Update app.py

app.py

@@ -38,7 +38,7 @@ REPO_CONFIG = {
     }
 }
 
-# Колонки, которые НЕ являются фичами (системные, категориальные или таргеты)
+# Columns that are NOT features (system, categorical, or targets)
 NON_FEATURE_COLS = {
     "sample_id", "sample_seed", "circuit_hash", "split", "circuit_qasm", 
     "qasm_raw", "qasm_transpiled", "circuit_type_resolved", "circuit_type_requested",
@@ -79,21 +79,21 @@ def get_methodology_content(ds_name: str):
     """
 
 def sync_ml_metrics(ds_name: str):
-    """Динамически находит все доступные числовые метрики (фичи) из CSV/Dataset"""
+    """Dynamically finds all available numerical metrics (features) from CSV/Dataset"""
     assets = load_all_assets(ds_name)
     df = assets["df"]
     
-    # Извлекаем все числовые колонки
+    # Extract all numeric columns
     numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
     
-    # Фильтруем: убираем системные ID и таргеты (всё, что начинается на ideal/noisy/error/sign)
+    # Filter: remove system IDs and targets (anything starting with ideal/noisy/error/sign)
     valid_features = [
         c for c in numeric_cols 
         if c not in NON_FEATURE_COLS 
         and not any(prefix in c for prefix in ["ideal_", "noisy_", "error_", "sign_"])
     ]
     
-    # Приоритетные метрики для выбора "по умолчанию"
+    # Priority metrics for "default" selection
     top_tier = ["gate_entropy", "meyer_wallach", "adjacency", "depth", "total_gates", "cx_count"]
     defaults = [f for f in top_tier if f in valid_features]
     
@@ -104,7 +104,7 @@ def train_model(ds_name: str, features: List[str]):
     assets = load_all_assets(ds_name)
     df = assets["df"]
     
-    # Используем глобальное значение Z как таргет
+    # Use global Z value as target
     target = "ideal_expval_Z_global"
     
     train_df = df.dropna(subset=features + [target])
@@ -125,7 +125,7 @@ def train_model(ds_name: str, features: List[str]):
 
     # 2. Feature Importance
     imp = model.feature_importances_
-    # Берем топ-10 если их много, или все если мало
+    # Take top 10 if there are many, or all if few
     top_n = min(len(features), 10)
     idx = np.argsort(imp)[-top_n:]
     axes[1].barh([features[i] for i in idx], imp[idx], color='#27ae60')
@@ -168,7 +168,7 @@ with gr.Blocks(theme=gr.themes.Soft(), title="QSBench Hub") as demo:
             with gr.Row():
                 with gr.Column(scale=1):
                     ml_ds_sel = gr.Dropdown(list(REPO_CONFIG.keys()), value="Core (Clean)", label="Select Dataset")
-                    # Динамический список метрик, извлекаемый из CSV
+                    # Dynamic metrics list extracted from CSV
                     ml_feat_sel = gr.CheckboxGroup(label="Available Metrics (extracted from CSV)", choices=[])
                     train_btn = gr.Button("Execute Baseline", variant="primary")
                 with gr.Column(scale=2):
@@ -189,7 +189,7 @@ with gr.Blocks(theme=gr.themes.Soft(), title="QSBench Hub") as demo:
     # Explorer
     ds_sel.change(update_explorer, [ds_sel, sp_sel], [sp_sel, data_view, c_raw, c_tr, meta_txt])
     
-    # ML Tab: Динамическое обновление метрик
+    # ML Tab: Dynamic metrics update
     ml_ds_sel.change(sync_ml_metrics, [ml_ds_sel], [ml_feat_sel])
     train_btn.click(train_model, [ml_ds_sel, ml_feat_sel], [p_out, t_out])