添加公式方法

src/core/algorithms/waterindex_inversion/__init__.py

@@ -348,7 +348,7 @@ class WaterIndexProcessor:
         hdr_path : str, optional
             ENVI HDR 文件路径（None → 自动构造）
         output_dir : str, optional
-            输出目录（None → 与 bsq_path 同目录下的 8_WaterIndex_Images/）
+            输出目录（None → 与 bsq_path 同目录下的 10_WaterIndex_Images/）
         formula_names : list, optional
             要处理的公式名列表（None → 处理全部）
         water_mask : np.ndarray, optional
@@ -374,7 +374,7 @@ class WaterIndexProcessor:
 
         # ── 自动构造输出目录 ────────────────────────────────────────────
         if output_dir is None:
-            output_dir = os.path.join(os.path.dirname(bsq_path), '8_WaterIndex_Images')
+            output_dir = os.path.join(os.path.dirname(bsq_path), '10_WaterIndex_Images')
         os.makedirs(output_dir, exist_ok=True)
 
         def progress(msg: str, pct: float):
@@ -610,7 +610,7 @@ class WaterIndexProcessor:
             if os.path.isfile(hdr_path_alt):
                 hdr_path = hdr_path_alt
 
-        output_dir = os.path.join(work_dir, "8_WaterIndex_Images")
+        output_dir = os.path.join(work_dir, "10_WaterIndex_Images")
 
         # ── 加载水域掩膜（可选）───────────────────────────────────────
         water_mask: Optional[np.ndarray] = None

src/core/glint_removal/get_spectral.py

@@ -2,6 +2,7 @@ from osgeo import gdal, osr
 import numpy as np
 import pandas as pd
 import os
+import re
 import spectral
 from math import sin, cos, tan, sqrt, radians
 
@@ -473,9 +474,56 @@ def get_spectral_in_coor(imgpath, coorpath, outpath, radius=0, flare_path=None,
     for i in range(min(3, coor_data.shape[0])):
         print(f"  行{i + 1}: {coor_data[i, :min(5, coor_data.shape[1])]}")  # 只显示前5列
     
-    # 提取原始坐标
-    lat_array = coor_data[:, 1]  # 第2列是纬度（跳过测量点ID列）
-    lon_array = coor_data[:, 2]  # 第3列是经度
+    # 提取原始坐标（使用智能坐标列检测）
+    lon_patterns = [
+        r'^lon', r'^lng', r'^longitude', r'经度', r'^x$', r'^utm_x$', r'^pixel_x$'
+    ]
+    lat_patterns = [
+        r'^lat', r'^latitude', r'纬度', r'^y$', r'^utm_y$', r'^pixel_y$'
+    ]
+
+    x_col_name, y_col_name = None, None
+
+    if coor_df is not None and hasattr(coor_df, 'columns'):
+        for col in coor_df.columns:
+            col_str = str(col).lower().strip()
+            if x_col_name is None and any(re.search(p, col_str) for p in lon_patterns):
+                x_col_name = col
+            if y_col_name is None and any(re.search(p, col_str) for p in lat_patterns):
+                y_col_name = col
+
+    if x_col_name and y_col_name and x_col_name in coor_df.columns and y_col_name in coor_df.columns:
+        lon_array = coor_df[x_col_name].values
+        lat_array = coor_df[y_col_name].values
+        print(f"💡 坐标列名检测: X/经度=[{x_col_name}], Y/纬度=[{y_col_name}]")
+    else:
+        numeric_cols = coor_df.select_dtypes(include=[np.number]).columns.tolist() if coor_df is not None else []
+        if len(numeric_cols) >= 2:
+            col1, col2 = numeric_cols[0], numeric_cols[1]
+            mean1 = coor_df[col1].head(10).mean()
+            mean2 = coor_df[col2].head(10).mean()
+            if abs(mean1) <= 90 and abs(mean2) > 90:
+                y_col_name, x_col_name = col1, col2
+                lon_array = coor_df[x_col_name].values
+                lat_array = coor_df[y_col_name].values
+            elif abs(mean2) <= 90 and abs(mean1) > 90:
+                x_col_name, y_col_name = col1, col2
+                lon_array = coor_df[x_col_name].values
+                lat_array = coor_df[y_col_name].values
+            else:
+                if mean1 > mean2:
+                    x_col_name, y_col_name = col1, col2
+                else:
+                    x_col_name, y_col_name = col2, col1
+                lon_array = coor_df[x_col_name].values
+                lat_array = coor_df[y_col_name].values
+            print(f"💡 触发智能数值推断坐标列: X/经度=[{x_col_name}], Y/纬度=[{y_col_name}]")
+        else:
+            if coor_data is not None and coor_data.shape[1] >= 3:
+                lat_array = coor_data[:, 1]
+                lon_array = coor_data[:, 2]
+            else:
+                raise Exception("坐标文件格式错误：需要至少2列数据，且最好包含坐标列名（如lon/lat/经度/纬度）")
     
     print(f"\n=== 原始坐标信息 ===")
     print(f"原始坐标范围: 经度 {np.min(lon_array):.6f} ~ {np.max(lon_array):.6f}, 纬度 {np.min(lat_array):.6f} ~ {np.max(lat_array):.6f}")

src/core/non_empirical_retrieval.py

@@ -247,7 +247,7 @@ def non_empirical_retrieval(algorithm, model_info_path, coor_spectral_path, outp
 if __name__ == "__main__":
     algorithm= "chl_a"
     model_info_path= r"E:\code\WQ\pipeline_result\work_dir\5_training_spectra\8_non_empirical_models\SS\SS_chl_a.json"
-    coor_spectral_path= r"E:\code\WQ\pipeline_result\work_dir\10_sampling\sampling_spectra.csv"
+    coor_spectral_path= r"E:\code\WQ\pipeline_result\work_dir\4_sampling\sampling_spectra.csv"
     output_path= r"E:\code\WQ\pipeline_result\work_dir\11_12_13_predictions\SS_chl_a.csv"
     wave_radius=5.0
     non_empirical_retrieval(algorithm, model_info_path, coor_spectral_path, output_path, wave_radius)

src/core/steps/prediction_step.py

@@ -24,7 +24,7 @@ class PredictionStep:
         chunk_size: int = 1000,
         water_mask_path: Optional[str] = None,
         glint_mask_path: Optional[str] = None,
-        output_dir: Union[str, Path] = "./10_sampling",
+        output_dir: Union[str, Path] = "./4_sampling",
         callback: Optional[Callable] = None,
         use_adaptive_sampling: bool = True,
     ) -> str:

src/core/water_quality_inversion_pipeline_GUI.py

@@ -144,7 +144,7 @@ class WaterQualityInversionPipeline:
         self.models_dir = self.work_dir / "7_Supervised_Model_Training"
         self.non_empirical_models_dir = self.work_dir / "8_Regression_Modeling"
         self.custom_regression_dir = self.work_dir / "9_Custom_Regression_Modeling"
-        self.sampling_dir = self.work_dir / "10_sampling"
+        self.sampling_dir = self.work_dir / "4_sampling"
         self.prediction_dir = self.work_dir / "11_12_13_predictions"
         self.visualization_dir = self.work_dir / "14_visualization"
         self.reports_dir = self.work_dir / "reports"
@@ -2276,7 +2276,7 @@ def main():
         'step6': {
             'formula_csv_file': 'path/to/water_quality_formulas.csv',  # 公式CSV文件路径
             'formula_names': ['Al10SABI', 'TurbBe16RedOverViolet'],  # 要计算的公式名称列表
-            'output_filename': 'water_quality_indices.csv',
+            'output_filename': 'training_spectra_indices.csv',
             'enabled': True  # 是否启用水质指数计算
         },
         'step7': {

src/gui/panels/step10_watercolor_panel.py

@@ -204,7 +204,7 @@ class Step10WatercolorPanel(QWidget):
             "输出目录:",
             "Directories"
         )
-        self.output_dir.line_edit.setPlaceholderText("留空 → 工作目录/8_WaterIndex_Images")
+        self.output_dir.line_edit.setPlaceholderText("留空 → 工作目录/10_WaterIndex_Images")
         self.output_dir.browse_btn.clicked.disconnect()
         self.output_dir.browse_btn.clicked.connect(self._browse_output_dir)
         output_layout.addRow("输出目录:", self.output_dir)
@@ -437,22 +437,42 @@ class Step10WatercolorPanel(QWidget):
             self.work_dir = None
 
         main_window = self.window()
+        deglint_path = None
 
-        # 自动填入去耀斑影像
-        if main_window and hasattr(main_window, 'step3_panel'):
-            deglint_path = main_window.step3_panel.output_file.get_path()
-            if deglint_path and not self.bsq_file.get_path():
-                if not os.path.isabs(deglint_path):
-                    deglint_path = os.path.join(self.work_dir or '', deglint_path).replace('\\', '/')
-                self.bsq_file.set_path(deglint_path)
-                hdr = Path(deglint_path).with_suffix('.hdr')
-                if hdr.exists():
-                    self.hdr_file.set_path(str(hdr))
-                    self._load_metadata(deglint_path, str(hdr))
+        # 1. 优先从 pipeline 的真实输出中获取
+        if pipeline and hasattr(pipeline, 'step_outputs'):
+            step3_out = pipeline.step_outputs.get('step3', {})
+            deglint_path = step3_out.get('deglint_image') or step3_out.get('output_path')
+
+        # 2. 回退：从 step3 面板实例获取
+        if not deglint_path and main_window and hasattr(main_window, 'step3_panel'):
+            if hasattr(main_window.step3_panel, 'output_file'):
+                deglint_path = main_window.step3_panel.output_file.get_path()
+
+        # 3. 终极回退：智能扫描 3_deglint 目录，取最新的 .bsq 或 .dat 文件
+        if not deglint_path and self.work_dir:
+            deglint_dir = os.path.join(self.work_dir, "3_deglint")
+            if os.path.isdir(deglint_dir):
+                import glob
+                candidates = glob.glob(os.path.join(deglint_dir, "*.bsq")) + glob.glob(os.path.join(deglint_dir, "*.dat"))
+                if candidates:
+                    candidates.sort(key=os.path.getmtime, reverse=True)
+                    deglint_path = candidates[0]
+
+        # 填入 UI 并自动寻找对应的 hdr 文件
+        if deglint_path:
+            if not os.path.isabs(deglint_path):
+                deglint_path = os.path.join(self.work_dir or '', deglint_path).replace('\\', '/')
+            self.bsq_file.set_path(deglint_path)
+
+            hdr_path = os.path.splitext(deglint_path)[0] + '.hdr'
+            if os.path.exists(hdr_path):
+                self.hdr_file.set_path(hdr_path)
+                self._load_metadata(deglint_path, hdr_path)
 
         # 自动填入输出目录
         if self.work_dir:
-            out_dir = os.path.join(self.work_dir, "8_WaterIndex_Images").replace('\\', '/')
+            out_dir = os.path.join(self.work_dir, "10_WaterIndex_Images").replace('\\', '/')
             os.makedirs(out_dir, exist_ok=True)
             if not self.output_dir.get_path():
                 self.output_dir.set_path(out_dir)
@@ -483,7 +503,7 @@ class Step10WatercolorPanel(QWidget):
             return
         if not output_dir:
             work_dir = self._get_default_work_dir()
-            output_dir = os.path.join(work_dir, "8_WaterIndex_Images").replace('\\', '/')
+            output_dir = os.path.join(work_dir, "10_WaterIndex_Images").replace('\\', '/')
             os.makedirs(output_dir, exist_ok=True)
             self.output_dir.set_path(output_dir)
 

src/gui/panels/step11_map_panel.py

@@ -253,7 +253,7 @@ class Step11MapPanel(QWidget):
         self.geotiff_dir_label = QLabel("水色指数目录:")
         self.geotiff_dir_label.setMinimumWidth(120)
         self.geotiff_dir_edit = QLineEdit()
-        self.geotiff_dir_edit.setPlaceholderText("选择 8_WaterIndex_Images 文件夹（批量渲染）…")
+        self.geotiff_dir_edit.setPlaceholderText("选择 10_WaterIndex_Images 文件夹（批量渲染）…")
         geotiff_dir_btn = QPushButton("浏览…")
         geotiff_dir_btn.setMaximumWidth(80)
         geotiff_dir_btn.clicked.connect(self.browse_geotiff_dir)
@@ -392,7 +392,7 @@ class Step11MapPanel(QWidget):
         """浏览 GeoTIFF 文件夹（批量模式）"""
         default = self._get_default_work_dir()
         if default:
-            default = os.path.join(default, "8_WaterIndex_Images")
+            default = os.path.join(default, "10_WaterIndex_Images")
         d = QFileDialog.getExistingDirectory(
             self, "选择水色指数 GeoTIFF 文件夹", default
         )
@@ -514,18 +514,18 @@ class Step11MapPanel(QWidget):
             pred_dir = None
             if hasattr(main_window, 'step11_prediction_panel'):
                 step8_widget = getattr(main_window.step11_prediction_panel, 'output_file', None)
-                step8_output = ""
+                step10_output = ""
                 if hasattr(step8_widget, 'get_path'):
-                    step8_output = step8_widget.get_path() or ""
+                    step10_output = step8_widget.get_path() or ""
                 elif hasattr(step8_widget, 'text'):
-                    step8_output = step8_widget.text() or ""
+                    step10_output = step8_widget.text() or ""
 
-                if step8_output:
+                if step10_output:
                     # 若为相对路径，使用 work_dir 合成为绝对路径
-                    if not os.path.isabs(step8_output):
-                        step8_output = os.path.join(self.work_dir or '', step8_output).replace('\\', '/')
+                    if not os.path.isabs(step10_output):
+                        step10_output = os.path.join(self.work_dir or '', step10_output).replace('\\', '/')
                     # 提取父目录后追加 Machine_Learning_Prediction（最底层真实子目录）
-                    base_pred_dir = str(Path(step8_output).parent)
+                    base_pred_dir = str(Path(step10_output).parent)
                     ml_pred_dir = Path(base_pred_dir) / "Machine_Learning_Prediction"
                     pred_dir = str(ml_pred_dir) if ml_pred_dir.exists() else base_pred_dir
 
@@ -594,13 +594,13 @@ class Step11MapPanel(QWidget):
                     print("⚠️ 提示：专题图生成模块需传入标准矢量边界文件 (.shp)，请手动选择。")
 
             # 6. 自动探测 Step 8 输出的水色指数 GeoTIFF（GeoTIFF 渲染模式）
-            step8_out_dir = Path(self.work_dir) / "8_WaterIndex_Images" if self.work_dir else None
-            if step8_out_dir and step8_out_dir.is_dir():
+            step10_out_dir = Path(self.work_dir) / "10_WaterIndex_Images" if self.work_dir else None
+            if step10_out_dir and step10_out_dir.is_dir():
                 # GeoTIFF 批量模式：填充目录供批量渲染
                 if not (self.geotiff_dir_edit.text() or "").strip():
-                    self.geotiff_dir_edit.setText(str(step8_out_dir))
+                    self.geotiff_dir_edit.setText(str(step10_out_dir))
                 # GeoTIFF 单文件模式：默认选中第一个
-                tif_files = sorted(step8_out_dir.glob("*.tif"))
+                tif_files = sorted(step10_out_dir.glob("*.tif"))
                 if tif_files and not (self.geotiff_file.get_path() or "").strip():
                     self.geotiff_file.set_path(str(tif_files[0]))
         except Exception as e:

src/gui/panels/step14_panel.py

@@ -253,7 +253,7 @@ class Step14Panel(QWidget):
         self.geotiff_dir_label = QLabel("水色指数目录:")
         self.geotiff_dir_label.setMinimumWidth(120)
         self.geotiff_dir_edit = QLineEdit()
-        self.geotiff_dir_edit.setPlaceholderText("选择 8_WaterIndex_Images 文件夹（批量渲染）…")
+        self.geotiff_dir_edit.setPlaceholderText("选择 10_WaterIndex_Images 文件夹（批量渲染）…")
         geotiff_dir_btn = QPushButton("浏览…")
         geotiff_dir_btn.setMaximumWidth(80)
         geotiff_dir_btn.clicked.connect(self.browse_geotiff_dir)
@@ -392,7 +392,7 @@ class Step14Panel(QWidget):
         """浏览 GeoTIFF 文件夹（批量模式）"""
         default = self._get_default_work_dir()
         if default:
-            default = os.path.join(default, "8_WaterIndex_Images")
+            default = os.path.join(default, "10_WaterIndex_Images")
         d = QFileDialog.getExistingDirectory(
             self, "选择水色指数 GeoTIFF 文件夹", default
         )
@@ -514,18 +514,18 @@ class Step14Panel(QWidget):
             pred_dir = None
             if hasattr(main_window, 'step11_prediction_panel'):
                 step8_widget = getattr(main_window.step11_prediction_panel, 'output_file', None)
-                step8_output = ""
+                step10_output = ""
                 if hasattr(step8_widget, 'get_path'):
-                    step8_output = step8_widget.get_path() or ""
+                    step10_output = step8_widget.get_path() or ""
                 elif hasattr(step8_widget, 'text'):
-                    step8_output = step8_widget.text() or ""
+                    step10_output = step8_widget.text() or ""
 
-                if step8_output:
+                if step10_output:
                     # 若为相对路径，使用 work_dir 合成为绝对路径
-                    if not os.path.isabs(step8_output):
-                        step8_output = os.path.join(self.work_dir or '', step8_output).replace('\\', '/')
+                    if not os.path.isabs(step10_output):
+                        step10_output = os.path.join(self.work_dir or '', step10_output).replace('\\', '/')
                     # 提取父目录后追加 Machine_Learning_Prediction（最底层真实子目录）
-                    base_pred_dir = str(Path(step8_output).parent)
+                    base_pred_dir = str(Path(step10_output).parent)
                     ml_pred_dir = Path(base_pred_dir) / "Machine_Learning_Prediction"
                     pred_dir = str(ml_pred_dir) if ml_pred_dir.exists() else base_pred_dir
 
@@ -594,13 +594,13 @@ class Step14Panel(QWidget):
                     print("⚠️ 提示：专题图生成模块需传入标准矢量边界文件 (.shp)，请手动选择。")
 
             # 6. 自动探测 Step 8 输出的水色指数 GeoTIFF（GeoTIFF 渲染模式）
-            step8_out_dir = Path(self.work_dir) / "8_WaterIndex_Images" if self.work_dir else None
-            if step8_out_dir and step8_out_dir.is_dir():
+            step10_out_dir = Path(self.work_dir) / "10_WaterIndex_Images" if self.work_dir else None
+            if step10_out_dir and step10_out_dir.is_dir():
                 # GeoTIFF 批量模式：填充目录供批量渲染
                 if not (self.geotiff_dir_edit.text() or "").strip():
-                    self.geotiff_dir_edit.setText(str(step8_out_dir))
+                    self.geotiff_dir_edit.setText(str(step10_out_dir))
                 # GeoTIFF 单文件模式：默认选中第一个
-                tif_files = sorted(step8_out_dir.glob("*.tif"))
+                tif_files = sorted(step10_out_dir.glob("*.tif"))
                 if tif_files and not (self.geotiff_file.get_path() or "").strip():
                     self.geotiff_file.set_path(str(tif_files[0]))
         except Exception as e:

src/gui/panels/step4_sampling_panel.py

@@ -6,6 +6,7 @@ Step4 面板 - 采样点布设
 
 import os
 
+from PyQt5.QtCore import QTimer
 from PyQt5.QtWidgets import (
     QWidget, QVBoxLayout, QGroupBox, QFormLayout,
     QPushButton, QCheckBox, QSpinBox, QMessageBox,
@@ -94,6 +95,11 @@ class Step4SamplingPanel(QWidget):
         layout.addStretch()
         self.setLayout(layout)
 
+        # 添加心跳定时器，每2秒自动检查一次输出文件状态，刷新预览按钮
+        self._status_timer = QTimer(self)
+        self._status_timer.timeout.connect(self._check_csv_exists)
+        self._status_timer.start(2000)
+
         # 监听输出路径变化，实时更新预览按钮状态
         self.output_file.line_edit.textChanged.connect(self._on_output_changed)
 

src/gui/panels/step7_index_panel.py

@@ -7,9 +7,8 @@ Step7 面板 - 水质指数计算
 import os
 import sys
 import pandas as pd
-import numpy as np
 from pathlib import Path
-from typing import Dict, List, Optional, Tuple
+from typing import Dict, List, Optional
 
 from PyQt5.QtWidgets import (
     QWidget, QVBoxLayout, QGroupBox, QGridLayout,
@@ -127,25 +126,10 @@ class Step7IndexPanel(QWidget):
         self.formula_group.setLayout(formula_outer_layout)
         main_layout.addWidget(self.formula_group)
 
-        # 4. 输出选项
-        output_group = QGroupBox("输出模式")
+        # 4. 执行设置
+        output_group = QGroupBox("执行设置")
         output_layout = QVBoxLayout()
 
-        mode_layout = QHBoxLayout()
-        self.mode_group = QButtonGroup()
-        self.radio_both = QRadioButton("两者皆出")
-        self.radio_wide = QRadioButton("仅宽表")
-        self.radio_single = QRadioButton("仅单文件")
-        self.mode_group.addButton(self.radio_both, 0)
-        self.mode_group.addButton(self.radio_wide, 1)
-        self.mode_group.addButton(self.radio_single, 2)
-        self.radio_both.setChecked(True)
-        mode_layout.addWidget(self.radio_both)
-        mode_layout.addWidget(self.radio_wide)
-        mode_layout.addWidget(self.radio_single)
-        mode_layout.addStretch()
-        output_layout.addLayout(mode_layout)
-
         self.enable_checkbox = QCheckBox("启用计算流程")
         self.enable_checkbox.setChecked(True)
         output_layout.addWidget(self.enable_checkbox)
@@ -261,25 +245,28 @@ class Step7IndexPanel(QWidget):
         for item in self.index_checkboxes.values():
             item.setCheckState(Qt.Unchecked)
 
-    def get_config(self) -> Dict:
+    def get_config(self) -> dict:
+        """获取配置"""
         selected = [
             name for name, item in self.index_checkboxes.items()
             if item.checkState() == Qt.Checked
         ]
-        # Build coefficient dict for selected formulas
-        formula_coefficients = {
-            name: self._formula_coef_map.get(name, [])
-            for name in selected
-        }
-        return {
+        config = {
             'training_csv_path': self.training_data_widget.get_path(),
             'formula_csv_file': self.builtin_formula_path,
             'formula_names': selected,
-            'formula_coefficients': formula_coefficients,
             'enabled': self.enable_checkbox.isChecked(),
-            'output_mode': self.mode_group.checkedId(),
+            'output_mode': 0,
         }
 
+        work_dir = self._get_work_dir()
+        if work_dir:
+            track_a_dir = os.path.join(work_dir, "6_water_quality_indices")
+            os.makedirs(track_a_dir, exist_ok=True)
+            config['output_file'] = os.path.join(track_a_dir, "training_spectra_indices.csv").replace('\\', '/')
+
+        return config
+
     def set_config(self, config: Dict):
         if 'training_csv_path' in config:
             self.training_data_widget.set_path(config['training_csv_path'])
@@ -288,10 +275,6 @@ class Step7IndexPanel(QWidget):
             for name, item in self.index_checkboxes.items():
                 item.setCheckState(Qt.Checked if name in sel else Qt.Unchecked)
         self.enable_checkbox.setChecked(config.get('enabled', True))
-        if 'output_mode' in config:
-            btn = self.mode_group.button(config['output_mode'])
-            if btn:
-                btn.setChecked(True)
 
     def update_from_config(self, work_dir=None, pipeline=None):
         if work_dir:
@@ -313,117 +296,24 @@ class Step7IndexPanel(QWidget):
             return main.work_dir
         return None
 
-    def _get_coord_cols(self, df: pd.DataFrame) -> Tuple[str, str]:
-        coord_candidates = ['lon', 'lng', 'longitude', '经度', 'x', 'lon_utm', 'utm_x', 'pixel_x']
-        lat_candidates = ['lat', 'latitude', '纬度', 'y', 'lat_utm', 'utm_y', 'pixel_y']
-
-        x_col, y_col = None, None
-        for col in df.columns:
-            cl = col.lower()
-            if x_col is None and any(c in cl for c in coord_candidates):
-                x_col = col
-            if y_col is None and any(c in cl for c in lat_candidates):
-                y_col = col
-
-        if x_col is None and len(df.columns) >= 2:
-            x_col = df.columns[0]
-        if y_col is None and len(df.columns) >= 2:
-            y_col = df.columns[1]
-
-        return x_col or 'x_coord', y_col or 'y_coord'
-
     def run_step(self):
+        """独立运行步骤7 (通过标准的 Worker 路由下发)"""
         config = self.get_config()
 
         if not config['enabled']:
             QMessageBox.information(self, "提示", "已禁用计算流程（启用计算流程未勾选）")
             return
 
-        training_path = config['training_csv_path']
+        training_path = config.get('training_csv_path')
         if not training_path or not os.path.exists(training_path):
             QMessageBox.warning(self, "提示", "请先选择输入特征提取CSV文件")
             return
 
-        formula_names = config['formula_names']
-        if not formula_names:
+        if not config.get('formula_names'):
             QMessageBox.warning(self, "提示", "请至少勾选一个公式")
             return
 
-        output_mode = config['output_mode']
-
-        try:
-            from src.core.steps.data_preparation_step import DataPreparationStep
-
-            spec_df = pd.read_csv(training_path)
-            x_col, y_col = self._get_coord_cols(spec_df)
-
-            # 构建 formula_csv_path（使用内置 waterindex.csv）
-            formula_csv_path = self.builtin_formula_path
-            if not formula_csv_path or not os.path.exists(formula_csv_path):
-                # 尝试从 src/gui/model/ 目录找
-                possible_path = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), 'gui', 'model', 'waterindex.csv')
-                if os.path.exists(possible_path):
-                    formula_csv_path = possible_path
-
-            work_dir = self._get_work_dir()
-
-            # 调用 DataPreparationStep 的静态方法计算水质指数（宽表输出）
-            indices_csv_path = DataPreparationStep.calculate_water_quality_indices(
-                training_csv_path=training_path,
-                formula_csv_file=formula_csv_path,
-                formula_names=formula_names,
-                output_file=None,  # 不在此处指定输出，由下面的双轨输出逻辑接管
-                enabled=True,
-                output_dir=work_dir if work_dir else os.getcwd(),
-            )
-
-            # 读取计算结果（宽表）
-            if indices_csv_path and os.path.exists(indices_csv_path):
-                output_df = pd.read_csv(indices_csv_path)
-            else:
-                output_df = spec_df  # fallback
-
-            track_a_path = None
-            track_b_dir = None
-
-            if output_mode in (0, 1):
-                track_a_dir = os.path.join(work_dir, "6_water_quality_indices") if work_dir else "6_water_quality_indices"
-                os.makedirs(track_a_dir, exist_ok=True)
-                track_a_path = os.path.join(track_a_dir, "training_spectra_indices.csv")
-
-            if output_mode in (0, 2):
-                track_b_dir = os.path.join(work_dir, "11_12_13_predictions", "Traditional_Indices") if work_dir else "11_12_13_predictions/Traditional_Indices"
-                os.makedirs(track_b_dir, exist_ok=True)
-
-            saved = []
-            if output_mode in (0, 1):
-                output_df.to_csv(track_a_path, index=False, float_format='%.6f')
-                saved.append(f"宽表: {track_a_path}")
-
-            if output_mode in (0, 2):
-                coord_x = spec_df[x_col].values if x_col in spec_df.columns else np.arange(len(spec_df))
-                coord_y = spec_df[y_col].values if y_col in spec_df.columns else np.zeros(len(spec_df))
-
-                for formula_name in formula_names:
-                    if formula_name not in output_df.columns:
-                        continue
-                    single_df = pd.DataFrame({
-                        'x_coord': coord_x,
-                        'y_coord': coord_y,
-                        'value': output_df[formula_name].values,
-                    })
-                    safe_name = formula_name.replace('/', '_').replace(' ', '_')
-                    out_path = os.path.join(track_b_dir, f"{safe_name}_prediction.csv")
-                    single_df.to_csv(out_path, index=False, float_format='%.6f')
-                saved.append(f"单文件目录: {track_b_dir}")
-
-            QMessageBox.information(
-                self, "计算完成",
-                f"已保存 {len(saved)} 个输出目标:\n" + "\n".join(saved)
-            )
-
-        except ImportError as e:
-            QMessageBox.critical(self, "依赖错误", f"无法导入模块:\n{e}")
-        except Exception as e:
-            import traceback
-            QMessageBox.critical(self, "计算失败", f"原因: {str(e)}\n{traceback.format_exc()}")
+        main_window = self.window()
+        if hasattr(main_window, 'run_single_step'):
+            pipeline_config = {'step7_index': config}
+            main_window.run_single_step('step7_index', pipeline_config)

src/gui/water_quality_gui.py

@@ -1365,46 +1365,21 @@ class WaterQualityGUI(QMainWindow):
         """初始化步骤依赖关系和标准输出路径"""
         # 定义每个步骤的标准输出路径模式（相对于工作目录）
         self.step_default_outputs = {
-            'step1': {
-                'water_mask_ndwi': '1_water_mask/water_mask_from_ndwi.dat',
-                'water_mask_shp': '1_water_mask/water_mask_from_shp.dat',
-                'hsi_preview': '1_water_mask/hsi_preview.png',
-                'water_mask_overlay': '1_water_mask/water_mask_overlay.png'
-            },
-            'step2': {
-                'glint_mask': '2_glint/severe_glint_area.dat'
-            },
-            'step3': {
-                'deglint_kutser': '3_deglint/deglint_kutser.bsq',
-                'deglint_goodman': '3_deglint/deglint_goodman.bsq',
-                'deglint_hedley': '3_deglint/deglint_hedley.bsq',
-                'deglint_sugar': '3_deglint/deglint_sugar.bsq',
-                'deglint_interpolated': '3_deglint/interpolated_*.bsq'
-            },
-            'step5_clean': {
-                'processed_data': '4_processed_data/processed_data.csv'
-            },
-            'step6_feature': {
-                'training_spectra': '5_training_spectra/training_spectra.csv'
-            },
-            'step7_index': {
-                'water_indices': '6_water_quality_indices/water_quality_indices.csv'
-            },
-            'step8_ml_train': {
-                'models': '7_Supervised_Model_Training/'
-            },
-            'step4_sampling': {
-                'sampling_points': '10_sampling/sampling_spectra.csv'
-            },
-            'step9_ml_predict': {
-                'predictions': '11_12_13_predictions/Machine_Learning_Prediction/'
-            },
-            'step11_map': {
-                'distribution_maps': '14_visualization/'
-            }
+            'step1': "1_water_mask/water_mask_from_ndwi.dat",
+            'step2': "2_glint/severe_glint_area.dat",
+            'step3': "3_deglint/deglint_kutser.bsq",
+            'step4_sampling': "4_sampling/sampling_spectra.csv",
+            'step5_clean': "4_processed_data/processed_data.csv",
+            'step6_feature': "5_training_spectra/training_spectra.csv",
+            'step7_index': "6_water_quality_indices/training_spectra_indices.csv",
+            'step8_ml_train': "7_Supervised_Model_Training/",
+            'step9_ml_predict': "11_12_13_predictions/Machine_Learning_Prediction/",
+            'step10_watercolor': "10_WaterIndex_Images/",
+            'step11_map': "14_visualization/"
         }
         
-        # 定义步骤间的依赖关系：{当前步骤: {输入字段: (依赖步骤, 输出类型, 面板属性名)}}
+        # 依赖关系字典结构:
+        # '当前步骤ID': { '依赖参数名': ('上游步骤ID', '上游输出类型/Key', '当前步骤接收该路径的组件属性名') }
         self.step_dependencies = {
             'step2': {
                 'img_path': ('step1', 'reference_img', 'img_file'),
@@ -1412,31 +1387,36 @@ class WaterQualityGUI(QMainWindow):
             },
             'step3': {
                 'img_path': ('step1', 'reference_img', 'img_file'),
-                'water_mask': ('step1', 'water_mask', 'water_mask_file'),
+                'water_mask': ('step1', 'water_mask', 'water_mask_file')
+            },
+            'step4_sampling': {
+                'deglint_img_path': ('step3', 'deglint_image', 'deglint_img_file'),
+                'water_mask_path': ('step1', 'water_mask', 'water_mask_file')
+            },
+            'step5_clean': {
+                'csv_path': ('step4_sampling', 'sampling_spectra', 'csv_file')  # step5 寻找 step4 的采样点
             },
             'step6_feature': {
                 'deglint_img_path': ('step3', 'deglint_image', 'deglint_img_file'),
                 'csv_path': ('step5_clean', 'processed_data', 'csv_file'),
-                'boundary_mask_path': ('step1', 'water_mask', 'boundary_mask_file'),
+                'boundary_mask_path': ('step1', 'water_mask', 'water_mask_file'), # step6_panel里叫water_mask_file
                 'glint_mask_path': ('step2', 'glint_mask', 'glint_mask_file')
             },
             'step7_index': {
-                'training_csv_path': ('step6_feature', 'training_spectra', 'output_file')
+                'training_csv_path': ('step6_feature', 'training_spectra', 'training_data_widget') # step7 找 step6 的光谱提取
             },
             'step8_ml_train': {
-                'training_csv_path': ('step7_index', 'water_indices', 'csv_file')
-            },
-            'step4_sampling': {
-                'deglint_img_path': ('step3', 'deglint_image', 'deglint_img_file'),
-                'water_mask_path': ('step1', 'water_mask', 'water_mask_file'),
-                'glint_mask_path': ('step2', 'glint_mask', 'glint_mask_file')
+                'training_csv_file': ('step7_index', 'training_spectra_indices', 'training_csv_file') # step8 找 step7 的指数宽表
             },
             'step9_ml_predict': {
-                'sampling_csv_path': ('step4_sampling', 'sampling_points', 'sampling_csv_file'),
-                'models_dir': ('step8_ml_train', 'models', 'models_dir_file')
+                'models_dir': ('step8_ml_train', 'Supervised_Model_Training', 'models_dir_widget')
+            },
+            'step10_watercolor': {
+                'bsq_file': ('step3', 'deglint_image', 'bsq_file') # 水色反演需要去耀斑BSQ影像
             },
             'step11_map': {
-                'prediction_csv_path': ('step9_ml_predict', 'predictions', 'prediction_csv_file')
+                'prediction_csv_dir_edit': ('step9_ml_predict', 'Machine_Learning_Prediction', 'prediction_csv_dir_edit'),
+                'geotiff_dir_edit': ('step10_watercolor', 'WaterIndex_Images', 'geotiff_dir_edit')
             }
         }
 
@@ -2312,7 +2292,17 @@ class WaterQualityGUI(QMainWindow):
         if step_id not in self.step_default_outputs:
             return None
 
-        step_outputs = self.step_default_outputs[step_id]
+        raw = self.step_default_outputs[step_id]
+
+        # ★ 兼容扁平化后的纯字符串路径格式
+        rel_path = None
+        if isinstance(raw, str):
+            rel_path = raw
+        elif isinstance(raw, dict):
+            rel_path = raw.get(output_type) or list(raw.values())[0]
+
+        if not rel_path:
+            return None
 
         # ★ 掩膜类型列表：这些类型只接受科学数据格式
         mask_types = {'water_mask', 'glint_mask', 'boundary_mask'}
@@ -2345,12 +2335,11 @@ class WaterQualityGUI(QMainWindow):
 
         # 根据输出类型查找对应的文件
         if output_type == 'water_mask':
-            # 水域掩膜：优先查找NDWI生成的，其次是shp生成的
-            for mask_type in ['water_mask_ndwi', 'water_mask_shp']:
-                if mask_type in step_outputs:
-                    mask_path = work_path / step_outputs[mask_type]
-                    if mask_path.exists():
-                        return str(mask_path)
+            # 水域掩膜：直接用统一路径
+            if rel_path:
+                mask_path = work_path / rel_path
+                if mask_path.exists():
+                    return str(mask_path)
         elif output_type == 'reference_img':
             # 参考影像：从step1的配置中获取用户输入的影像路径
             if hasattr(self, 'step1_panel'):
@@ -2358,32 +2347,29 @@ class WaterQualityGUI(QMainWindow):
                 if img_path and Path(img_path).exists():
                     return img_path
         elif output_type == 'deglint_image':
-            # 去耀斑影像：查找step3的各种去耀斑方法输出
-            deglint_types = ['deglint_kutser', 'deglint_goodman', 'deglint_hedley', 'deglint_sugar']
-            for deglint_type in deglint_types:
-                if deglint_type in step_outputs:
-                    deglint_path = work_path / step_outputs[deglint_type]
-                    if deglint_path.exists():
-                        return str(deglint_path)
+            # 去耀斑影像：直接用统一路径
+            if rel_path:
+                deglint_path = work_path / rel_path
+                if deglint_path.exists():
+                    return str(deglint_path)
             # 还要检查插值方法生成的文件
             deglint_dir = work_path / "3_deglint"
             if deglint_dir.exists():
                 for file_path in deglint_dir.glob("interpolated_*.bsq"):
                     return str(file_path)
-        elif output_type in step_outputs:
-            # 直接匹配的输出类型
-            relative_path = step_outputs[output_type]
-            if relative_path.endswith('/'):
+        elif rel_path:
+            # 直接匹配的输出类型（统一使用 rel_path）
+            if rel_path.endswith('/'):
                 # 是目录
-                output_path = work_path / relative_path.rstrip('/')
+                output_path = work_path / rel_path.rstrip('/')
                 if output_path.exists() and output_path.is_dir():
                     return str(output_path)
             else:
                 # 是文件
-                output_path = work_path / relative_path
+                output_path = work_path / rel_path
                 if output_path.exists():
                     return str(output_path)
-        
+
         return None
 
     def scan_work_directory_for_files(self, work_path):

src/preprocessing/process_water_quality_data.py

@@ -4,6 +4,7 @@ if not hasattr(threading.Thread, "isAlive"):
 
 import warnings
 import os
+import re
 import numpy as np
 import pandas as pd
 from scipy import stats
@@ -11,6 +12,54 @@ from scipy import stats
 warnings.filterwarnings("ignore")
 
 
+def auto_detect_coord_columns(df: pd.DataFrame):
+    """
+    双重验证智能识别坐标列：
+    1. 严格正则匹配列名
+    2. 基于数值范围的地理学推断
+    """
+    lon_patterns = [
+        r'^lon', r'^lng', r'^longitude', r'经度', r'^x$', r'^utm_x$', r'^pixel_x$'
+    ]
+    lat_patterns = [
+        r'^lat', r'^latitude', r'纬度', r'^y$', r'^utm_y$', r'^pixel_y$'
+    ]
+
+    x_col, y_col = None, None
+
+    for col in df.columns:
+        col_str = str(col).lower().strip()
+        if x_col is None and any(re.search(p, col_str) for p in lon_patterns):
+            x_col = col
+        if y_col is None and any(re.search(p, col_str) for p in lat_patterns):
+            y_col = col
+
+    if x_col and y_col:
+        return x_col, y_col
+
+    numeric_cols = df.select_dtypes(include=[np.number]).columns.tolist()
+
+    if len(numeric_cols) >= 2:
+        col1, col2 = numeric_cols[0], numeric_cols[1]
+        mean1 = df[col1].head(10).mean()
+        mean2 = df[col2].head(10).mean()
+
+        if abs(mean1) <= 90 and abs(mean2) > 90:
+            y_col, x_col = col1, col2
+        elif abs(mean2) <= 90 and abs(mean1) > 90:
+            x_col, y_col = col1, col2
+        else:
+            if mean1 > mean2:
+                x_col, y_col = col1, col2
+            else:
+                x_col, y_col = col2, col1
+
+        print(f"💡 触发智能数值推断坐标列: X/经度->[{x_col}], Y/纬度->[{y_col}]")
+        return x_col, y_col
+
+    return df.columns[0], df.columns[1]
+
+
 def detect_outliers_iqr(data: pd.DataFrame, column: str) -> pd.Series:
     """使用 IQR 方法检测异常值，返回与 data 同索引的布尔序列"""
     s = pd.to_numeric(data[column], errors="coerce")
@@ -92,11 +141,15 @@ def process_water_quality_data(input_file: str, output_file: str):
     print(f"原始数据形状: {df.shape}")
     print(f"列名: {list(df.columns)}")
 
+    # 0.5) 智能检测坐标列
+    x_col, y_col = auto_detect_coord_columns(df)
+    print(f"坐标列检测结果: X/经度=[{x_col}], Y/纬度=[{y_col}]")
+
     # 1) 经纬度精度筛选（小数位 >= 7）
     print("\n正在筛选经纬度精度(小数位>=7)...")
     initial_count = len(df)
 
-    for col in ["经度", "纬度"]:
+    for col in [y_col, x_col]:
         if col in df.columns:
             dec_len = df[col].apply(_decimal_len)
             keep_mask = dec_len >= 7
@@ -109,26 +162,23 @@ def process_water_quality_data(input_file: str, output_file: str):
 
     # 2) 异常值检测（IQR）- 只删除异常值，不删除整行
     print("\n正在检测异常值(IQR)...")
-    # 数值列
     numeric_columns = df.select_dtypes(include=[np.number]).columns.tolist()
 
-    # 排除不检测的列
-    exclude_columns = ["时间", "测量点", "纬度", "经度"]
+    exclude_columns = {"时间", "测量点", y_col, x_col}
     if "原始" in df.columns:
-        exclude_columns.append("原始")
+        exclude_columns.add("原始")
 
     columns_to_check = [c for c in numeric_columns if c not in exclude_columns]
     print(f"将检测以下列的异常值: {columns_to_check}")
 
     df_clean = df.copy()
     total_outliers_removed = 0
-    
+
     for column in columns_to_check:
         if column in df_clean.columns and df_clean[column].notna().sum() > 0:
             col_mask = detect_outliers_iqr(df_clean, column)
             outlier_count = int(col_mask.sum())
             print(f'列 "{column}" 检测到 {outlier_count} 个异常值，将其设为 NaN')
-            # 只将异常值设为 NaN，不删除整行
             df_clean.loc[col_mask, column] = np.nan
             total_outliers_removed += outlier_count
 
@@ -140,7 +190,7 @@ def process_water_quality_data(input_file: str, output_file: str):
         df_clean = df_clean.drop(columns=["原始"])
         print('已去除 "原始" 列')
 
-    # 4) 字段类型处理：尽量把“时间”转为 datetime
+    # 4) 字段类型处理：尽量把"时间"转为 datetime
     if "时间" in df_clean.columns:
         try:
             df_clean["时间"] = pd.to_datetime(df_clean["时间"], errors="coerce")
@@ -153,22 +203,18 @@ def process_water_quality_data(input_file: str, output_file: str):
         print('错误：未找到 "测量点" 列')
         return
 
-    # 构建聚合字典
     agg_dict = {}
     if "时间" in df_clean.columns and np.issubdtype(df_clean["时间"].dtype, np.datetime64):
-        # 时间取平均（等价于时间戳平均）
         agg_dict["时间"] = "mean"
     elif "时间" in df_clean.columns:
-        # 如果不是时间类型，保留最常见值以避免无意义的字符串平均
         agg_dict["时间"] = lambda s: s.mode().iloc[0] if not s.mode().empty else s.dropna().iloc[0] if s.dropna().size else np.nan
 
-    for col in ["纬度", "经度"]:
+    for col in [y_col, x_col]:
         if col in df_clean.columns:
             agg_dict[col] = "mean"
 
-    # 其余数值列取均值
     for col in df_clean.select_dtypes(include=[np.number]).columns:
-        if col not in ["纬度", "经度"]:
+        if col not in {y_col, x_col}:
             agg_dict[col] = "mean"
 
     grouped = df_clean.groupby("测量点", as_index=False).agg(agg_dict)

src/utils/sampling.py

@@ -1049,7 +1049,7 @@ if __name__ == "__main__":
     bil_file = r"E:\wq_gui_test\3_deglint\deglint_goodman.bsq"
     water_mask_shp = r"E:\wq_gui_test\1_water_mask\water_mask_from_shp.dat"
     severe_glint = r"E:\wq_gui_test\2_glint\severe_glint_area.dat"
-    output_csvpath = r"E:\wq_gui_test\10_sampling\sampling_spectra.csv"
+    output_csvpath = r"E:\wq_gui_test\4_sampling\sampling_spectra.csv"
 
     # 设置参数
     interval = 50  # 基础采样点间隔（像元数），当use_adaptive_sampling=False时使用

tmp_watercolor_rescue.py

@@ -204,7 +204,7 @@ class Step11WaterColorPanel(QWidget):
             "输出目录:",
             "Directories"
         )
-        self.output_dir.line_edit.setPlaceholderText("留空 → 工作目录/8_WaterIndex_Images")
+        self.output_dir.line_edit.setPlaceholderText("留空 → 工作目录/10_WaterIndex_Images")
         self.output_dir.browse_btn.clicked.disconnect()
         self.output_dir.browse_btn.clicked.connect(self._browse_output_dir)
         output_layout.addRow("输出目录:", self.output_dir)
@@ -452,7 +452,7 @@ class Step11WaterColorPanel(QWidget):
 
         # 自动填入输出目录
         if self.work_dir:
-            out_dir = os.path.join(self.work_dir, "8_WaterIndex_Images").replace('\\', '/')
+            out_dir = os.path.join(self.work_dir, "10_WaterIndex_Images").replace('\\', '/')
             os.makedirs(out_dir, exist_ok=True)
             if not self.output_dir.get_path():
                 self.output_dir.set_path(out_dir)
@@ -483,7 +483,7 @@ class Step11WaterColorPanel(QWidget):
             return
         if not output_dir:
             work_dir = self._get_default_work_dir()
-            output_dir = os.path.join(work_dir, "8_WaterIndex_Images").replace('\\', '/')
+            output_dir = os.path.join(work_dir, "10_WaterIndex_Images").replace('\\', '/')
             os.makedirs(output_dir, exist_ok=True)
             self.output_dir.set_path(output_dir)