nicer plot test

app.py

@@ -24,13 +24,11 @@ default_texts = [
 model = SentenceTransformer('paraphrase-multilingual-MiniLM-L12-v2')
 
 # Function to compute document embeddings and apply PCA
-# Modify the Gradio interface to accept a list of identifiers and texts
 def compute_pca(data):
-    # data is expected to be a list of dictionaries with 'Identifier' and 'Text' keys
+    # data is expected to be a list of dictionaries with 'Identifiant' and 'Texte' keys
     df = pd.DataFrame(data, columns=["Identifiant", "Texte"])
 
-
-    # Remove rows where 'Identifier' or 'Text' is empty or contains only whitespace
+    # Remove rows where 'Identifiant' or 'Texte' is empty or contains only whitespace
     valid_entries = df[
         (df['Identifiant'].str.strip() != '') & 
         (df['Texte'].str.strip() != '')
@@ -51,8 +49,18 @@ def compute_pca(data):
     valid_entries['PC1'] = pca_result[:, 0]
     valid_entries['PC2'] = pca_result[:, 1]
     
-    # Plot the PCA result with identifiers as labels
-    fig = px.scatter(valid_entries, x='PC1', y='PC2', text='Identifiant', title='PCA des plongements sémantiques')
+    # Plot the PCA result with identifiers as labels, with text positioned above the points
+    fig = px.scatter(
+        valid_entries, 
+        x='PC1', 
+        y='PC2', 
+        text='Identifiant', 
+        title='PCA des plongements sémantiques'
+    )
+
+    # Update the text position to be above the points
+    fig.update_traces(textposition='top center')
+
     return fig
 
 def text_editor_app():