...

[iramuteq] / iracmd.py

diff --git a/iracmd.py b/iracmd.py
index 3d496cb..aefb09d 100644 (file)
--- a/iracmd.py
+++ b/iracmd.py
@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 #Author: Pierre Ratinaud
 #Copyright (c) 2010 Pierre Ratinaud
-#Lisense: GNU/GPL
+#License: GNU/GPL
 
 import os
 from optparse import OptionParser
@@ -18,8 +18,8 @@ from ConfigParser import *
 #from textchdalc import AnalyseAlceste
 #from textdist import PamTxt
 #from textafcuci import AfcUci
-from analysetxt import Alceste
-from corpus import Corpus, copycorpus, BuildFromAlceste
+from textreinert import Reinert
+from corpus import Corpus, copycorpus, BuildFromAlceste, BuildSubCorpus
 from textaslexico import Lexico
 from textstat import Stat
 from tools import SubCorpus
@@ -132,6 +132,8 @@ class CmdLine :
                 pathout = os.path.dirname(os.path.dirname(os.path.abspath(options.read)))
                 self.corpus = corpus
                 print self.corpus
+                corpus.parametres['pathout'] = '/home/pierre/fac/etudiant/verdier/corpus20_corpus_2/test2'
+                BuildSubCorpus(corpus, parametres = {'fromthem' : True, 'theme' : [u'-*thématique_idéal']})
 
             if corpus is not None :
                 corpus.conn_all()
@@ -143,16 +145,20 @@ class CmdLine :
 #            log.warning('ATTENTION gethapaxuces')
 #            MakeUciStat(corpus)
             #corpus.gethapaxuces()
-                ucisize = corpus.getucisize()
-                ucisize = [`val` for val in ucisize]
-                uciet = [[val.split('_')[1] for val in uci.etoiles[1:]] for uci in corpus.ucis]
-                #for line in uciet :
+             #   ucisize = corpus.getucisize()
+             #   ucisize = [`val` for val in ucisize]
+                #uciet = [uci.etoiles[1:] for uci in corpus.ucis]
+                #uceet = [corpus.ucis[uce.uci].etoiles[1:] for uci in corpus.ucis for uce in uci.uces]
+                #print uceet[0:10]
+                #for line in uceet :
                 #    print '\t'.join(line)
                 #res = zip(uciet, ucisize)
-                res = [uciet[i] + [ucisize[i]] for i, val in enumerate(uciet)]
-                print res[0:10]
-                with open('ucisize.csv', 'w') as f :
-                    f.write('\n'.join(['\t'.join(val) for val in res]))
+             #   res = [uciet[i] + [ucisize[i]] for i, val in enumerate(uciet)]
+             #   print res[0:10]
+                #ucesize = corpus.getucesize()
+                #print ucesize[0:40]
+                #with open('sentences_size.csv', 'w') as f :
+                #    f.write('\n'.join([`val`  for val in ucesize]))
                 #    self.content = f.read()
                 #self.content = self.content.replace('\r','')
                 if options.type_analyse == 'alceste' :
@@ -162,7 +168,7 @@ class CmdLine :
                     #corpus.read_corpus()
                     #corpus.parse_active(gramact, gramsup)
                     config['type'] = 'alceste'
-                    self.Text = Alceste(self, corpus, parametres = config)
+                    self.Text = Reinert(self, corpus, parametres = config)
                 #    self.Text = AnalyseAlceste(self, cmd = True, big = True)
                     #self.Text = AnalyseAlceste(self, cmd = True)
                 elif options.type_analyse == 'pam' :