Proper File Selection

app.py

@@ -14,6 +14,7 @@ from sklearn.linear_model import LinearRegression
 
 N_COMPONENTS = 2
 TSNE_NEIGHBOURS = 150
+WEIGHT_FACTOR = 0.25
 
 TOOLTIPS = """
 <div>
@@ -40,16 +41,16 @@ def config_style():
     """, unsafe_allow_html=True)
     st.markdown('<h1 class="main-title">Merit Embeddings 🎒📃🏆</h1>', unsafe_allow_html=True)
 
-def load_embeddings(model, version, embedding_prefix):
+def load_embeddings(model, version, embedding_prefix, weight_factor):
     if model == "Donut":
-        df_real = pd.read_csv(f"data/donut_{version}_de_Rodrigo_merit_secret_all_{embedding_prefix}embeddings.csv")
-        df_par = pd.read_csv(f"data/donut_{version}_de_Rodrigo_merit_es-digital-paragraph-degradation-seq_{embedding_prefix}embeddings.csv")
-        df_line = pd.read_csv(f"data/donut_{version}_de_Rodrigo_merit_es-digital-line-degradation-seq_{embedding_prefix}embeddings.csv")
-        df_seq  = pd.read_csv(f"data/donut_{version}_de_Rodrigo_merit_es-digital-seq_{embedding_prefix}embeddings.csv")
-        df_rot  = pd.read_csv(f"data/donut_{version}_de_Rodrigo_merit_es-digital-rotation-degradation-seq_{embedding_prefix}embeddings.csv")
-        df_zoom = pd.read_csv(f"data/donut_{version}_de_Rodrigo_merit_es-digital-zoom-degradation-seq_{embedding_prefix}embeddings.csv")
-        df_render = pd.read_csv(f"data/donut_{version}_de_Rodrigo_merit_es-render-seq_{embedding_prefix}embeddings.csv")
-        df_pretratrained = pd.read_csv(f"data/donut_{version}_de_Rodrigo_merit_aux_IIT-CDIP_{embedding_prefix}embeddings.csv")
+        df_real = pd.read_csv(f"data/donut/{version}/{embedding_prefix}/de_Rodrigo_merit_secret_all_{weight_factor}embeddings.csv")
+        df_par = pd.read_csv(f"data/donut/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-paragraph-degradation-seq_{weight_factor}embeddings.csv")
+        df_line = pd.read_csv(f"data/donut/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-line-degradation-seq_{weight_factor}embeddings.csv")
+        df_seq  = pd.read_csv(f"data/donut/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-seq_{weight_factor}embeddings.csv")
+        df_rot  = pd.read_csv(f"data/donut/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-rotation-degradation-seq_{weight_factor}embeddings.csv")
+        df_zoom = pd.read_csv(f"data/donut/{version}/{embedding_prefix}/de_Rodrigo_merit_es-digital-zoom-degradation-seq_{weight_factor}embeddings.csv")
+        df_render = pd.read_csv(f"data/donut/{version}/{embedding_prefix}/de_Rodrigo_merit_es-render-seq_{weight_factor}embeddings.csv")
+        df_pretratrained = pd.read_csv(f"data/donut/{version}/{embedding_prefix}/de_Rodrigo_merit_aux_IIT-CDIP_{weight_factor}embeddings.csv")
         
         # Asignar etiquetas de versión
         df_real["version"] = "real"
@@ -540,9 +541,16 @@ def run_model(model_name):
     # Selector para el método de cómputo del embedding
     embedding_computation = st.selectbox("¿Cómo se computa el embedding?", options=["weighted", "averaged"], key=f"embedding_method_{model_name}")
     # Se asigna el prefijo correspondiente
-    prefijo_embedding = "weighted_" if embedding_computation == "weighted" else "averaged_"
+    # prefijo_embedding = "weighted_" if embedding_computation == "weighted" else "averaged_"
+
+    if embedding_computation == "weighted":
+        # prefijo_embedding = "weighted_"
+        weight_factor = f"{WEIGHT_FACTOR}_"
+    else:
+        # prefijo_embedding = "averaged_"
+        weight_factor = ""
     
-    embeddings = load_embeddings(model_name, version, prefijo_embedding)
+    embeddings = load_embeddings(model_name, version, embedding_computation, weight_factor)
     if embeddings is None:
         return