diff --git a/data-computer/v1/lda.py b/data-computer/v1/lda.py
index d6a9a01..66c4535 100755
--- a/data-computer/v1/lda.py
+++ b/data-computer/v1/lda.py
@@ -40,7 +40,7 @@
 def tokenize(text):
     tokens = [word for word in text.replace("'"," ").split() if word not in stopwords and len(word)>2]
     if len(tokens)==0:
-        return ["n/a"]
+        return []
     return tokens
 
 # Max topic
@@ -68,11 +68,11 @@
 
 
 # following parameters depends of the size of the corpus : num_topics and num_iterations
-n = len(all_data)
-if n< 1001:
+len_data = len(all_data)
+if len_data< 1001:
     num_topics = 10
     num_iterations=150
-elif n < 20001:
+elif len_data < 20001:
     num_topics = 15
     num_iterations=200
 else:
@@ -82,16 +82,52 @@
 
 # training LDA
 texts = []
-for line in all_data:
-    if "value" in line:
-        texts.append(tokenize(lemmatize(uniformize(line["value"]))))
+index_without_value = []
+for i in range(len_data):
+    line = all_data[i]
+    if "value" in line and type(line["value"])==str:
+        tokens = tokenize(lemmatize(uniformize(line["value"])))
+        if tokens != []:
+            texts.append(tokenize(lemmatize(uniformize(line["value"]))))
+        else:
+            index_without_value.append(i)
     else:
-        texts.append("n/a")
+        index_without_value.append(i)
 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)
+dictionary.filter_extremes(no_below=3,no_above=0.8)
 corpus = [dictionary.doc2bow(text) for text in texts]
 
-lda_model = models.LdaModel(corpus, num_topics=num_topics, id2word=dictionary,iterations=num_iterations,alpha="symmetric", eta = "auto",minimum_probability=0.1)
+try:
+    lda_model = models.LdaModel(corpus, num_topics=num_topics, id2word=dictionary,iterations=num_iterations,alpha="symmetric", eta = "auto",minimum_probability=0.1)
+except:
+    index_without_value = [i for i in range(len_data)]
+
+
+# extract infos
+for i in range(len_data):
+
+    #return n/a if docs wasn't in model
+    if i in index_without_value:
+        line["value"]="n/a"
+        sys.stdout.write(json.dumps(line))
+        sys.stdout.write("\n")
+    else:
+        line = all_data[i]
+        doc = line["value"]
+        doc_bow = dictionary.doc2bow(tokenize(uniformize(line["value"])))
+        topics = lda_model[doc_bow]
+        topic_info = {}
+        for topic_id, topic_weight in topics:
+            topic_info[f"topic_{topic_id + 1}"] = {}
+            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["value"]={}
+        line["value"]["topics"]=topic_info
+        line["value"]["best_topic"]=max_topic(topic_info)
+        sys.stdout.write(json.dumps(line))
+        sys.stdout.write("\n")
 
 
 # #To see topics (to test it with a jsonl file)
@@ -101,25 +137,3 @@
 # cm = models.coherencemodel.CoherenceModel(model=lda_model, texts=texts, coherence='c_v')
 # cm.get_coherence()
 # exit()
-
-
-# extract infos
-for line in all_data:
-    doc = line["value"]
-    doc_bow = dictionary.doc2bow(tokenize(uniformize(line["value"])))
-    topics = lda_model[doc_bow]
-    topic_info = {}
-    for topic_id, topic_weight in topics:
-        topic_info[f"topic_{topic_id + 1}"] = {}
-        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["value"]={}
-    line["value"]["topics"]=topic_info
-    line["value"]["best_topic"]=max_topic(topic_info)
-
-# Write output
-for line in all_data:
-    sys.stdout.write(json.dumps(line))
-    sys.stdout.write("\n")