refactor(step6): 步骤6机器学习建模UI汉化 + 默认全不选 + 底层反向映射清洗

src/core/steps/modeling_step.py

@@ -14,6 +14,114 @@ import pandas as pd
 import numpy as np
 
 
+# ============================================================
+# 汉化 -> 英文 反向映射字典（UI 复选框显示文本 -> 底层算法键名）
+# ============================================================
+
+# 模型名称：中文 (缩写) -> 英文键名
+MODEL_NAME_MAP = {
+    "多元线性回归 (MLR)": "LinearRegression",
+    "岭回归 (Ridge)": "Ridge",
+    "套索回归 (Lasso)": "Lasso",
+    "弹性网络 (ElasticNet)": "ElasticNet",
+    "偏最小二乘 (PLSR)": "PLS",
+    "决策树 (CART)": "DecisionTree",
+    "随机森林 (RF)": "RF",
+    "极端随机树 (ET)": "ExtraTrees",
+    "极值梯度提升 (XGBoost)": "XGBoost",
+    "轻量梯度提升 (LightGBM)": "LightGBM",
+    "类别梯度提升 (CatBoost)": "CatBoost",
+    "梯度提升树 (GBDT)": "GradientBoosting",
+    "自适应提升 (AdaBoost)": "AdaBoost",
+    "支持向量回归 (SVR)": "SVR",
+    "K近邻回归 (KNN)": "KNN",
+    "多层感知机 (BP神经网络)": "MLP",
+}
+
+# 预处理方法：各种可能的中文变体 -> 标准键名
+PREPROC_NAME_MAP = {
+    # 无处理
+    "无 (None)": "None",
+    "None": "None",
+    # MMS
+    "最小-最大归一化 (MMS)": "MMS",
+    "MMS": "MMS",
+    # SS
+    "标度化 (SS)": "SS",
+    "SS": "SS",
+    # SNV
+    "标准正态变换 (SNV)": "SNV",
+    "SNV": "SNV",
+    # MA
+    "移动平均 (MA)": "MA",
+    "MA": "MA",
+    # SG
+    "Savitzky-Golay (SG)": "SG",
+    "SG": "SG",
+    # MSC
+    "多元散射校正 (MSC)": "MSC",
+    "MSC": "MSC",
+    # D1
+    "一阶导数 (D1)": "D1",
+    "D1": "D1",
+    # D2
+    "二阶导数 (D2)": "D2",
+    "D2": "D2",
+    # DT
+    "去趋势 (DT)": "DT",
+    "DT": "DT",
+    # CT
+    "中心化 (CT)": "CT",
+    "CT": "CT",
+}
+
+# 数据划分方法：各种可能的中文变体 -> 标准键名
+SPLIT_NAME_MAP = {
+    "SPXY 算法 (考量X-Y空间)": "spxy",
+    "spxy": "spxy",
+    "KS 算法 (考量X空间)": "ks",
+    "ks": "ks",
+    "随机划分 (Random)": "random",
+    "random": "random",
+}
+
+
+def _normalize_model_names(model_names: List[str]) -> List[str]:
+    """清洗模型名称列表：将汉化显示文本还原为英文键名"""
+    result = []
+    for name in model_names:
+        if name in MODEL_NAME_MAP:
+            result.append(MODEL_NAME_MAP[name])
+        else:
+            # 已经是英文键名，直接保留
+            result.append(name)
+    return result
+
+
+def _normalize_preprocessing_methods(methods: List[str]) -> List[str]:
+    """清洗预处理方法列表：将汉化显示文本还原为标准键名"""
+    result = []
+    for method in methods:
+        if method in PREPROC_NAME_MAP:
+            result.append(PREPROC_NAME_MAP[method])
+        else:
+            # 已经是标准键名，直接保留
+            result.append(method)
+    return result
+
+
+def _normalize_split_methods(methods: List[str]) -> List[str]:
+    """清洗数据划分方法列表：将汉化显示文本还原为标准键名"""
+    result = []
+    for method in methods:
+        if method in SPLIT_NAME_MAP:
+            result.append(SPLIT_NAME_MAP[method])
+        else:
+            # 已经是标准键名，直接保留
+            result.append(method)
+    return result
+
+
 class ModelingStep:
     """建模步骤"""
 
@@ -75,6 +183,15 @@ class ModelingStep:
         if split_methods is None:
             split_methods = ["spxy", "ks", "random"]
 
+        # ---- 汉化清洗：将 UI 传来的中文/混合名称转换为底层英文键名 ----
+        preprocessing_methods = _normalize_preprocessing_methods(preprocessing_methods)
+        model_names = _normalize_model_names(model_names)
+        split_methods = _normalize_split_methods(split_methods)
+
+        print(f"[参数清洗] 预处理方法: {preprocessing_methods}")
+        print(f"[参数清洗] 模型名称: {model_names}")
+        print(f"[参数清洗] 划分方法: {split_methods}")
+
         modeler = WaterQualityModelingBatch(str(output_dir))
         modeler.train_models_batch(
             csv_path=training_csv_path,