X-Git-Url: http://iramuteq.org/git?p=iramuteq;a=blobdiff_plain;f=textstat.py;h=ee0e4ef4ae7a10dd7892f3bda67789a0f9320dae;hp=afc9ff16e188431b586c5c4c638e467c1f4973ac;hb=3563d5ffbef160a381af784d9d8cce2ce26e11d9;hpb=7fb5b2b86f6c9a0617208ee85211177c23d12f47

diff --git a/textstat.py b/textstat.py
index afc9ff1..ee0e4ef 100644
--- a/textstat.py
+++ b/textstat.py
@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 #Author: Pierre Ratinaud
 #Copyright (c) 2008-2012 Pierre Ratinaud
-#Lisense: GNU/GPL
+#License: GNU/GPL
 
 #from chemins import ConstructPathOut, StatTxtPathOut, ffr
 from chemins import PathOut
@@ -19,7 +19,6 @@ from time import sleep
 import wx
 import os
 
-print 'TEST LOGGING'
 import logging
 
 logger = logging.getLogger('iramuteq.textstat')
@@ -66,13 +65,13 @@ class Stat(AnalyseText) :
         phapax_forme = (float(len(hapax)) / (float(len(formes)))) * 100
         moy_occu_mot = float(occurrences) / float(len(formes))
         txt = 'Globale\n'
-        txt += 'nombre d\'uci : %i\n' % len(self.corpus.ucis)
+        txt += 'nombre de textes : %i\n' % len(self.corpus.ucis)
         txt += 'nombre d\'occurrences : %i\n' % occurrences
         txt += 'nombre de formes : %i\n' % (len(formes))
         txt += 'moyenne d\'occurrences par forme : %.2f\n' % moy_occu_mot
         txt += 'nombre d\'hapax : %i (%.2f%% des occurrences - %.2f%% des formes)\n' % (len(hapax), phapax, phapax_forme)
         print float(occurrences), float(len(self.corpus.ucis))
-        txt += 'moyenne d\'occurrences par uci : %.2f' % (float(occurrences)/float(len(self.corpus.ucis)))
+        txt += 'moyenne d\'occurrences par texte : %.2f' % (float(occurrences)/float(len(self.corpus.ucis)))
         if self.dlg :
              self.dlg.Update(7, u'Ecriture...')
         self.result['glob'] = txt
@@ -81,12 +80,17 @@ class Stat(AnalyseText) :
         txt = """
         source("%s")
         tot <- read.csv2("%s", header = FALSE, row.names = 1)
-        hapax <- read.csv2("%s", header = FALSE, row.names = 1)
-        tot <- rbind(tot, hapax)
+        """ % (self.parent.RscriptsPath['Rgraph'], self.pathout['total.csv'])
+        if len(hapax) :
+            txt += """
+            hapax <- read.csv2("%s", header = FALSE, row.names = 1)
+            tot <- rbind(tot, hapax)
+            """ % self.pathout['hapax.csv']
+        txt += """
         open_file_graph("%s", width = 400, height = 400)
-        plot(log(tot[,1]), log = 'x', xlab='log(rangs)', ylab = 'log(frequences)', col = 'red', pch=16)
+        plot(tot[,1], log = 'xy', xlab='log(rangs)', ylab = 'log(frequences)', col = 'red', pch=16)
         dev.off()
-        """ % (self.parent.RscriptsPath['Rgraph'], self.pathout['total.csv'], self.pathout['hapax.csv'], self.pathout['zipf.png'])
+        """ % (self.pathout['zipf.png'])
         tmpscript = tempfile.mktemp(dir=self.parent.TEMPDIR)
         with open(tmpscript, 'w') as f :
             f.write(txt)