Update app.py

app.py

@@ -20,6 +20,7 @@ DATASET_MAP = {
 
 TARGET_COL = "ideal_expval_Z_global"
 
+# Колонки, которые никогда не должны быть признаками (фичами)
 EXCLUDE_COLS = {
     "sample_id", "sample_seed", "circuit_hash", "split", "circuit_qasm", 
     "qasm_raw", "qasm_transpiled", "circuit_type_resolved", "circuit_type_requested",
@@ -41,13 +42,15 @@ def get_df(dataset_key):
 
 def get_numeric_feature_cols(df: pd.DataFrame) -> list[str]:
     numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
-    # Убираем все таргеты и нерелевантные колонки
+    # Оставляем только структурные метрики, убираем таргеты и ошибки
     return [c for c in numeric_cols if c not in EXCLUDE_COLS and not c.startswith("error_") and "expval" not in c]
 
 # =========================================================
 # LOGIC
 # =========================================================
-def update_explorer(dataset_name, split_name):
+
+# Функция для обновления первой вкладки (Explorer)
+def update_explorer_tab(dataset_name, split_name):
     df = get_df(dataset_name)
     splits = df["split"].unique().tolist() if "split" in df.columns else ["train"]
     filtered = df[df["split"] == split_name].head(10) if "split" in df.columns else df.head(10)
@@ -55,29 +58,34 @@ def update_explorer(dataset_name, split_name):
     qasm_raw = filtered["qasm_raw"].iloc[0] if "qasm_raw" in filtered.columns else "// N/A"
     qasm_tr = filtered["qasm_transpiled"].iloc[0] if "qasm_transpiled" in filtered.columns else "// N/A"
     
+    return gr.update(choices=splits), filtered, qasm_raw, qasm_tr
+
+# Функция для обновления списка фичей во второй вкладке (ML Demo)
+def update_ml_features(dataset_name):
+    df = get_df(dataset_name)
     features = get_numeric_feature_cols(df)
-    # По умолчанию выбираем первые 8 признаков (обычно это n_qubits, depth и базовые гейты)
-    default_features = features[:8]
+    # По умолчанию выбираем первые несколько важных метрик
+    default_selection = [f for f in ["n_qubits", "depth", "total_gates", "gate_entropy", "meyer_wallach"] if f in features]
+    if not default_selection: default_selection = features[:5]
     
-    return gr.update(choices=splits), filtered, qasm_raw, qasm_tr, gr.update(choices=features, value=default_features)
+    return gr.update(choices=features, value=default_selection)
 
 def run_model_demo(dataset_name, selected_features):
     df = get_df(dataset_name)
     
-    # КРИТИЧЕСКОЕ ИСПРАВЛЕНИЕ: фильтруем признаки, которые реально есть в этом датасете
+    # Защита от несуществующих колонок (KeyError)
     valid_features = [f for f in selected_features if f in df.columns]
     
     if not valid_features:
-        return None, "### ⚠️ No valid features selected for this dataset."
+        return None, "### ⚠️ Ошибка: Выбранные признаки не найдены в этом датасете."
     
     target = TARGET_COL if TARGET_COL in df.columns else df.filter(like="expval").columns[0]
     
-    # Подготовка данных
     work_df = df.dropna(subset=valid_features + [target]).reset_index(drop=True)
     X, y = work_df[valid_features], work_df[target]
     
-    if len(work_df) < 50:
-        return None, "### ⚠️ Not enough data rows to train."
+    if len(work_df) < 20:
+        return None, "### ⚠️ Недостаточно данных для обучения."
 
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
@@ -88,35 +96,36 @@ def run_model_demo(dataset_name, selected_features):
     sns.set_theme(style="whitegrid")
     fig, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize=(18, 5))
 
-    # Parity
+    # График предсказаний
     ax1.scatter(y_test, preds, alpha=0.4, color='#636EFA')
     ax1.plot([y.min(), y.max()], [y.min(), y.max()], 'r--', lw=2)
-    ax1.set_title(f"R² = {r2_score(y_test, preds):.3f}")
+    ax1.set_title(f"R² Score: {r2_score(y_test, preds):.3f}")
     ax1.set_xlabel("Actual")
     ax1.set_ylabel("Predicted")
 
-    # Importance
+    # Важность признаков (топ-10)
     importances = model.feature_importances_
-    indices = np.argsort(importances)[-10:] # Только топ-10 для красоты
+    indices = np.argsort(importances)[-10:]
     ax2.barh(range(len(indices)), importances[indices], color='#EF553B')
     ax2.set_yticks(range(len(indices)))
     ax2.set_yticklabels([valid_features[i] for i in indices])
-    ax2.set_title("Top Feature Importance")
+    ax2.set_title("Feature Importance")
 
-    # Residuals
+    # Распределение ошибок
     sns.histplot(y_test - preds, kde=True, ax=ax3, color='#00CC96')
-    ax3.set_title("Error Distribution")
+    ax3.set_title("Residuals")
     
     plt.tight_layout()
-    return fig, f"### Train Stats: {dataset_name}\n**MAE:** {mean_absolute_error(y_test, preds):.4f}"
+    return fig, f"### Отчет по датасету: {dataset_name}\n**MAE:** {mean_absolute_error(y_test, preds):.4f}"
 
 # =========================================================
 # UI
 # =========================================================
-with gr.Blocks() as demo:
-    gr.Markdown("# 🌌 QSBench Unified Explorer")
+with gr.Blocks(title="QSBench Explorer") as demo:
+    gr.Markdown("# 🌌 QSBench: Quantum Synthetic Benchmark")
     
     with gr.Tabs():
+        # ВКЛАДКА 1: ПРОСМОТР ДАННЫХ
         with gr.TabItem("🔎 Explorer"):
             with gr.Row():
                 ds_selector = gr.Dropdown(choices=list(DATASET_MAP.keys()), value="Core (Clean)", label="Dataset")
@@ -128,21 +137,32 @@ with gr.Blocks() as demo:
                 qasm_raw_view = gr.Code(label="Raw QASM", language="python", lines=10)
                 qasm_tr_view = gr.Code(label="Transpiled QASM", language="python", lines=10)
 
+        # ВКЛАДКА 2: МАШИННОЕ ОБУЧЕНИЕ
         with gr.TabItem("🤖 ML Demo"):
             with gr.Row():
                 with gr.Column(scale=1):
-                    m_ds_selector = gr.Dropdown(choices=list(DATASET_MAP.keys()), value="Core (Clean)", label="Target Dataset")
-                    f_selector = gr.CheckboxGroup(label="Features", choices=[])
-                    train_btn = gr.Button("Train", variant="primary")
+                    gr.Markdown("### Настройка обучения")
+                    m_ds_selector = gr.Dropdown(choices=list(DATASET_MAP.keys()), value="Core (Clean)", label="Dataset for ML")
+                    f_selector = gr.CheckboxGroup(label="Признаки (Features)", choices=[])
+                    train_btn = gr.Button("Запустить обучение", variant="primary")
                 with gr.Column(scale=2):
                     plot_out = gr.Plot()
                     text_out = gr.Markdown()
 
-    # Ссылки
-    ds_selector.change(update_explorer, [ds_selector, split_selector], [split_selector, data_table, qasm_raw_view, qasm_tr_view, f_selector])
+    # --- ЛОГИКА СОБЫТИЙ ---
+
+    # При изменении датасета в Explorer — обновляем таблицу и QASM
+    ds_selector.change(update_explorer_tab, [ds_selector, split_selector], [split_selector, data_table, qasm_raw_view, qasm_tr_view])
+    
+    # ПРИНЦИПИАЛЬНО: При изменении датасета в ML Demo — обновляем список чекбоксов
+    m_ds_selector.change(update_ml_features, inputs=[m_ds_selector], outputs=[f_selector])
+    
+    # Кнопка обучения
     train_btn.click(run_model_demo, [m_ds_selector, f_selector], [plot_out, text_out])
     
-    demo.load(update_explorer, [ds_selector, split_selector], [split_selector, data_table, qasm_raw_view, qasm_tr_view, f_selector])
+    # Инициализация при старте
+    demo.load(update_explorer_tab, [ds_selector, split_selector], [split_selector, data_table, qasm_raw_view, qasm_tr_view])
+    demo.load(update_ml_features, [m_ds_selector], [f_selector])
 
 if __name__ == "__main__":
     demo.launch(theme=gr.themes.Soft())