diff --git a/data-computer/v1/lda.py b/data-computer/v1/lda.py
index 6ded96c..6b42d0f 100755
--- a/data-computer/v1/lda.py
+++ b/data-computer/v1/lda.py
@@ -4,7 +4,6 @@
 import sys
 from gensim import corpora, models
 import unicodedata
-import string
 import re
 import spacy
 
@@ -27,10 +26,9 @@
     text = remove_accents(text)
 
     # remove punctuation except " ' "
-    punctuation = ''.join(char for char in string.punctuation if char != "'")
-    text = ''.join(char for char in text if char not in punctuation)
+    text = ''.join(char if char.isalpha() or char == "'" else ' ' for char in text)
 
-    return text.lower()
+    return ' '.join(text.lower().split())
 
 #lemmatize
 def lemmatize(text):
@@ -59,13 +57,13 @@
 n = len(all_data)
 if n< 1001:
     num_topics = 10
-    num_iterations=100
+    num_iterations=150
 elif n < 20001:
     num_topics = 15
-    num_iterations=150
+    num_iterations=200
 else:
     num_topics = 20
-    num_iterations=200
+    num_iterations=250
 
 
 # training LDA
@@ -76,10 +74,14 @@
     else:
         texts.append("n/a")
 dictionary = corpora.Dictionary(texts) # Create a tf dictionary, but replace text by an id : [ [(id_token,numb_token),...] , [....] ]. The list represent docs of corpus
+dictionary.filter_extremes(no_below=3,no_above=0.6)
 corpus = [dictionary.doc2bow(text) for text in texts]
 
-lda_model = models.LdaModel(corpus, num_topics=num_topics, id2word=dictionary,iterations=num_iterations)
+lda_model = models.LdaModel(corpus, num_topics=num_topics, id2word=dictionary,iterations=num_iterations,alpha="symmetric", eta = "auto",minimum_probability=0.1)
 
+# To see topics (just for me)
+# sys.stdout.write(json.dumps(lda_model.print_topics()))
+# exit()
 
 # extract infos
 for line in all_data:
@@ -92,11 +94,10 @@
         topic_words = [word for word, _ in lda_model.show_topic(topic_id)]
         topic_info[f"topic_{topic_id + 1}"]["words"] = topic_words
         topic_info[f"topic_{topic_id + 1}"]["weight"] = str(topic_weight)
-    
+
     line["lda"]= topic_info
 
 # Write all corpus in once
 for line in all_data:
     sys.stdout.write(json.dumps(line))
     sys.stdout.write("\n")
-