From: Pierre Ratinaud Date: Tue, 20 Jun 2017 14:11:21 +0000 (+0200) Subject: profile translation X-Git-Url: http://iramuteq.org/git?a=commitdiff_plain;h=b4ab59a79dbc62d4234778e793c05718648c6775;p=iramuteq profile translation --- diff --git a/ProfList.py b/ProfList.py index da8d316..6b553e9 100644 --- a/ProfList.py +++ b/ProfList.py @@ -31,12 +31,13 @@ from copy import copy #--------------------------------------------------------------------------- class ProfListctrlPanel(wx.ListCtrl, listmix.ListCtrlAutoWidthMixin, listmix.ColumnSorterMixin): - def __init__(self, parent, gparent, profclasse, Alceste=False, cl=0): + def __init__(self, parent, gparent, profclasse, Alceste=False, cl=0, translation = False): wx.ListCtrl.__init__( self, parent, -1, style=wx.LC_REPORT|wx.LC_VIRTUAL|wx.LC_HRULES|wx.LC_VRULES) self.parent = parent self.Alceste = Alceste self.Source = gparent + self.translation = translation self.cl = cl self.var_mod = {} self.them_mod = {} @@ -714,7 +715,7 @@ class ProfListctrlPanel(wx.ListCtrl, listmix.ListCtrlAutoWidthMixin, listmix.Col vchistable = [line[1:] for line in chistable] fchistable = [line[0] for line in chistable] words = self.getselectedwords() - tableout = [vchistable[fchistable.index(word)] for word in words] + tableout = [vchistable[fchistable.index(self.getword(word))] for word in words] tmpgraph = tempfile.mktemp(dir=self.Source.parent.TEMPDIR) nbcl = len(title) nbwords = len(words) @@ -733,9 +734,15 @@ class ProfListctrlPanel(wx.ListCtrl, listmix.ListCtrlAutoWidthMixin, listmix.Col vchistable = [line[1:] for line in chistable] fchistable = [line[0] for line in chistable] words = self.getselectedwords() - tableout = [vchistable[fchistable.index(word)] for word in words] + tableout = [vchistable[fchistable.index(self.getword(word))] for word in words] BarFrame(self.Source.parent, tableout, title, words, tree = self.Source.pathout['Rdendro']) + def getword(self, word) : + if self.translation : + return self.lems[word] + else : + return word + def make_concord(self, uces, title, color = 'red') : corpus = self.Source.corpus ListWord = [self.getColumnText(self.GetFirstSelected(), 6)] @@ -744,6 +751,7 @@ class ProfListctrlPanel(wx.ListCtrl, listmix.ListCtrlAutoWidthMixin, listmix.Col last = self.GetNextSelected(last) ListWord.append(self.getColumnText(last, 6)) ucef = [] + ListWord = [self.getword(word) for word in ListWord] if self.Source.parametres['classif_mode'] != 2 : for word in ListWord : uci = False @@ -811,6 +819,7 @@ class ProfListctrlPanel(wx.ListCtrl, listmix.ListCtrlAutoWidthMixin, listmix.Col #print 'ATTENTION PRINT ET TABLE' #corpus.make_et_table() word = self.getColumnText(self.GetFirstSelected(), 6) + word = self.getword(word) lems = corpus.getlems() uces = corpus.lc[self.cl-1] rep = [] diff --git a/functions.py b/functions.py index 2d72b4c..b41c483 100644 --- a/functions.py +++ b/functions.py @@ -794,3 +794,139 @@ def read_chd(filein, fileout): mere[line[2]] = mere[line[0]]['children'][-1] with open(fileout, 'w') as f : f.write(json.dumps(chd)) + + +translation_languages = {"Afrikaans":"af", "Albanian":"sq", "Amharic":"am", "Arabic":"ar", "Armenian":"hy", "Azeerbaijani":"az", "Basque":"eu", "Belarusian":"be", "Bengali":"bn", "Bosnian":"bs", "Bulgarian":"bg", "Catalan":"ca", "Cebuano":"ceb", "Chichewa":"ny", "Chinese (Simplified)":"zh-CN", "Chinese (Traditional)":"zh-TW", "Corsican":"co", "Croatian":"hr", "Czech":"cs", "Danish":"da", "Dutch":"nl", "English":"en", "Esperanto":"eo", "Estonian":"et", "Filipino":"tl", "Finnish":"fi", "French":"fr", "Frisian":"fy", "Galician":"gl", "Georgian":"ka", "German":"de", "Greek":"el", "Gujarati":"gu", "Haitian Creole":"ht", "Hausa":"ha", "Hawaiian":"haw", "Hebrew":"iw", "Hindi":"hi", "Hmong":"hmn ", "Hungarian":"hu", "Icelandic":"is", "Igbo":"ig", "Indonesian":"id", "Irish":"ga", "Italian":"it", "Japanese":"ja", "Javanese":"jw", "Kannada":"kn", "Kazakh":"kk", "Khmer":"km", "Korean":"ko", "Kurdish":"ku", "Kyrgyz":"ky", "Lao":"lo", "Latin":"la", "Latvian":"lv", "Lithuanian":"lt", "Luxembourgish":"lb", "Macedonian":"mk", "Malagasy":"mg", "Malay":"ms", "Malayalam":"ml", "Maltese":"mt", "Maori":"mi", "Marathi":"mr", "Mongolian":"mn", "Burmese":"my", "Nepali":"ne", "Norwegian":"no", "Pashto":"ps", "Persian":"fa", "Polish":"pl", "Portuguese":"pt", "Punjabi":"ma", "Romanian":"ro", "Russian":"ru", "Samoan":"sm", "Scots Gaelic":"gd", "Serbian":"sr", "Sesotho":"st", "Shona":"sn", "Sindhi":"sd", "Sinhala":"si", "Slovak":"sk", "Slovenian":"sl", "Somali":"so", "Spanish":"es", "Sundanese":"su", "Swahili":"sw", "Swedish":"sv", "Tajik":"tg", "Tamil":"ta", "Telugu":"te", "Thai":"th", "Turkish":"tr", "Ukrainian":"uk", "Urdu":"ur", "Uzbek":"uz", "Vietnamese":"vi", "Welsh":"cy", "Xhosa":"xh", "Yiddish":"yi", "Yoruba":"yo", "Zulu":"zu", } + + +def gettranslation(words, lf, lt) : + import urllib2 + import json + agent = {'User-Agent': + "Mozilla/4.0 (\ + compatible;\ + MSIE 6.0;\ + Windows NT 5.1;\ + SV1;\ + .NET CLR 1.1.4322;\ + .NET CLR 2.0.50727;\ + .NET CLR 3.0.04506.30\ + )"} + base_link = "https://translate.googleapis.com/translate_a/single?client=gtx&sl=%s&tl=%s&dt=t&q=%s" + print len(words) + totrans = urllib2.quote('\n'.join(words).encode('utf8')) + link = base_link % (lf, lt, totrans) + request = urllib2.Request(link, headers=agent) + raw_data = urllib2.urlopen(request).read() + data = json.loads(raw_data) + return [line[0].decode('utf8').replace(u"'", u'_').replace(u' | ', u'|').replace(u' ', u'_').replace(u'-',u'_').replace(u'\n','') for line in data[0]] + +def makenprof(prof, trans, deb=0) : + nprof=[] + if deb == 0 : + nprof.append(prof[0]) + for i, val in enumerate(trans) : + line = prof[deb+i+1][:] + line[6] = val + nprof.append(line) + return nprof + +def treatempty(val) : + if val.strip() == '' : + return '_' + else : + return val + +def translateprofile(corpus, dictprofile, lf='it', lt='fr') : + nprof = {} + lems = {} + for i in range(len(dictprofile)) : + prof = dictprofile[`i+1`] + try : + lenact = prof.index([u'*****', u'*', u'*', u'*', u'*', u'*', '', '']) + lensup = -1 + except ValueError: + try : + lenact = prof.index([u'*', u'*', u'*', u'*', u'*', u'*', '', '']) + lensup = 0 + except ValueError: + lenact = len(prof) + lensup = 0 + try : + lensup += prof.index([u'*', u'*', u'*', u'*', u'*', u'*', '', '']) + lensup = lensup - lenact + except ValueError: + lensup += len(prof) - lenact + if lenact != 0 : + if lenact > 400 : + nlenact = 400 + else : + nlenact = lenact + actori = [line[6] for line in prof[1:nlenact]] + act = [val.replace(u'_', u' ') for val in actori] + act = gettranslation(act, lf, lt) + for j, val in enumerate(actori) : + if act[j] not in lems : + lems[act[j]] = val + else : + while act[j] in lems : + act[j] = act[j] + u"+" + lems[act[j]] = val + nprof[`i+1`] = makenprof(prof, act) + + if lensup != 0 : + if lensup > 400 : + nlensup = 400 + else : + nlensup = lensup + supori = [line[6] for line in prof[(1+lenact):(lenact+nlensup)]] + sup = [val.replace(u'_', u' ') for val in supori] + sup = [treatempty(val) for val in sup] + sup = gettranslation(sup, lf, lt) + for j, val in enumerate(supori) : + if sup[j] not in lems : + lems[sup[j]] = val + else : + while sup[j] in lems : + sup[j] = sup[j] + u"+" + lems[sup[j]] = val + nprof[`i+1`].append([u'*****', u'*', u'*', u'*', u'*', u'*', '', '']) + nprof[`i+1`] += makenprof(prof, sup, deb=lenact) + + try : + lenet = prof.index([u'*', u'*', u'*', u'*', u'*', u'*', '', '']) + nprof[`i+1`].append([u'*', u'*', u'*', u'*', u'*', u'*', '', '']) + nprof[`i+1`] += prof[(lenet+1):] + except : + pass + return nprof, lems + + +def write_translation_profile(prof, lems, language, dictpathout) : + if os.path.exists(dictpathout['translations.txt']) : + with codecs.open(dictpathout['translations.txt'], 'r', 'utf8') as f : + translist = f.read() + translist = [line.split('\t') for line in translist.splitlines()] + else : + translist = [] + toprint = [] + toprint.append(['','','','','','']) + toprint.append([u'***', u'nb classes', `len(prof)`, u'***', '', '']) + for i in range(len(prof)) : + toprint.append([u'**', u'classe', `i+1`, u'**', '', '']) + toprint.append([u'****'] + prof[`i+1`][0] + [u'****']) + rest = [[`line[1]`, `line[2]`, `line[3]`, `line[4]`, line[6], line[7].replace('< 0,0001', '0.00009').replace('NS (','').replace(')','')] for line in prof[`i+1`][1:]] + for i, line in enumerate(prof[`i+1`][1:]) : + if line[0] == u'*' : + rest[i] = [u'*', u'*', u'*', u'*', u'*', u'*'] + elif line[0] == u'*****' : + rest[i] = [u'*****',u'*',u'*', u'*', u'*', u'*'] + toprint += rest + with open(dictpathout['translation_profile_%s.csv' % language], 'w') as f : + f.write('\n'.join([';'.join(line) for line in toprint]).encode('utf8')) + with open(dictpathout['translation_words_%s.csv' % language], 'w') as f : + f.write('\n'.join(['\t'.join([val, lems[val]]) for val in lems]).encode('utf8')) + if 'translation_profile_%s.csv' % language not in [val[0] for val in translist] : + translist.append(['translation_profile_%s.csv' % language, 'translation_words_%s.csv' % language]) + with open(dictpathout['translations.txt'], 'w') as f : + f.write('\n'.join(['\t'.join(line) for line in translist]).encode('utf8')) diff --git a/layout.py b/layout.py index 54ea926..4ea02da 100644 --- a/layout.py +++ b/layout.py @@ -162,7 +162,7 @@ class GraphPanelAfc(wx.Panel): image_path = self.list_graph[image_id][0] viewer = ImageViewer(self, {'tmpgraph' : os.path.join(self.dirout,image_path), 'svg': 'FALSE', 'wildcard': '*.*'}, self.labels[image_id].GetLabelText(), self.listimg[image_id].GetSize()) viewer.Show() - #print image_path + #print image_path #print self.labels[image_id].GetLabelText() def afc_graph(self,event): @@ -299,7 +299,7 @@ class GraphPanelAfc(wx.Panel): # } # web = WebExport(self.ira, parametres) # afcout = web.exportafc() -# dial = SimpleDialog(self.ira) +# dial = SimpleDialog(self.ira) # dial.link.SetLabel(afcout) # dial.link.SetURL(afcout) # dial.Layout() @@ -351,15 +351,17 @@ class GraphPanel(wx.ScrolledWindow): self.SetFocus() -def open_antiprofil(panel, AntiProfile, encoding) : - DictAnti = ReadProfileAsDico(AntiProfile, True, encoding) +def open_antiprofil(panel, AntiProfile, encoding, title = _(u"Antiprofiles").decode('utf8'), translation = False, lems=None) : + if not translation : + DictAnti = ReadProfileAsDico(AntiProfile, True, encoding) + else : + DictAnti = AntiProfile panel.AntiProfNB = aui.AuiNotebook(panel, -1, wx.DefaultPosition) for i in range(0, panel.parametres['clnb']): - tabantiprofile = ProfListctrlPanel(panel, panel, DictAnti[str(i + 1)], True, i + 1) + tabantiprofile = ProfListctrlPanel(panel.parent, panel, DictAnti[str(i + 1)], True, i + 1, translation = translation) + tabantiprofile.lems = lems panel.AntiProfNB.AddPage(tabantiprofile, 'classe %s' % str(i + 1)) - panel.TabChdSim.AddPage(panel.AntiProfNB, _(u"Antiprofiles").decode('utf8')) - - + panel.TabChdSim.AddPage(panel.AntiProfNB, title) def getlemgram(corpus, lem) : if not lem[6] in corpus.lems : @@ -369,7 +371,7 @@ def getlemgram(corpus, lem) : class OpenCHDS(): def __init__(self, parent, corpus, parametres, Alceste=False): - #sep = u'\n ' + #sep = u'\n ' sep=' ' self.parent = parent self.corpus = corpus @@ -379,7 +381,7 @@ class OpenCHDS(): DictPathOut = self.pathout self.DictPathOut = DictPathOut self.dictpathout = DictPathOut - self.parent = parent + self.Alceste = Alceste Profile = DictPathOut['PROFILE_OUT'] AntiProfile = DictPathOut['ANTIPRO_OUT'] @@ -441,7 +443,7 @@ class OpenCHDS(): # #panel.chd_toolbar.AddLabelTool(self.ID_rapport, "rapport", rap_img, shortHelp=u"Produire le rapport", longHelp=u"Exporter un rapport en texte simple") # butrap = wx.Button(panel.chd_toolbar, self.ID_rapport, u"Rapport ") # panel.chd_toolbar.AddControl(butrap) -# +# # panel.chd_toolbar.Realize() # sizer1.Add(panel.chd_toolbar,0, wx.EXPAND, 5) @@ -454,7 +456,7 @@ class OpenCHDS(): sizer1.Add(panel.TabChdSim,10, wx.EXPAND, 5) panel.SetSizer(sizer1) sizer1.Fit(panel) - + if isinstance(self.corpus, Corpus) : panel.TabChdSim.corpus = corpus @@ -467,15 +469,13 @@ class OpenCHDS(): self.notenb = self.parent.nb.GetPageCount() - + if os.path.exists(self.DictPathOut['liste_graph_chd']) : list_graph = read_list_file(self.DictPathOut['liste_graph_chd'], self.encoding) CHD = GraphPanelDendro(panel.TabChdSim, DictPathOut, list_graph, txt = self.debtext) panel.TabChdSim.AddPage(CHD,'CHD') - - panel.ProfNB = aui.AuiNotebook(panel, -1, wx.DefaultPosition) - notebook_flags |= aui.AUI_NB_WINDOWLIST_BUTTON - panel.ProfNB.SetAGWWindowStyleFlag(notebook_flags) + + #panel.ProfNB.SetArtProvider(aui.ChromeTabArt()) #panel.ProfNB = LB.LabelBook(panel, -1, agwStyle = INB_LEFT|INB_SHOW_ONLY_TEXT|INB_FIT_LABELTEXT) #panel.ProfNB = wx.Listbook(self.parent, -1, style = wx.BK_DEFAULT) @@ -485,6 +485,11 @@ class OpenCHDS(): if os.path.exists(DictPathOut['prof_seg']) : prof_seg = ReadProfileAsDico(DictPathOut['prof_seg'], False, self.encoding) self.prof_seg_nb = aui.AuiNotebook(panel, -1, wx.DefaultPosition) + + + panel.ProfNB = aui.AuiNotebook(panel, -1, wx.DefaultPosition) + notebook_flags |= aui.AUI_NB_WINDOWLIST_BUTTON + panel.ProfNB.SetAGWWindowStyleFlag(notebook_flags) for i in range(0, clnb): self.cluster_size.append(DictProfile[str(i + 1)][0][0:3]) if isinstance(self.corpus, Corpus) : @@ -505,11 +510,11 @@ class OpenCHDS(): if clnb > 2 : self.TabAFC = aui.AuiNotebook(panel.TabChdSim, -1, wx.DefaultPosition) - log.info('read AFC') + log.info('read AFC') list_graph=read_list_file(DictPathOut['liste_graph_afc'], self.encoding) self.tabAFCGraph = GraphPanelAfc(self.TabAFC, DictPathOut, list_graph, self.clnb, coding=self.encoding) self.TabAFC.AddPage(self.tabAFCGraph, _(u"CA").decode('utf8')) - + if os.path.exists(self.DictPathOut['afc_facteur']) : dictrow, first = ReadList(self.DictPathOut['afc_facteur'], self.encoding) self.TabAFC_facteur = ListForSpec(self.parent, parametres, dictrow, first[1:]) @@ -520,7 +525,7 @@ class OpenCHDS(): self.TabAFC.AddPage(self.TabAFC_facteur, _(u"Factor").decode('utf8')) #self.TabAFC.AddPage(self.TabAFC_colonne, u'Colonnes') #self.TabAFC.AddPage(self.TabAFC_ligne, u'Lignes') - + sizer_3 = wx.BoxSizer(wx.VERTICAL) self.parent.nb_panel_2 = wx.Panel(panel.TabChdSim, -1) self.parent.button_simi = wx.Button(self.parent.nb_panel_2, -1, "Voyager") @@ -530,7 +535,7 @@ class OpenCHDS(): self.parent.nb_panel_2.SetSizer(sizer_3) self.TabAFC.AddPage(self.parent.nb_panel_2, _(u"3D graph").decode('utf8')) self.parent.Bind(wx.EVT_BUTTON, self.onsimi, self.parent.button_simi) - + panel.TabChdSim.AddPage(panel.ProfNB, _(u"Profiles").decode('utf8')) #panel.TabChdSim.AddPage(panel.AntiProfNB, 'Antiprofils') dlg.Update(4 + self.clnb, 'Affichage...') @@ -538,23 +543,43 @@ class OpenCHDS(): panel.TabChdSim.AddPage(self.TabAFC, _(u"CA").decode('utf8')) if os.path.exists(DictPathOut['prof_seg']) : panel.TabChdSim.AddPage(self.prof_seg_nb, _(u"Repeated segments profiles").decode('utf8')) - + # panel.Bind(wx.EVT_BUTTON, self.ongetrapport, id = self.ID_rapport) if os.path.exists(os.path.join(self.parametres['pathout'], 'tgenchi2.csv')) : self.parametres['tgenspec'] = os.path.join(self.parametres['pathout'], 'tgenchi2.csv') TgenLayout(panel) + + if os.path.exists(self.dictpathout['translations.txt']) : + with codecs.open(self.dictpathout['translations.txt'], 'r', 'utf8') as f: + translist = f.read() + translist = [line.split('\t') for line in translist.splitlines()] + for line in translist : + self.opentrans(line) + panel.TabChdSim.SetSelection(0) self.parent.nb.AddPage(panel, _(u"Clustering").decode('utf8') + ' - %s' % corpname) self.parent.ShowTab(True) - self.parent.nb.SetSelection(self.parent.nb.GetPageCount() - 1) + self.parent.nb.SetSelection(self.parent.nb.GetPageCount() - 1) #for pane in self.parent._mgr.GetAllPanes() : # if isinstance(pane.window, aui.AuiNotebook): # nb = pane.window # nb.SetAGWWindowStyleFlag(notebook_flags) # nb.SetArtProvider(aui.ChromeTabArt()) - dlg.Destroy() + dlg.Destroy() + + self.parent._mgr.Update() - + + def opentrans(self, trans) : + prof = ReadProfileAsDico(self.dictpathout[trans[0]], False, 'utf8') + with codecs.open(self.dictpathout[trans[1]], 'r', 'utf8') as f : + lems = f.read() + lems = [line.split('\t') for line in lems.splitlines()] + lems = dict(lems) + open_antiprofil(self.panel, prof, 'utf8', title = trans[0], translation=True, lems=lems) + self.panel.lems = lems + self.panel.TabChdSim.SetSelection(self.panel.TabChdSim.GetPageCount() - 1) + def onsimi(self,event): outfile = print_simi3d(self) error = exec_rcode(self.parent.RPath, outfile, wait = True) @@ -615,7 +640,7 @@ def PrintRapport(self, corpus, parametres, istxt = True): txt += ' '.join([u'%i' % sum([len(cl) for cl in corpus.lc]), _(u'texts classified on').decode('utf8'), '%i (%.2f%%)%s' % (corpus.getucinb(), (float(sum([len(cl) for cl in corpus.lc]))) / float(corpus.getucinb()) * 100, sep)]) else : txt += ' '.join(['%i' % self.ucecla, _(u'line classified on').decode('utf8'), '%i (%.2f%%)%s' % (self.Ucenb, (float(self.ucecla) / float(self.Ucenb)) * 100, sep)]) - + txt += ''.join([sep, u'###########################', sep, _(u'time').decode('utf8'), ' : %s' % parametres.get('time', ''), sep, u'###########################', sep]) with open(self.pathout['pre_rapport'], 'w') as f : @@ -630,11 +655,11 @@ class SashList(wx.Panel) : #self.gparent=gparent #self.dlist=dlist #self.first = first - #self.menu = menu + #self.menu = menu # A window to the left of the client window #self.listlex = listlex self.leftwin1 = wx.SashLayoutWindow( - self, -1, wx.DefaultPosition, (200, 300), + self, -1, wx.DefaultPosition, (200, 300), wx.NO_BORDER|wx.SW_3D ) @@ -644,9 +669,9 @@ class SashList(wx.Panel) : self.leftwin1.SetBackgroundColour(wx.Colour(0, 255, 0)) self.leftwin1.SetSashVisible(wx.SASH_RIGHT, True) self.leftwin1.SetExtraBorderSize(10) - + #textWindow = wx.TextCtrl( - # leftwin1, -1, "", wx.DefaultPosition, wx.DefaultSize, + # leftwin1, -1, "", wx.DefaultPosition, wx.DefaultSize, # wx.TE_MULTILINE|wx.SUNKEN_BORDER # ) @@ -654,9 +679,9 @@ class SashList(wx.Panel) : self.leftWindow1 = self.leftwin1 winids.append(self.leftwin1.GetId()) - + rightwin1 = wx.SashLayoutWindow( - self, -1, wx.DefaultPosition, (200, 300), + self, -1, wx.DefaultPosition, (200, 300), wx.NO_BORDER|wx.SW_3D ) @@ -667,7 +692,7 @@ class SashList(wx.Panel) : rightwin1.SetSashVisible(wx.SASH_RIGHT, True) rightwin1.SetExtraBorderSize(10) #textWindow = wx.TextCtrl( - # leftwin1, -1, "", wx.DefaultPosition, wx.DefaultSize, + # leftwin1, -1, "", wx.DefaultPosition, wx.DefaultSize, # wx.TE_MULTILINE|wx.SUNKEN_BORDER # ) @@ -702,7 +727,7 @@ class TgenLayout : if tab.tgen : tgentab = tab break - + if tgentab : self.page.tgentab.RefreshData(self.page.tgens) self.page.tgentab.tgens = tgen.tgen @@ -733,12 +758,12 @@ class dolexlayout : self.DictType, firstt = ReadList(self.dictpathout['tablespect'], self.corpus.parametres['syscoding']) self.DictEff, firsteff = ReadList(self.dictpathout['tableafcm'], self.corpus.parametres['syscoding']) self.DictEffType, firstefft = ReadList(self.dictpathout['tabletypem'], self.corpus.parametres['syscoding']) - self.DictEffRelForme, firsteffrelf = ReadList(self.dictpathout['eff_relatif_forme'], self.corpus.parametres['syscoding']) - self.DictEffRelType, firsteffrelt = ReadList(self.dictpathout['eff_relatif_type'], self.corpus.parametres['syscoding']) + self.DictEffRelForme, firsteffrelf = ReadList(self.dictpathout['eff_relatif_forme'], self.corpus.parametres['syscoding']) + self.DictEffRelType, firsteffrelt = ReadList(self.dictpathout['eff_relatif_type'], self.corpus.parametres['syscoding']) self.etoiles = firsteff[1:] #sash = SashList(ira.nb) - - + + self.TabStat = aui.AuiNotebook(ira.nb, -1, wx.DefaultPosition) self.TabStat.parametres = parametres self.ListPan = ListForSpec(ira, self, self.DictSpec, self.etoiles) @@ -750,8 +775,8 @@ class dolexlayout : self.ListPanEffType = ListForSpec(ira, self, self.DictEffType, self.etoiles) self.ListPanEffRelForme = ListForSpec(ira, self, self.DictEffRelForme, self.etoiles) self.ListPanEffRelType = ListForSpec(ira, self, self.DictEffRelType, self.etoiles) - - self.TabStat.AddPage(self.ListPan, _(u'Forms').decode('utf8')) + + self.TabStat.AddPage(self.ListPan, _(u'Forms').decode('utf8')) if os.path.exists(self.pathout['banalites.csv']) : self.TabStat.AddPage(self.listban, _(u'Banal forms').decode('utf8')) self.TabStat.AddPage(self.ListPant, _(u'POS').decode('utf8')) @@ -768,10 +793,10 @@ class dolexlayout : self.tabAFCTGraph = GraphPanelAfc(self.TabAFC, self.dictpathout, list_graph, self.parametres['clnb'], itempath ='liste_graph_afct', coding=self.encoding) self.TabAFC.AddPage(self.tabAFCTGraph, _(u'CA POS').decode('utf8')) self.TabStat.AddPage(self.TabAFC, _(u'CA').decode('utf8')) - + ira.nb.AddPage(self.TabStat, ' - '.join([_(u'Specificities').decode('utf8'), self.parametres['name']])) self.ira = ira - + self.TabStat.corpus = self.corpus self.TabStat.etoiles = self.etoiles if os.path.exists(os.path.join(self.parametres['pathout'], 'tgenspec.csv')) : @@ -787,6 +812,7 @@ class StatLayout: self.corpus = corpus self.ira = ira self.read_result() + self.parametres = parametres self.TabStat = aui.AuiNotebook(ira.nb, -1, wx.DefaultPosition) self.TabStat.parametres = parametres self.TabStat.corpus = corpus @@ -798,18 +824,18 @@ class StatLayout: list_graph = [['zipf.png', 'zipf']] self.TabStatTot = GraphPanel(ira.nb, self.pathout, list_graph, self.result['glob']) self.TabStat.AddPage(self.TabStatTot, _(u'Abstract').decode('utf8')) - + dictlabel = {'total' : _(u'Total').decode('utf8'), u'formes_actives' : _(u'Actives forms').decode('utf8'), u'formes_supplémentaires': _(u'Supplementary forms').decode('utf8'), u'hapax' : _(u'Hapax').decode('utf8'), } - + for item in self.result: if item != 'glob': datam = [['forme', 'nb']] self.ListPan = ListPanel(ira, self, self.result[item]) - self.TabStat.AddPage(self.ListPan, dictlabel[item]) + self.TabStat.AddPage(self.ListPan, dictlabel[item]) ira.nb.AddPage(self.TabStat, '%s' % parametres['name']) ira.nb.SetSelection(ira.nb.GetPageCount() - 1) ira.ShowAPane("Tab_content") @@ -818,7 +844,7 @@ class StatLayout: lcle = {'total' :u'total.csv', u'formes_actives':u'formes_actives.csv', u'formes_supplémentaires':u'formes_supplémentaires.csv', u'hapax': u'hapax.csv'} self.result = {} for key in lcle : - with open(self.pathout[lcle[key]], 'r') as f : + with codecs.open(self.pathout[lcle[key]], 'r', sys.getdefaultencoding()) as f : self.result[key] = [line.split(';') for line in f.read().splitlines()] self.result[key] = dict([[i,[line[0],int(line[1]), line[2]]] for i, line in enumerate(self.result[key])]) with open(self.pathout['glob.txt'], 'r') as f : @@ -846,7 +872,7 @@ class GraphPanelDendro(wx.Panel): self.butdendro = wx.BitmapButton(self, -1, dendro_img) self.butdendrotexte = wx.BitmapButton(self, -1, dendro_liste_img) self.butdendrocloud = wx.BitmapButton(self, -1, dendro_cloud_img) - + for i in range(0,len(list_graph)): if os.path.exists(os.path.join(self.dirout,list_graph[i][0])) : filename, ext = os.path.splitext(list_graph[i][0]) @@ -855,7 +881,7 @@ class GraphPanelDendro(wx.Panel): else : self.listimg.append(wx.StaticBitmap(self.panel_1, -1, wx.Bitmap(os.path.join(self.dirout,list_graph[i][0]), wx.BITMAP_TYPE_ANY))) self.labels.append(wx.StaticText(self.panel_1, -1, list_graph[i][1])) - + self.__set_properties() self.__do_layout() @@ -877,7 +903,7 @@ class GraphPanelDendro(wx.Panel): } self.type_dendro = [ u"phylogram", u"cladogram", u"fan", u"unrooted", u"radial" ] - def __do_layout(self): + def __do_layout(self): self.sizer_1 = wx.BoxSizer(wx.VERTICAL) self.sizer_2 = wx.BoxSizer(wx.HORIZONTAL) self.sizer_3 = wx.BoxSizer(wx.VERTICAL) @@ -892,7 +918,7 @@ class GraphPanelDendro(wx.Panel): self.panel_1.SetSizer(self.sizer_3) self.sizer_2.Add(self.sizer_1, 0, wx.EXPAND, 0) self.sizer_2.Add(self.panel_1, 1, wx.EXPAND, 0) - self.SetSizer(self.sizer_2) + self.SetSizer(self.sizer_2) def make_param(self, dial): self.param['width'] = dial.m_spinCtrl2.GetValue() @@ -903,6 +929,11 @@ class GraphPanelDendro(wx.Panel): self.param['color_nb'] = dial.m_radioBox1.GetSelection() self.param['taille_classe'] = dial.m_checkBox1.GetValue() self.param['type_tclasse'] = dial.m_radioBox2.GetSelection() + if self.param.get('translation', False) : + if dial.trans.GetSelection() == 0 : + del self.param['translation'] + else : + self.param['translation'] = self.param['translation'][dial.trans.GetSelection()-1][1] def make_dendro(self, dendro = 'simple') : if self.param['svg'] : @@ -953,9 +984,20 @@ class GraphPanelDendro(wx.Panel): debsup <- debet } chistable <- chistabletot[1:(debsup-1),] + """ % (ffr(self.dictpathout['RData.RData']), ffr(self.ira.RscriptsPath['Rgraph'])) + if self.param.get('translation', False) : + txt += """ + rn <- read.csv2("%s", header=FALSE, sep='\t') + rnchis <- row.names(chistable) + commun <- intersect(rnchis, unique(rn[,2])) + idrnchis <- sapply(commun, function(x) {which(rnchis==x)}) + idrn <- sapply(commun, function(x) {which(as.vector(rn[,2])==x)[1]}) + rownames(chistable)[idrnchis] <- as.vector(rn[idrn,1]) + """ % ffr(self.param['translation']) + txt += """ open_file_graph("%s", width=%i, height=%i, svg = %s) plot.dendro.prof(tree.cut1$tree.cl, classes, chistable, nbbycl = 60, type.dendro="%s", bw=%s, lab=NULL) - """ % (ffr(self.dictpathout['RData.RData']), ffr(self.ira.RscriptsPath['Rgraph']), ffr(fileout), width, height, svg, type_dendro, bw) + """ % (ffr(fileout), width, height, svg, type_dendro, bw) elif dendro == 'cloud' : txt += """ load("%s") @@ -974,7 +1016,7 @@ class GraphPanelDendro(wx.Panel): f.write(txt) busy = wx.BusyInfo(_("Please wait...").decode('utf8'), self.parent) wx.SafeYield() - error = exec_rcode(self.ira.RPath, tmpfile, wait=True) + error = exec_rcode(self.ira.RPath, tmpfile, wait=True) del busy check_Rresult(self.ira, error) self.list_graph.append([fileout, 'Dendrogramme CHD1 - %s' % type_dendro]) @@ -996,9 +1038,16 @@ class GraphPanelDendro(wx.Panel): if val == wx.ID_OK : self.make_param(dial) self.make_dendro() - + def ondendrotexte(self, evt): self.param['typedendro'] = 'texte' + if os.path.exists(self.dictpathout['translations.txt']) : + with codecs.open(self.dictpathout['translations.txt'], 'r', 'utf8') as f : + content = f.read() + print content + trans = [line.split('\t')[1] for line in content.splitlines()] + trans = [[val, self.dictpathout[val]] for val in trans] + self.param['translation'] = trans dial = PrefDendro(self.ira, self.param) val = dial.ShowModal() if val == wx.ID_OK : @@ -1038,14 +1087,14 @@ class CopusPanel(wx.Panel) : self.parametres = parametres fgSizer5 = wx.FlexGridSizer( 0, 2, 0, 0 ) fgSizer5.SetFlexibleDirection( wx.BOTH ) - fgSizer5.SetNonFlexibleGrowMode( wx.FLEX_GROWMODE_SPECIFIED ) + fgSizer5.SetNonFlexibleGrowMode( wx.FLEX_GROWMODE_SPECIFIED ) self.fgSizer5 = fgSizer5 - + self.m_staticText18 = wx.StaticText( self, wx.ID_ANY, _(u"Description of corpus").decode('utf8'), wx.DefaultPosition, wx.DefaultSize, 0 ) self.m_staticText18.Wrap( -1 ) fgSizer5.Add( self.m_staticText18, 0, wx.ALL, 5 ) - + self.m_staticText19 = wx.StaticText( self, wx.ID_ANY, u"", wx.DefaultPosition, wx.DefaultSize, 0 ) self.m_staticText19.Wrap( -1 ) fgSizer5.Add( self.m_staticText19, 0, wx.ALL, 5 ) @@ -1053,7 +1102,7 @@ class CopusPanel(wx.Panel) : self.m_staticText20 = wx.StaticText( self, wx.ID_ANY, u"Nom", wx.DefaultPosition, wx.DefaultSize, 0 ) self.m_staticText20.Wrap( -1 ) fgSizer5.Add( self.m_staticText20, 0, wx.ALL, 5 ) - + self.m_staticText21 = wx.StaticText( self, wx.ID_ANY, parametres['corpus_name'], wx.DefaultPosition, wx.DefaultSize, 0 ) self.m_staticText21.Wrap( -1 ) fgSizer5.Add( self.m_staticText21, 0, wx.ALL, 5 ) @@ -1073,7 +1122,7 @@ class CopusPanel(wx.Panel) : self.m_staticText18 = wx.StaticText( self, wx.ID_ANY, u"Paramètres", wx.DefaultPosition, wx.DefaultSize, 0 ) self.m_staticText18.Wrap( -1 ) fgSizer5.Add( self.m_staticText18, 0, wx.ALL, 5 ) - + self.m_staticText19 = wx.StaticText( self, wx.ID_ANY, u"", wx.DefaultPosition, wx.DefaultSize, 0 ) self.m_staticText19.Wrap( -1 ) fgSizer5.Add( self.m_staticText19, 0, wx.ALL, 5 ) @@ -1084,7 +1133,7 @@ class CopusPanel(wx.Panel) : self.m_staticText18 = wx.StaticText( self, wx.ID_ANY, u"Statistiques", wx.DefaultPosition, wx.DefaultSize, 0 ) self.m_staticText18.Wrap( -1 ) fgSizer5.Add( self.m_staticText18, 0, wx.ALL, 5 ) - + self.m_staticText19 = wx.StaticText( self, wx.ID_ANY, u"", wx.DefaultPosition, wx.DefaultSize, 0 ) self.m_staticText19.Wrap( -1 ) fgSizer5.Add( self.m_staticText19, 0, wx.ALL, 5 ) @@ -1147,8 +1196,9 @@ class LabbeLayout(DefaultTextLayout): list_graph = [['labbe-tree.png', _(u'Ward clustering (method ward2)').decode('utf8')], ['labbe-heatmap.png', _(u'Heatmap').decode('utf8')], ['labbe-matrix.png', _(u'Matrix').decode('utf8')]] - self.TabStatTot = GraphPanel(self.ira.nb, self.pathout, list_graph) - self.Tab.AddPage(self.TabStatTot, _(u"Labbe's distance").decode('utf8')) + for val in list_graph : + #self.TabStatTot = GraphPanel(self.ira.nb, self.pathout, [val]) + self.Tab.AddPage(GraphPanel(self.Tab, self.pathout, [val]), val[1]) self.Tab.corpus = self.corpus self.Tab.parametres = self.parametres self.ira.nb.AddPage(self.Tab, u'%s' % self.parametres['name']) @@ -1225,12 +1275,12 @@ class SimiLayout(DefaultTextLayout) : # 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) +# #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) # if prep.val == wx.ID_OK : # self.parametres = prep.parametres -# +# # script = PrintSimiScript(self) # script.make_script() # pid = exec_rcode(self.ira.RPath, script.scriptout, wait = True) @@ -1249,7 +1299,7 @@ class SimiLayout(DefaultTextLayout) : # #'bargraphw' : 60*int(self.param['clnb']), # } # web = WebExport(self.ira, parametres) -# fileout = web.exportsimi() +# fileout = web.exportsimi() # else : # fileout = script.filename # if os.path.exists(self.pathout['liste_graph']): @@ -1302,10 +1352,10 @@ class SimiLayout(DefaultTextLayout) : mss.CenterOnParent() mss.ShowModal() mss.Destroy() - + def blender(self, evt): blender(self) - + class DefaultMatLayout : def __init__(self, parent, tableau, parametres) : @@ -1344,7 +1394,7 @@ class Chi2Layout(DefaultMatLayout) : self.tab.parametres = self.parametres self.ira.nb.AddPage(self.tab, ' - '.join([u"Chi2", self.parametres['name']])) #self.ira.nb.SetSelection(self.ira.nb.GetPageCount() - 1) - #self.ira.ShowAPane("Tab_content") + #self.ira.ShowAPane("Tab_content") class ProtoLayout(DefaultMatLayout) : @@ -1370,7 +1420,7 @@ class SimiMatLayout(DefaultMatLayout) : self.indices = indices_simi if os.path.exists(self.pathout['liste_graph']) : list_graph = read_list_file(self.pathout['liste_graph']) - else : + else : list_graph = [['','']] notebook_flags = aui.AUI_NB_DEFAULT_STYLE | aui.AUI_NB_TAB_EXTERNAL_MOVE | aui.AUI_NB_TAB_MOVE | aui.AUI_NB_TAB_FLOAT self.tabsimi = aui.AuiNotebook(self.parent.nb, -1, wx.DefaultPosition) @@ -1437,7 +1487,7 @@ class SimiMatLayout(DefaultMatLayout) : graph_simi.append([os.path.basename(fileout), self.script.txtgraph]) else : graph_simi = [[os.path.basename(fileout), self.script.txtgraph]] - print_liste(self.pathout['liste_graph'], graph_simi) + print_liste(self.pathout['liste_graph'], graph_simi) DoConf().makeoptions([self.parametres['type']], [self.parametres], self.pathout['Analyse.ira']) if self.parametres['type_graph'] == 1: if self.parametres['svg'] : @@ -1450,7 +1500,7 @@ class SimiMatLayout(DefaultMatLayout) : self.graphpan.panel_1.Scroll(0,self.graphpan.panel_1.GetScrollRange(wx.VERTICAL)) else : self.dial.Destroy() - + def make_param(self) : if self.parametres['first'] : @@ -1492,7 +1542,7 @@ class SimiMatLayout(DefaultMatLayout) : 'com' : self.dial.comcheck.GetValue(), 'communities' : self.dial.choix_com.GetSelection(), 'edgecurved' : self.dial.check_curved.GetValue(), - } + } if 'cexfromchi' in self.parametres : paramsimi['cexfromchi'] = self.dial.checkit.GetValue() if 'sfromchi' in self.parametres : @@ -1508,7 +1558,7 @@ class SimiMatLayout(DefaultMatLayout) : if self.parametres['type_graph'] == 1 : graph = False wait = False - else : + else : graph = True wait = True pid = exec_rcode(self.parent.RPath, self.tmpfile, wait = wait, graph = graph) @@ -1517,8 +1567,8 @@ class SimiMatLayout(DefaultMatLayout) : dlg.Pulse(u'R ...') sleep(0.2) check_Rresult(self.parent, pid) - - def export(self, evt) : + + def export(self, evt) : nb = 1 while os.path.exists(os.path.join(self.pathout.dirout,'graph_'+str(nb)+'.graphml')): nb +=1 @@ -1552,11 +1602,11 @@ class SimiMatLayout(DefaultMatLayout) : mss.CenterOnParent() mss.ShowModal() mss.Destroy() - + def blender(self, evt): blender(self) - + class GraphPanelSimi(wx.Panel): def __init__(self,parent, dico, list_graph): wx.Panel.__init__(self,parent) @@ -1586,7 +1636,7 @@ class GraphPanelSimi(wx.Panel): else : self.listimg.append(wx.StaticBitmap(self.panel_1, -1, wx.Bitmap(os.path.join(self.dirout,list_graph[i][0]), wx.BITMAP_TYPE_ANY))) self.labels.append(wx.StaticText(self.panel_1, -1, list_graph[i][1])) - self.panel_1.Bind(wx.EVT_MOTION, self.onMouseMove) + self.panel_1.Bind(wx.EVT_MOTION, self.onMouseMove) self.__set_properties() self.__do_layout() @@ -1596,7 +1646,7 @@ class GraphPanelSimi(wx.Panel): self.panel_1.SetScrollRate(20, 20) self.panel_1.SetFocus() - def __do_layout(self): + def __do_layout(self): self.sizer_1 = wx.BoxSizer(wx.HORIZONTAL) self.sizer_2 = wx.BoxSizer(wx.VERTICAL) self.sizer_3 = wx.BoxSizer(wx.VERTICAL) @@ -1609,7 +1659,8 @@ class GraphPanelSimi(wx.Panel): self.panel_1.SetSizer(self.sizer_3) self.sizer_1.Add(self.sizer_2, 0, wx.EXPAND, 0) self.sizer_1.Add(self.panel_1, 1, wx.EXPAND, 0) - self.SetSizer(self.sizer_1) + self.SetSizer(self.sizer_1) def onMouseMove(self, event): self.panel_1.SetFocus() +