updating dropdown

app.py

@@ -16,7 +16,8 @@ T = {
         "all_scores": "Show All Score Types",
         "no_data": "No data matches the selected filters.",
         "avg_over_time": "Average {} Over Time",
-        "scores_over_time": "Sentiment Scores Over Time"
+        "scores_over_time": "Sentiment Scores Over Time",
+        "select_entities_prompt": "Please select at least one entity to view the graph."
     },
     "Български": {
         "title": "📊 Табло за анализ на настроенията",
@@ -27,7 +28,8 @@ T = {
         "all_scores": "Покажи всички типове оценки",
         "no_data": "Няма данни за избраните филтри.",
         "avg_over_time": "Средна стойност на {} във времето",
-        "scores_over_time": "Оценки на настроенията във времето"
+        "scores_over_time": "Оценки на настроенията във времето",
+        "select_entities_prompt": "Моля, изберете поне един обект, за да видите графиката."
     }
 }
 
@@ -55,22 +57,33 @@ def get_data():
 st.title(T[LANG]["title"])
 df = get_data()
 
+# --- Entity dropdown with counts ---
 entity_counts = df["entity"].value_counts()
-domain_counts = df["domain"].value_counts()
+entity_labels = [f"{ent} ({count})" for ent, count in entity_counts.items()]
+entity_lookup = {f"{ent} ({count})": ent for ent, count in entity_counts.items()}
+selected_labels = st.multiselect(T[LANG]["select_entities"], entity_labels)
+entities = [entity_lookup[label] for label in selected_labels]
 
-entities = st.multiselect(T[LANG]["select_entities"], entity_counts.index.tolist())
+# --- Domain dropdown ---
+domain_counts = df["domain"].value_counts()
 domains = st.multiselect(T[LANG]["select_domains"], domain_counts.index.tolist())
 score_type = st.selectbox(T[LANG]["score_type"], ["entity_score", "title_score", "overall_score"])
 group_by_domain = st.checkbox(T[LANG]["group_by_domain"])
 group_by_score_type = st.checkbox(T[LANG]["all_scores"])
 
-# Apply filters
+# --- Filters ---
 filtered_df = df.copy()
 if entities:
     filtered_df = filtered_df[filtered_df["entity"].isin(entities)]
 if domains:
     filtered_df = filtered_df[filtered_df["domain"].isin(domains)]
 
+# --- Stop early if no entity selected ---
+if not entities:
+    st.info(T[LANG]["select_entities_prompt"])
+    st.stop()
+
+# --- Continue only if data exists ---
 if not filtered_df.empty:
     filtered_df["date"] = filtered_df["created_at"].dt.floor("D")
 
@@ -120,8 +133,6 @@ if not filtered_df.empty:
             return label
 
         grouped["label"] = grouped.apply(build_label, axis=1)
-
-        # ✅ Sort by avg score then by date
         label_avg = grouped.groupby("label")["score"].mean().reset_index(name="avg_score")
         grouped = grouped.merge(label_avg, on="label")
         grouped = grouped.sort_values(by=["avg_score", "date"], ascending=[False, True])
@@ -170,8 +181,6 @@ if not filtered_df.empty:
             return label
 
         grouped["label"] = grouped.apply(build_label, axis=1)
-
-        # ✅ Sort by avg score then by date
         label_avg = grouped.groupby("label")[score_type].mean().reset_index(name="avg_score")
         grouped = grouped.merge(label_avg, on="label")
         grouped = grouped.sort_values(by=["avg_score", "date"], ascending=[False, True])