainer()
tableslist = list()
for xml in xmls:
tableslist.append(
trainer.readAnnotatedxmlforTableDecomposition(annotatedxmlloc +
xml +
"_TD_ANNOTATED"))
svm.domaintrainforTableDecomposition(tableslist)
return svm
def TrainUsingSVM(xmls, preprocessor, trainer, xmlloc, annotatedxmlloc):
svm = SVMImpl()
annotatedxmllist = list()
for xmlname in xmls:
fontdict = preprocessor.getFontDictionary(
ET.parse(xmlloc + xmlname + ".xml")
) #list(pages), pages -> list(cols), col -> list(<Sparse/NonSparse, tag>)
annotatedxml = trainer.readAnnotatedXml(annotatedxmlloc + xmlname +
"_annotated")
annotatedxmllist.append([annotatedxml, fontdict])
svm.domaintrain(annotatedxmllist)
return svm
