Include Paligemma Embeddings Visualization

app.py

@@ -124,6 +124,45 @@ def load_embeddings(model, version, embedding_prefix, weight_factor):
                 "synthetic": pd.concat([df_seq, df_line, df_par, df_rot, df_zoom, df_render], ignore_index=True),
                 "pretrained": df_pretratrained}
     
+    elif model == "Paligemma":
+        df_real = pd.read_csv(f"data/paligemma/{version}/{embedding_prefix}/de_Rodrigo_merit_secret_britanico_{weight_factor}embeddings.csv")
+        df_par = pd.read_csv(f"data/paligemma/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-paragraph-degradation-seq_{weight_factor}embeddings.csv")
+        df_line = pd.read_csv(f"data/paligemma/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-line-degradation-seq_{weight_factor}embeddings.csv")
+        df_seq  = pd.read_csv(f"data/paligemma/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-seq_{weight_factor}embeddings.csv")
+        df_rot  = pd.read_csv(f"data/paligemma/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-rotation-degradation-seq_{weight_factor}embeddings.csv")
+        df_zoom = pd.read_csv(f"data/paligemma/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-zoom-degradation-seq_{weight_factor}embeddings.csv")
+        df_render = pd.read_csv(f"data/paligemma/{version}/{embedding_prefix}/de_Rodrigo_merit_es-render-seq_{weight_factor}embeddings.csv")
+        
+        # Cargar ambos subconjuntos pretrained y combinarlos
+        # TODO Pretrained de idefics2, se mantienen para evitar error, pero se debe meter los de paligemma
+        df_pretratrained_PDFA = pd.read_csv(f"data/idefics2/{version}/{embedding_prefix}/de_Rodrigo_merit_aux_PDFA_{weight_factor}embeddings.csv")
+        df_pretratrained_IDL = pd.read_csv(f"data/idefics2/{version}/{embedding_prefix}/de_Rodrigo_merit_aux_IDL_{weight_factor}embeddings.csv")
+        df_pretratrained = pd.concat([df_pretratrained_PDFA, df_pretratrained_IDL], ignore_index=True)
+        
+        # Asignar etiquetas de versión
+        df_real["version"] = "real"
+        df_par["version"] = "synthetic"
+        df_line["version"] = "synthetic"
+        df_seq["version"] = "synthetic"
+        df_rot["version"] = "synthetic"
+        df_zoom["version"] = "synthetic"
+        df_render["version"] = "synthetic"
+        df_pretratrained["version"] = "pretrained"
+
+        # Asignar fuente (source)
+        df_par["source"] = "es-digital-paragraph-degradation-seq"
+        df_line["source"] = "es-digital-line-degradation-seq"
+        df_seq["source"] = "es-digital-seq"
+        df_rot["source"] = "es-digital-rotation-degradation-seq"
+        df_zoom["source"] = "es-digital-zoom-degradation-seq"
+        df_render["source"] = "es-render-seq"
+        df_pretratrained["source"] = "pretrained"
+
+        return {"real": df_real, 
+                "synthetic": pd.concat([df_seq, df_line, df_par, df_rot, df_zoom, df_render], ignore_index=True),
+                "pretrained": df_pretratrained}
+    
+    
     else:
         st.error("Modelo no reconocido")
         return None
@@ -1357,13 +1396,16 @@ def run_model(model_name):
 
 def main():
     config_style()
-    tabs = st.tabs(["Donut", "Idefics2"])
+    tabs = st.tabs(["Donut", "Idefics2" , "Paligemma"])
     with tabs[0]:
         st.markdown('<h2 class="sub-title">Donut 🤗</h2>', unsafe_allow_html=True)
         run_model("Donut")
     with tabs[1]:
         st.markdown('<h2 class="sub-title">Idefics2 🤗</h2>', unsafe_allow_html=True)
         run_model("Idefics2")
+    with tabs[2]:
+        st.markdown('<h2 class="sub-title">Paligemma 🤗</h2>', unsafe_allow_html=True)
+        run_model("Paligemma")
 
 if __name__ == "__main__":
     main()