Update app.py

app.py

@@ -11,7 +11,7 @@ from sklearn.ensemble import RandomForestRegressor
 from sklearn.metrics import mean_absolute_error, r2_score
 from sklearn.model_selection import train_test_split
 
-# Setup logging
+# --- CONFIG & LOGGING ---
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
@@ -47,12 +47,13 @@ NON_FEATURE_COLS = {
 
 _ASSET_CACHE = {}
 
+# --- CORE LOGIC ---
 def fetch_remote_json(url: str) -> Optional[dict]:
     try:
         response = requests.get(url, timeout=5)
         return response.json() if response.status_code == 200 else None
     except Exception as e:
-        logger.error(f"Error fetching metadata: {e}")
+        logger.error(f"Error: {e}")
         return None
 
 def load_all_assets(key: str) -> Dict:
@@ -69,7 +70,7 @@ def generate_guide_markdown(assets: Dict) -> str:
     meta = assets.get("meta", {})
     params = meta.get("parameters", {})
     report = assets.get("report", {})
-    if not meta: return "⚠️ *Metadata unavailable.*"
+    if not meta: return "### ⚠️ Metadata Unreachable"
 
     families = report.get("families", {})
     fam_table = "| Family | Samples | Description |\n| :--- | :--- | :--- |\n"
@@ -80,14 +81,14 @@ def generate_guide_markdown(assets: Dict) -> str:
     ## 📖 Methodology & Release Notes: {meta.get('dataset_version', '1.0.0-demo')}
     
     ### 1. Generation Engine
-    Generated using **QSBench v{meta.get('generator_version', '5.0')}**.
-    - **Qubits:** {params.get('n_qubits')} | **Depth:** {params.get('depth')}
+    - **Generator:** QSBench v{meta.get('generator_version', '5.x')}
     - **Noise:** `{params.get('noise', 'None')}` (p={params.get('noise_prob', 0)})
-    - **Backend:** {meta.get('backend_device', 'GPU')}
+    - **Backend:** {meta.get('backend_device', 'GPU')} | {meta.get('precision_mode', 'double')}
 
     ### 2. Structural Metrics
-    * **Gate Entropy:** Distribution of gates.
-    * **Meyer-Wallach:** Global entanglement.
+    * **Gate Entropy:** Measures circuit "chaos" and gate distribution complexity.
+    * **Meyer-Wallach:** Quantifies global entanglement levels.
+    * **Adjacency:** Graph density of the qubit interaction map.
 
     ### 3. Circuit Family Coverage
     {fam_table}
@@ -98,10 +99,11 @@ def update_explorer_view(ds_name: str, split_name: str):
     df = assets["df"]
     splits = df["split"].unique().tolist() if "split" in df.columns else ["train"]
     display_df = df[df["split"] == split_name].head(10) if "split" in df.columns else df.head(10)
-    raw_qasm = display_df["qasm_raw"].iloc[0] if "qasm_raw" in display_df.columns else "// No data"
-    tr_qasm = display_df["qasm_transpiled"].iloc[0] if "qasm_transpiled" in display_df.columns else "// No data"
     
-    meta_summary = f"### 📋 Pack: {ds_name} | Release: {assets.get('meta', {}).get('dataset_version', 'N/A')}"
+    raw_qasm = display_df["qasm_raw"].iloc[0] if "qasm_raw" in display_df.columns else "// N/A"
+    tr_qasm = display_df["qasm_transpiled"].iloc[0] if "qasm_transpiled" in display_df.columns else "// N/A"
+    
+    meta_summary = f"### 📋 Pack: {ds_name} | Version: {assets.get('meta', {}).get('dataset_version', 'N/A')}"
     return gr.update(choices=splits), display_df, raw_qasm, tr_qasm, meta_summary, generate_guide_markdown(assets)
 
 def sync_ml_inputs(ds_name: str):
@@ -109,30 +111,49 @@ def sync_ml_inputs(ds_name: str):
     df = assets["df"]
     numeric = df.select_dtypes(include=[np.number]).columns.tolist()
     valid = [c for c in numeric if c not in NON_FEATURE_COLS and not c.startswith(("error_", "sign_", "ideal_", "noisy_"))]
-    top_picks = [f for f in ["gate_entropy", "meyer_wallach", "n_qubits", "depth"] if f in valid]
+    top_picks = [f for f in ["gate_entropy", "meyer_wallach", "n_qubits", "depth", "total_gates"] if f in valid]
     return gr.update(choices=valid, value=top_picks)
 
 def train_baseline_model(ds_name: str, selected_features: List[str]):
     if not selected_features: return None, "### ❌ Error: Select features."
+    
     assets = load_all_assets(ds_name)
     df = assets["df"]
     target = "ideal_expval_Z_global" if "ideal_expval_Z_global" in df.columns else df.filter(like="expval").columns[0]
+    
     train_df = df.dropna(subset=selected_features + [target])
     X, y = train_df[selected_features], train_df[target]
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
     model = RandomForestRegressor(n_estimators=100, max_depth=12, n_jobs=-1, random_state=42)
     model.fit(X_train, y_train)
     preds = model.predict(X_test)
-    fig, axes = plt.subplots(1, 3, figsize=(20, 6))
-    axes[0].scatter(y_test, preds, alpha=0.4); axes[0].plot([y.min(), y.max()], [y.min(), y.max()], 'r--')
-    axes[1].barh(selected_features[:10], model.feature_importances_[:10])
-    sns.histplot(y_test - preds, kde=True, ax=axes[2])
-    plt.tight_layout()
+
+    # Улучшенная визуализация (исправляет обрезку)
+    sns.set_theme(style="whitegrid", context="talk")
+    fig, axes = plt.subplots(1, 3, figsize=(22, 7))
+    
+    # 1. Parity
+    axes[0].scatter(y_test, preds, alpha=0.4, color='#34495e')
+    axes[0].plot([y.min(), y.max()], [y.min(), y.max()], 'r--', lw=2)
+    axes[0].set_title(f"Accuracy (R²: {r2_score(y_test, preds):.3f})")
+
+    # 2. Importance (с поправкой на длинные названия)
+    imp = model.feature_importances_
+    idx = np.argsort(imp)[-10:]
+    axes[1].barh([selected_features[i] for i in idx], imp[idx], color='#1abc9c')
+    axes[1].set_title("Top Metrics Importance")
+
+    # 3. Residuals
+    sns.histplot(y_test - preds, kde=True, ax=axes[2], color='#e67e22')
+    axes[2].set_title("Prediction Error")
+
+    plt.tight_layout() # Автоматически подгоняет отступы
     return fig, f"**MAE:** {mean_absolute_error(y_test, preds):.4f}"
 
 # --- UI ---
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🌌 QSBench: Quantum Synthetic Benchmark Suite")
+with gr.Blocks(theme=gr.themes.Soft(), title="QSBench Hub") as demo:
+    gr.Markdown("# 🌌 QSBench: Quantum Analytics Hub")
     
     with gr.Tabs():
         with gr.TabItem("🔎 Explorer"):
@@ -149,7 +170,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
             with gr.Row():
                 with gr.Column(scale=1):
                     ml_ds = gr.Dropdown(choices=list(REPO_CONFIG.keys()), value="Core (Clean)", label="Dataset")
-                    ml_feat = gr.CheckboxGroup(label="Features", choices=[])
+                    ml_feat = gr.CheckboxGroup(label="Structural Metrics", choices=[])
                     btn = gr.Button("Train Baseline", variant="primary")
                 with gr.Column(scale=2):
                     plot_out = gr.Plot(); txt_out = gr.Markdown()
@@ -157,17 +178,16 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
         with gr.TabItem("📖 Methodology & Guide"):
             guide_md = gr.Markdown("Loading guide...")
 
-    # FOOTER WITH YOUR LINKS
+    # FOOTER
     gr.Markdown(f"""
     ---
-    ### 🔗 Project Resources & Store
-    * **🤗 Hugging Face:** [QSBench Organization](https://huggingface.co/QSBench)
-    * **💻 GitHub:** [QSBench Source Code](https://github.com/QSBench)
-    * **🌐 Official Site:** [qsbench.github.io](https://qsbench.github.io)
-    
-    *QSBench is an open-source framework for noise-aware Quantum Machine Learning benchmarking.*
+    ### 🔗 Project Resources & Links
+    * **🤗 Hugging Face:** [QSBench Org](https://huggingface.co/QSBench) — Dataset shards and demos.
+    * **💻 GitHub:** [QSBench Repository](https://github.com/QSBench) — Generator source code.
+    * **🌐 Project Site:** [qsbench.github.io](https://qsbench.github.io) — Documentation & Papers.
     """)
 
+    # Handlers
     ds_select.change(update_explorer_view, [ds_select, split_select], [split_select, data_table, code_raw, code_tr, metadata_box, guide_md])
     ml_ds.change(sync_ml_inputs, [ml_ds], [ml_feat])
     btn.click(train_baseline_model, [ml_ds, ml_feat], [plot_out, txt_out])