commited all contents created by participants

2017-12-21 18:12:40 +01:00
parent cefd1c2ad0
commit b936b1e616
2137 changed files with 1076319 additions and 730 deletions
@@ -0,0 +1,17 @@
+from nltk.tokenize import sent_tokenize, word_tokenize
+from nltk.corpus import stopwords
+import re
+ 
+data = "Sous le pont Mirabeau coule la Seine Et nos amours Faut-il qu'il m'en souvienne..."
+stopWords = set(stopwords.words('french'))
+words = word_tokenize(data)
+
+wordsFiltered = []
+ 
+for w in words:
+    if w not in stopWords:
+        wordsFiltered.append(w)
+ 
+print(wordsFiltered)
+#print(len(stopWords))
+#print(stopWords)