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
+    # 提取原始坐标（使用智能坐标列检测）
-    lat_array = coor_data[:, 1]  # 第2列是纬度（跳过测量点ID列）
+    lon_patterns = [
-    lon_array = coor_data[:, 2]  # 第3列是经度
+        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/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):
+                    if not os.path.isabs(step10_output):
-                        step8_output = os.path.join(self.work_dir or '', step8_output).replace('\\', '/')
+                        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
+            step10_out_dir = Path(self.work_dir) / "10_WaterIndex_Images" if self.work_dir else None
-            if step8_out_dir and step8_out_dir.is_dir():
+            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):
+                    if not os.path.isabs(step10_output):
-                        step8_output = os.path.join(self.work_dir or '', step8_output).replace('\\', '/')
+                        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
+            step10_out_dir = Path(self.work_dir) / "10_WaterIndex_Images" if self.work_dir else None
-            if step8_out_dir and step8_out_dir.is_dir():
+            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/water_quality_gui.py

@@ -1378,7 +1378,8 @@ class WaterQualityGUI(QMainWindow):
             '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'),
@@ -1386,31 +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')
+                'training_csv_file': ('step7_index', 'training_spectra_indices', 'training_csv_file') # step8 找 step7 的指数宽表
-            },
-            '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')
             },
             'step9_ml_predict': {
-                'sampling_csv_path': ('step4_sampling', 'sampling_points', 'sampling_csv_file'),
+                'models_dir': ('step8_ml_train', 'Supervised_Model_Training', 'models_dir_widget')
-                'models_dir': ('step8_ml_train', 'models', 'models_dir_file')
+            },
+            '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')
             }
         }
 

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
@@ -109,13 +162,11 @@ 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", y_col, x_col}
-    exclude_columns = ["时间", "测量点", "纬度", "经度"]
     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}")
@@ -128,7 +179,6 @@ def process_water_quality_data(input_file: str, output_file: str):
             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)

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)