def loadFile(self):
if self.fileIndex:
fn = self.recentFiles[self.fileIndex]
self.recentFiles.remove(fn)
self.recentFiles.insert(0, fn)
self.fileIndex = 0
else:
fn = self.recentFiles[0]
self.filecombo.clear()
for file in self.recentFiles:
self.filecombo.addItem(os.path.split(file)[1])
self.filecombo.updateGeometry()
self.error()
try:
self.stopwords = orngText.loadWordSet(fn)
except:
self.error("Cannot read the file")
self.graph.axisScale(QwtPlot.xBottom).interval().maxValue() -
self.graph.axisScale(QwtPlot.xBottom).interval().minValue()
) * self.percRadius / 100.0
if __name__ == "__main__":
#from orngTextCorpus import *
import pickle, orngText
## os.chdir("/home/mkolar/Docs/Diplomski/repository/orange/OrangeWidgets/Other/")
appl = QApplication(sys.argv)
ow = OWCorrAnalysis()
#owb = OWBagofWords.OWBagofWords()
t = orngText.loadFromXML(r'c:\test\orange\msnbc.xml')
#owb.data = t
#owb.show()
stop = orngText.loadWordSet(r'C:\tmtorange\common\en_stopwords.txt')
p = orngText.Preprocess(language='hr')
print('Done with loading')
t1 = orngText.extractLetterNGram(t, 2)
#t1 = orngText.extractWordNGram(t, stopwords = stop, measure = 'MI', threshold = 7, n=2)
#t1 = orngText.extractWordNGram(t1, stopwords = stop, measure = 'MI', threshold = 10, n=3)
#t1 = orngText.extractNamedEntities(t, stopwords = stop)
#t1 = orngText.bagOfWords(t1, stopwords = stop)
print(len(t1.domain.getmetas(orngText.TEXTMETAID)))
print('Done with extracting')
#t2 = orngText.FSS(t1, 'TF', 'MIN', 0.98)
#print len(t2.domain.getmetas())
print('Done with feature selection')
appl.setMainWidget(ow)
#t3 = orngText.DSS(t2, 'WF', 'MIN', 1)
#print 'Done with document selection'
self.graph.radius = 100.0
return
self.graph.radius = (self.graph.axisScale(QwtPlot.xBottom).interval().maxValue() - self.graph.axisScale(QwtPlot.xBottom).interval().minValue()) * self.percRadius / 100.0;
if __name__=="__main__":
#from orngTextCorpus import *
import cPickle, orngText
## os.chdir("/home/mkolar/Docs/Diplomski/repository/orange/OrangeWidgets/Other/")
appl = QApplication(sys.argv)
ow = OWCorrAnalysis()
#owb = OWBagofWords.OWBagofWords()
t = orngText.loadFromXML(r'c:\test\orange\msnbc.xml')
#owb.data = t
#owb.show()
stop = orngText.loadWordSet(r'C:\tmtorange\common\en_stopwords.txt')
p = orngText.Preprocess(language = 'hr')
print 'Done with loading'
t1 = orngText.extractLetterNGram(t, 2)
#t1 = orngText.extractWordNGram(t, stopwords = stop, measure = 'MI', threshold = 7, n=2)
#t1 = orngText.extractWordNGram(t1, stopwords = stop, measure = 'MI', threshold = 10, n=3)
#t1 = orngText.extractNamedEntities(t, stopwords = stop)
#t1 = orngText.bagOfWords(t1, stopwords = stop)
print len(t1.domain.getmetas(orngText.TEXTMETAID))
print 'Done with extracting'
#t2 = orngText.FSS(t1, 'TF', 'MIN', 0.98)
#print len(t2.domain.getmetas())
print 'Done with feature selection'
appl.setMainWidget(ow)
#t3 = orngText.DSS(t2, 'WF', 'MIN', 1)
#print 'Done with document selection'