feat: 添加GPU检测与自动回退逻辑并移除冗余文档

- 在notebook中引入GPU检测逻辑，根据CUDA可用性自动选择XGBoost计算后端
- 更新XGBoost配置，使用动态变量替代硬编码的GPU参数
- 删除过时的需求分析文档，保持项目结构整洁
- 确保代码在不同硬件环境下均可正常运行

强化学习个人课程作业报告/notebooks/insurance_premium_risk.ipynb

@@ -44,9 +44,7 @@
    "id": "a12f069a",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import warnings\nwarnings.filterwarnings('ignore')\nimport os\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.metrics import accuracy_score, f1_score, classification_report, confusion_matrix, ConfusionMatrixDisplay\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.preprocessing import StandardScaler, LabelEncoder\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.ensemble import RandomForestClassifier, VotingClassifier\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.preprocessing import OneHotEncoder\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.cluster import KMeans\nfrom sklearn.mixture import GaussianMixture\nfrom sklearn.metrics import silhouette_score\nfrom sklearn.decomposition import PCA\nimport xgboost as xgb\nimport optuna\noptuna.logging.set_verbosity(optuna.logging.WARNING)\n\nRANDOM_STATE = 42\nnp.random.seed(RANDOM_STATE)\nplt.rcParams['figure.figsize'] = (10, 6)\nplt.rcParams['font.size'] = 12\nsns.set_style('whitegrid')\nprint('All libraries imported successfully!')"
-   ]
+   "source": "import xgboost as xgb\nimport optuna\noptuna.logging.set_verbosity(optuna.logging.WARNING)\n\n# GPU Fallback: 自动检测CUDA可用性，无GPU时自动切换到CPU\ntry:\n    import subprocess\n    result = subprocess.run(['nvidia-smi'], capture_output=True, text=True)\n    USE_GPU = result.returncode == 0\nexcept:\n    USE_GPU = False\n\nXGB_TREE_METHOD = 'gpu_hist' if USE_GPU else 'hist'\nXGB_DEVICE = 'cuda' if USE_GPU else 'cpu'\nprint(f'XGBoost compute method: {\"GPU (CUDA)\" if USE_GPU else \"CPU\"}')\n\nRANDOM_STATE = 42\nnp.random.seed(RANDOM_STATE)\nplt.rcParams['figure.figsize'] = (10, 6)\nplt.rcParams['font.size'] = 12\nsns.set_style('whitegrid')\nprint('All libraries imported successfully!')"
   },
   {
    "cell_type": "code",
@@ -227,9 +225,7 @@
    "id": "30cd02ce",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "import time\n\nprint('Training Random Forest...')\nstart = time.time()\nrf_pipeline = Pipeline(steps=[\n    ('preprocessor', preprocessor),\n    ('classifier', RandomForestClassifier(n_estimators=200, class_weight='balanced', random_state=RANDOM_STATE, n_jobs=-1))\n])\nrf_pipeline.fit(X_train, y_train_enc)\nrf_time = time.time() - start\n\nrf_results = evaluate_model(rf_pipeline, X_train, y_train_enc, X_val, y_val_enc, le_target, 'RandomForest')\nrf_results['train_time'] = rf_time\n\nprint('Training XGBoost...')\nstart = time.time()\nxgb_pipeline = Pipeline(steps=[\n    ('preprocessor', preprocessor),\n    ('classifier', xgb.XGBClassifier(n_estimators=200, learning_rate=0.1, max_depth=6,\n                                    objective='multi:softmax', num_class=3,\n                                    tree_method='gpu_hist', device='cuda', random_state=RANDOM_STATE, verbosity=0))\n])\nxgb_pipeline.fit(X_train, y_train_enc)\nxgb_time = time.time() - start\n\nxgb_results = evaluate_model(xgb_pipeline, X_train, y_train_enc, X_val, y_val_enc, le_target, 'XGBoost')\nxgb_results['train_time'] = xgb_time\n\nprint(f'RF time: {rf_time:.2f}s | XGB time: {xgb_time:.2f}s')"
-   ]
+   "source": "print('Training Random Forest...')\nstart = time.time()\nrf_pipeline = Pipeline(steps=[\n    ('preprocessor', preprocessor),\n    ('classifier', RandomForestClassifier(n_estimators=200, class_weight='balanced', random_state=RANDOM_STATE, n_jobs=-1))\n])\nrf_pipeline.fit(X_train, y_train_enc)\nrf_time = time.time() - start\n\nrf_results = evaluate_model(rf_pipeline, X_train, y_train_enc, X_val, y_val_enc, le_target, 'RandomForest')\nrf_results['train_time'] = rf_time\n\nprint('Training XGBoost...')\nstart = time.time()\nxgb_pipeline = Pipeline(steps=[\n    ('preprocessor', preprocessor),\n    ('classifier', xgb.XGBClassifier(n_estimators=200, learning_rate=0.1, max_depth=6,\n                                    objective='multi:softmax', num_class=3,\n                                    tree_method=XGB_TREE_METHOD, device=XGB_DEVICE,\n                                    random_state=RANDOM_STATE, verbosity=0))\n])\nxgb_pipeline.fit(X_train, y_train_enc)\nxgb_time = time.time() - start\n\nxgb_results = evaluate_model(xgb_pipeline, X_train, y_train_enc, X_val, y_val_enc, le_target, 'XGBoost')\nxgb_results['train_time'] = xgb_time\n\nprint(f'RF time: {rf_time:.2f}s | XGB time: {xgb_time:.2f}s')"
   },
   {
    "cell_type": "code",
@@ -293,9 +289,7 @@
    "id": "e6361576",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "def objective(trial):\n    params = {\n        'n_estimators': trial.suggest_int('n_estimators', 100, 500),\n        'max_depth': trial.suggest_int('max_depth', 3, 10),\n        'learning_rate': trial.suggest_float('learning_rate', 0.01, 0.3, log=True),\n        'min_child_weight': trial.suggest_int('min_child_weight', 1, 10),\n        'subsample': trial.suggest_float('subsample', 0.5, 1.0),\n        'colsample_bytree': trial.suggest_float('colsample_bytree', 0.5, 1.0),\n        'gamma': trial.suggest_float('gamma', 0, 5),\n        'reg_alpha': trial.suggest_float('reg_alpha', 1e-4, 10.0, log=True),\n        'reg_lambda': trial.suggest_float('reg_lambda', 1e-4, 10.0, log=True),\n        'objective': 'multi:softmax',\n        'num_class': 3,\n        'random_state': RANDOM_STATE,\n        'tree_method': 'gpu_hist', 'device': 'cuda',\n        'verbosity': 0\n    }\n    pipeline = Pipeline(steps=[\n        ('preprocessor', preprocessor),\n        ('classifier', xgb.XGBClassifier(**params))\n    ])\n    pipeline.fit(X_train, y_train_enc)\n    y_pred = pipeline.predict(X_val)\n    score = f1_score(y_val_enc, y_pred, average='macro')\n    return score\n\nprint('Starting Optuna hyperparameter optimisation (30 trials)...')\nstudy = optuna.create_study(direction='maximize', sampler=optuna.samplers.TPESampler(seed=RANDOM_STATE))\nstudy.optimize(objective, n_trials=30, show_progress_bar=False)\n\nprint(f'Best trial: {study.best_trial.number} | Best macro-F1: {study.best_value:.4f}')"
-   ]
+   "source": "def objective(trial):\n    params = {\n        'n_estimators': trial.suggest_int('n_estimators', 100, 500),\n        'max_depth': trial.suggest_int('max_depth', 3, 10),\n        'learning_rate': trial.suggest_float('learning_rate', 0.01, 0.3, log=True),\n        'min_child_weight': trial.suggest_int('min_child_weight', 1, 10),\n        'subsample': trial.suggest_float('subsample', 0.5, 1.0),\n        'colsample_bytree': trial.suggest_float('colsample_bytree', 0.5, 1.0),\n        'gamma': trial.suggest_float('gamma', 0, 5),\n        'reg_alpha': trial.suggest_float('reg_alpha', 1e-4, 10.0, log=True),\n        'reg_lambda': trial.suggest_float('reg_lambda', 1e-4, 10.0, log=True),\n        'objective': 'multi:softmax',\n        'num_class': 3,\n        'random_state': RANDOM_STATE,\n        'tree_method': XGB_TREE_METHOD,\n        'device': XGB_DEVICE,\n        'verbosity': 0\n    }\n    pipeline = Pipeline(steps=[\n        ('preprocessor', preprocessor),\n        ('classifier', xgb.XGBClassifier(**params))\n    ])\n    pipeline.fit(X_train, y_train_enc)\n    y_pred = pipeline.predict(X_val)\n    score = f1_score(y_val_enc, y_pred, average='macro')\n    return score\n\nprint('Starting Optuna hyperparameter optimisation (30 trials)...')\nstudy = optuna.create_study(direction='maximize', sampler=optuna.samplers.TPESampler(seed=RANDOM_STATE))\nstudy.optimize(objective, n_trials=30, show_progress_bar=False)\n\nprint(f'Best trial: {study.best_trial.number} | Best macro-F1: {study.best_value:.4f}')"
   },
   {
    "cell_type": "code",
@@ -313,9 +307,7 @@
    "id": "640263ea",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "best_xgb_params = {\n    **study.best_params,\n    'objective': 'multi:softmax',\n    'num_class': 3,\n    'random_state': RANDOM_STATE,\n    'tree_method': 'gpu_hist', 'device': 'cuda',\n    'verbosity': 0\n}\n\nprint('Training tuned XGBoost...')\nimport time\nstart = time.time()\ntuned_xgb_pipeline = Pipeline(steps=[\n    ('preprocessor', preprocessor),\n    ('classifier', xgb.XGBClassifier(**best_xgb_params))\n])\ntuned_xgb_pipeline.fit(X_train, y_train_enc)\ntuned_time = time.time() - start\n\ntuned_results = evaluate_model(tuned_xgb_pipeline, X_train, y_train_enc, X_val, y_val_enc, le_target, 'XGBoost_Tuned')\ntuned_results['train_time'] = tuned_time\n\nprint('\\n=== TUNED XGBOOST RESULTS ===')\nfor k, v in tuned_results.items():\n    if k != 'model':\n        print(f'{k}: {v:.4f}')\n\nprint(f'\\nTuning improvement (macro-F1): +{tuned_results[\"val_f1_macro\"] - xgb_results[\"val_f1_macro\"]:.4f}')"
-   ]
+   "source": "best_xgb_params = {\n    **study.best_params,\n    'objective': 'multi:softmax',\n    'num_class': 3,\n    'random_state': RANDOM_STATE,\n    'tree_method': XGB_TREE_METHOD,\n    'device': XGB_DEVICE,\n    'verbosity': 0\n}\n\nprint('Training tuned XGBoost...')\nimport time\nstart = time.time()\ntuned_xgb_pipeline = Pipeline(steps=[\n    ('preprocessor', preprocessor),\n    ('classifier', xgb.XGBClassifier(**best_xgb_params))\n])\ntuned_xgb_pipeline.fit(X_train, y_train_enc)\ntuned_time = time.time() - start\n\ntuned_results = evaluate_model(tuned_xgb_pipeline, X_train, y_train_enc, X_val, y_val_enc, le_target, 'XGBoost_Tuned')\ntuned_results['train_time'] = tuned_time\n\nprint('\\n=== TUNED XGBOOST RESULTS ===')\nfor k, v in tuned_results.items():\n    if k != 'model':\n        print(f'{k}: {v:.4f}')\n\nprint(f'\\nTuning improvement (macro-F1): +{tuned_results[\"val_f1_macro\"] - xgb_results[\"val_f1_macro\"]:.4f}')"
   },
   {
    "cell_type": "code",