with codecs.open(self.pathout['actives.csv'], 'r', self.parametres['encoding']) as f :
self.actives = f.read()
self.actives = self.actives.splitlines()#[act for act in self.actives.splitlines()]
- dictcol = dict([[i, [act, self.corpus.getlemeff(act)]] for i, act in enumerate(self.actives)])
+ if os.path.exists(self.pathout['actives_nb.csv']) :
+ with open(self.pathout['actives_nb.csv'], 'r') as f :
+ act_nb = f.read()
+ act_nb = act_nb.splitlines()
+ dictcol = dict([[i, [self.actives[i], int(act_nb[i])]] for i, val in enumerate(self.actives)])
+ else :
+ dictcol = dict([[i, [act, self.corpus.getlemeff(act)]] for i, act in enumerate(self.actives)])
#res = SelectColumn(self.ira, dictcol, self.actives, self.pathout['selected.csv'], selected = selected, dlg = True)
#if res.ok :
prep = PrepSimi(self.ira, self, self.parametres,self.pathout['selected.csv'], self.actives, indices_simi, wordlist = dictcol, selected = selected)