diff --git a/data-computer/requirements.txt b/data-computer/requirements.txt
index 1a0fc4f..7a892f5 100755
--- a/data-computer/requirements.txt
+++ b/data-computer/requirements.txt
@@ -1,3 +1,4 @@
 gensim==4.3.2
 spacy==3.6.1
+scikit-learn==1.3.2
 en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.6.0/en_core_web_sm-3.6.0.tar.gz
diff --git a/data-computer/v1/hdbscan.py b/data-computer/v1/hdbscan.py
index 71c07b0..4553f43 100755
--- a/data-computer/v1/hdbscan.py
+++ b/data-computer/v1/hdbscan.py
@@ -3,11 +3,13 @@
 import json
 from sklearn.cluster import HDBSCAN
 from sklearn.feature_extraction.text import TfidfVectorizer
+from scipy.spatial import distance
 import sys
 import unicodedata
 import re
 import spacy
 
+import matplotlib.pyplot as plt
 
 
 #normalize text
@@ -57,22 +59,33 @@
         texts.append(lemmatize(uniformize(line["value"])))
     else:
         texts.append("n/a")
-vectorizer = TfidfVectorizer(stop_words=stopwords,analyzer="word",max_df=0.8,min_df=2) #delete terms with high/low frequences
+vectorizer = TfidfVectorizer(stop_words=stopwords,analyzer="word",max_df=0.8,min_df=3) #delete terms with high/low frequences
 X = vectorizer.fit_transform(texts)
 
 
 # HDBSCAN
-min_cluster_size = max(2,2*int(len(texts)/100))
-
+cosine_dist_X = distance.cdist(X.toarray(), X.toarray(), metric='cosine')
 clusterer = HDBSCAN(
     algorithm='auto',
-    metric='euclidean', #metric = cosine ?
-    min_cluster_size=min_cluster_size,
+    metric='precomputed', #metric = cosine ?
+    min_cluster_size=5,
+    cluster_selection_epsilon=0.5,
+    cluster_selection_method="eom",
     n_jobs=1) 
 
-clusterer.fit(X)
+clusterer.fit(cosine_dist_X)
 
+print(clusterer)
+exit()
+tests = []
+for i in range(len(all_data)):
+    tests.append({"cluster":int(clusterer.labels_[i]+1), "weight":str(clusterer.probabilities_[i])})
+sys.stdout.write(json.dumps(tests))
 
+plt.scatter(data[:, 0], data[:, 1], c=cluster_labels, cmap='viridis', s=50)
+plt.show()
+
+exit()
 # extract infos
 res = []
 for i in range(len(all_data)):