Update app.py

app.py

@@ -193,7 +193,7 @@ all_stars = sorted(list(star_popularity.keys()), key=lambda s: star_popularity[s
 # --- YENİ EKLENTİ SONU ---
 
 def get_movie_recommendations(selected_tags, selected_directors, selected_stars, min_imdb_rating_slider, num_recommendations_slider, search_text=""):
-
+    
     print(f"\n--- Öneri İsteği ---")
     print(f"Seçilen Türler: {selected_tags}")
     print(f"Seçilen Yönetmenler: {selected_directors}")
@@ -209,29 +209,29 @@ def get_movie_recommendations(selected_tags, selected_directors, selected_stars,
     recommendations_df = df_filtered.copy()
 
     recommendations_df = recommendations_df[recommendations_df['IMDb Rating'] >= min_imdb_rating_slider]
-
+    
     if selected_tags_list:
         recommendations_df = recommendations_df[
             recommendations_df['Tags_cleaned'].apply(lambda x: any(tag in x for tag in selected_tags_list))
         ]
-
+    
     if selected_directors_list:
         recommendations_df = recommendations_df[
             recommendations_df['Director_cleaned'].apply(lambda x: any(director in x for director in selected_directors_list))
         ]
-
+        
     if selected_stars_list:
         recommendations_df = recommendations_df[
             recommendations_df['Stars_cleaned'].apply(lambda x: any(star in x for star in selected_stars_list))
         ]
-
+            
     if search_text and len(recommendations_df) > 0 and sentence_model is not None:
         try:
             query_embedding = sentence_model.encode(search_text, convert_to_tensor=True)
         except Exception as e:
             print(f"HATA: Arama metni embedding'i oluşturulurken hata oluştu: {e}")
             return "Arama metni işlenirken bir hata oluştu. Lütfen tekrar deneyin."
-
+        
         filtered_indices = recommendations_df.index.tolist()
         if not filtered_indices or len(film_embeddings) == 0:
             return "Filtreleme sonrası film bulunamadı."
@@ -242,10 +242,10 @@ def get_movie_recommendations(selected_tags, selected_directors, selected_stars,
 
             current_film_embeddings = film_embeddings[filtered_indices]
             cosine_scores = util.cos_sim(query_embedding, current_film_embeddings)[0]
-            recommendations_df['Similarity_Score'] = cosine_scores.cpu().numpy()
+            recommendations_df['Similarity_Score'] = cosine_scores.cpu().numpy() 
             recommendations_df = recommendations_df.sort_values(
-                by=['Similarity_Score', 'IMDb Rating', 'Votes_numeric'],
-                ascending=[False, False, False]
+                by=['Similarity_Score', 'IMDb Rating', 'Votes_numeric'], 
+                ascending=[False, False, False] 
             ).reset_index(drop=True)
         except Exception as e:
             print(f"HATA: NLP benzerlik hesaplanırken hata oluştu: {e}")
@@ -255,12 +255,12 @@ def get_movie_recommendations(selected_tags, selected_directors, selected_stars,
 
     if not search_text or sentence_model is None:
         recommendations_df = recommendations_df.sort_values(
-            by=['IMDb Rating', 'Votes_numeric'],
+            by=['IMDb Rating', 'Votes_numeric'], 
             ascending=[False, False]
         ).reset_index(drop=True)
-
+    
     top_recommendations = recommendations_df.head(num_recommendations_slider)
-
+    
     if top_recommendations.empty:
         return """
         <div class="no-results-card">
@@ -369,7 +369,7 @@ custom_theme = gr.themes.Base(
     # Dropdown, Slider, Textbox
     input_background_fill="hsl(220, 10%, 20%)", # Koyu gri
     input_border_color="hsl(220, 10%, 30%)",
-    input_text_color="white",
+    # input_text_color="white", # BU SATIR KALDIRILDI!
     slider_color="hsl(24, 88%, 50%)", # Slider dolgu rengi
     # Genel Gradio panelleri
     block_background_fill="hsl(220, 10%, 15%)", # Daha koyu panel arka planı