From d2a918bc5bb3b6e3b2a625df4478f8aba9ee8046 Mon Sep 17 00:00:00 2001
From: MAFTOUH Mohammed Amine <mohammed-amine.maftouh@imt-atlantique.net>
Date: Wed, 5 Mar 2025 12:16:39 +0000
Subject: [PATCH] Update 3 files

- /projet_imt.py
- /clustering/mesures_clustering.py
- /clustering/agg_clustering.py
---
 clustering/agg_clustering.py     |  1 +
 clustering/mesures_clustering.py |  1 +
 projet_imt.py                    | 11 +++++------
 3 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/clustering/agg_clustering.py b/clustering/agg_clustering.py
index b8a25e2..6bda725 100644
--- a/clustering/agg_clustering.py
+++ b/clustering/agg_clustering.py
@@ -1,3 +1,4 @@
+from sklearn.cluster import AgglomerativeClustering
 def agglomerative_clustering(reduced_embeddings, n_clusters):
     """
     Applique l'Agglomerative Clustering avec un nombre fixe de clusters.
diff --git a/clustering/mesures_clustering.py b/clustering/mesures_clustering.py
index af1ffdf..9c6c2e7 100644
--- a/clustering/mesures_clustering.py
+++ b/clustering/mesures_clustering.py
@@ -1,3 +1,4 @@
+from sklearn.metrics import silhouette_score
 def compute_silhouette_scores(reduced_embeddings, labels):
     """
     Calcule les scores de silhouette pour différents nombres de clusters.
diff --git a/projet_imt.py b/projet_imt.py
index 2b34264..b31b5d8 100644
--- a/projet_imt.py
+++ b/projet_imt.py
@@ -8,18 +8,14 @@ from utils.reduction_dimesion import *
 
 import pandas as pd
 import numpy as np
-import matplotlib.pyplot as plt
-import ast
 import umap
-from sklearn.cluster import KMeans
 from sklearn.metrics import silhouette_score
 from sklearn.cluster import AgglomerativeClustering
-from sklearn.metrics import silhouette_score
 
 
 def main():
     # lecture du fichier csv
-    df = load .....
+    df = pd.read_csv("/Users/mac/Desktop/topic_modeling/df_user_messages_new.csv")
     # reduction des dimensions
     reduced_embeddings = reduce_embeddings(df, n_components=50, random_state=42)
     # clustering
@@ -29,6 +25,9 @@ def main():
     # afficher les resultats
     messages_par_cluster= afficher_messages_par_cluster(df,labels)
 
+    return messages_par_cluster
+
 
 if __name__ == "__main__":
-    main()
+    messages_par_cluster = main()
+    print(messages_par_cluster)
\ No newline at end of file
-- 
GitLab