duxingchen/WQ_GUI
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Rename pipeline method names to match step numbers (Step4)

Browse Source
This commit is contained in:
DXC
2026-06-11 14:58:39 +08:00
parent 7c7a31ce00
commit d3262ae80d
6 changed files with 36 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
src/core/pipeline/runner.py
View File

@ -95,14 +95,14 @@ PIPELINE_STEPS: List[StepSpec] = [
description="耀斑去除",
),
StepSpec(
step_id="step4", method_name="step4_process_csv",
step_id="step4", method_name="step5_process_csv",
requires=["csv_path"], produces=["processed_csv_path"],
required_input_files=["csv_path"],
output_file="{work_dir}/4_processed_data/processed_data.csv",
description="CSV 异常值清洗",
),
StepSpec(
step_id="step5", method_name="step5_extract_training_spectra",
step_id="step5", method_name="step6_extract_spectra",
requires=["deglint_img_path", "processed_csv_path", "csv_path", "boundary_path", "glint_mask_path"],
produces=["training_csv_path"],
parameter_map={
@ -115,14 +115,14 @@ PIPELINE_STEPS: List[StepSpec] = [
description="实测样本点光谱提取",
),
StepSpec(
step_id="step7", method_name="step7_water_quality_indices",
step_id="step7", method_name="step7_calc_indices",
requires=["training_csv_path"], produces=["indices_path", "trad_indices_dir"],
required_input_files=["training_csv_path"],
output_file="{work_dir}/6_water_quality_indices/training_spectra_indices.csv",
description="水质参数指数计算（双轨输出：A轨宽表 + B轨单文件）",
),
StepSpec(
step_id="step8", method_name="step8_ml_modeling",
step_id="step8", method_name="step8_train_ml",
requires=["training_csv_path"], produces=["models_dir"],
required_input_files=["training_csv_path"],
output_file="{work_dir}/7_Supervised_Model_Training/best_models.pkl",
@ -145,14 +145,14 @@ PIPELINE_STEPS: List[StepSpec] = [
description="水色指数反演（BSQ 影像直接处理）",
),
StepSpec(
step_id="step10", method_name="step10_sampling",
step_id="step10", method_name="step4_sampling",
requires=["deglint_img_path", "water_mask_path"], produces=["sampling_csv_path"],
required_input_files=["deglint_img_path", "water_mask_path"],
output_file="{work_dir}/4_sampling/sampling_spectra.csv",
description="整景密集采样点生成 + 光谱提取",
),
StepSpec(
step_id="step11_ml", method_name="step11_ml_prediction",
step_id="step11_ml", method_name="step9_predict_ml",
requires=["sampling_csv_path", "models_dir"], produces=["prediction_csv_path"],
required_input_files=["sampling_csv_path", "models_dir"],
output_file="{work_dir}/11_12_13_predictions/prediction_results.csv",
@ -167,7 +167,7 @@ PIPELINE_STEPS: List[StepSpec] = [
description="非经验模型预测",
),
StepSpec(
step_id="step14", method_name="step14_distribution_map",
step_id="step14", method_name="step10_map",
requires=["prediction_csv_path", "boundary_shp_path"],
produces=["distribution_map_path"],
required_input_files=["prediction_csv_path", "boundary_shp_path"],

2
src/core/steps/data_preparation_step.py
View File

@ -2,7 +2,7 @@
"""
数据准备步骤
包含 step4_process_csv, step5_extract_training_spectra, step5_5_calculate_water_quality_indices
包含 step5_process_csv, step6_extract_spectra, step5_5_calculate_water_quality_indices
"""
import time

38
src/core/water_quality_inversion_pipeline_GUI.py
View File

@ -585,7 +585,7 @@ class WaterQualityInversionPipeline:
status="failed", error=str(e))
raise
def step4_process_csv(self, csv_path: str, skip_dependency_check: bool = False, **kwargs) -> str:
def step5_process_csv(self, csv_path: str, skip_dependency_check: bool = False, **kwargs) -> str:
"""
步骤4: 对csv文件进行处理，筛选剔除异常值
@ -606,7 +606,7 @@ class WaterQualityInversionPipeline:
self._notify("completed", f"处理后的CSV文件已保存: {result}")
return result
def step5_extract_training_spectra(self, deglint_img_path: Optional[str] = None,
def step6_extract_spectra(self, deglint_img_path: Optional[str] = None,
radius: int = 5,
source_epsg: int = 4326,
csv_path: Optional[str] = None,
@ -657,7 +657,7 @@ class WaterQualityInversionPipeline:
self._notify("completed", f"训练光谱数据已保存: {result}")
return result
def step6_water_quality_indices(self,
def step7_calc_indices(self,
training_csv_path: Optional[str] = None,
formula_csv_file: Optional[str] = None,
formula_names: Optional[List[str]] = None,
@ -701,7 +701,7 @@ class WaterQualityInversionPipeline:
self._notify("completed", f"水质指数已保存: {result}")
return result
def step7_ml_modeling(self, feature_start_column: str = "374.285004",
def step8_train_ml(self, feature_start_column: str = "374.285004",
preprocessing_methods: List[str] = None,
model_names: List[str] = None,
split_methods: List[str] = None,
@ -859,7 +859,7 @@ class WaterQualityInversionPipeline:
msg = f"Step 9: 浓度反演完毕，结果保存于: {result_csv}"
(self.logger.info if hasattr(self, 'logger') else print)(msg)
def step10_sampling(self, deglint_img_path: Optional[str] = None,
def step4_sampling(self, deglint_img_path: Optional[str] = None,
interval: int = 50,
sample_radius: int = 5,
chunk_size: int = 1000,
@ -906,7 +906,7 @@ class WaterQualityInversionPipeline:
self._notify("completed", f"采样点光谱数据已保存: {result}")
return result
def step11_ml_prediction(self, sampling_csv_path: str,
def step9_predict_ml(self, sampling_csv_path: str,
models_dir: Optional[str] = None,
metric: str = 'test_r2',
prediction_column: str = 'prediction',
@ -947,7 +947,7 @@ class WaterQualityInversionPipeline:
self._notify("completed", f"预测完成，结果保存在: {self.prediction_dir}")
return result
def step14_distribution_map(self, prediction_csv_path: str,
def step10_map(self, prediction_csv_path: str,
boundary_shp_path: str,
output_image_path: Optional[str] = None,
resolution: float = 30,
@ -1623,7 +1623,7 @@ class WaterQualityInversionPipeline:
# 步骤4: 处理CSV文件
if 'step4' in config:
self._notify("步骤4: 数据预处理", "start")
self.step4_process_csv(**config['step4'])
self.step5_process_csv(**config['step4'])
self._notify("步骤4: 数据预处理", "completed", f"(输出: {self.processed_csv_path})")
else:
self._notify("步骤4: 数据预处理", "skipped", "未配置")
@ -1631,7 +1631,7 @@ class WaterQualityInversionPipeline:
# 步骤5: 提取训练样本点光谱
if 'step5' in config:
self._notify("步骤5: 光谱提取", "start")
self.step5_extract_training_spectra(**config['step5'])
self.step6_extract_spectra(**config['step5'])
self._notify("步骤5: 光谱提取", "completed", f"(输出: {self.training_csv_path})")
else:
self._notify("步骤5: 光谱提取", "skipped", "未配置")
@ -1639,7 +1639,7 @@ class WaterQualityInversionPipeline:
# 步骤6: 计算水质指数
if 'step6' in config:
self._notify("步骤6: 水质光谱指数计算", "start")
self.step6_water_quality_indices(**config['step6'])
self.step7_calc_indices(**config['step6'])
self._notify("步骤6: 水质光谱指数计算", "completed", f"(输出: {self.indices_path})")
else:
self._notify("步骤6: 水质光谱指数计算", "skipped", "未配置")
@ -1647,7 +1647,7 @@ class WaterQualityInversionPipeline:
# 步骤7: 训练模型
if 'step7' in config:
self._notify("步骤7: 模型训练", "start")
self.step7_ml_modeling(**config['step7'])
self.step8_train_ml(**config['step7'])
self._notify("步骤7: 模型训练", "completed", f"(输出: {self.models_dir})")
else:
self._notify("步骤7: 模型训练", "skipped", "未配置")
@ -1671,7 +1671,7 @@ class WaterQualityInversionPipeline:
# 步骤10: 生成预测采样点
if 'step10' in config:
self._notify("步骤10: 采样点生成", "start")
sampling_csv_path = self.step10_sampling(**config['step10'])
sampling_csv_path = self.step4_sampling(**config['step10'])
self._notify("步骤10: 采样点生成", "completed", f"(输出: {sampling_csv_path})")
else:
sampling_csv_path = None
@ -1682,7 +1682,7 @@ class WaterQualityInversionPipeline:
self._notify("步骤11: 参数预测", "start")
step11_ml_config = config['step11_ml'].copy()
step11_ml_config['sampling_csv_path'] = sampling_csv_path
prediction_files = self.step11_ml_prediction(**step11_ml_config)
prediction_files = self.step9_predict_ml(**step11_ml_config)
self._notify("步骤11: 参数预测", "completed", f"(生成{len(prediction_files)}个预测文件)")
else:
prediction_files = {}
@ -1724,7 +1724,7 @@ class WaterQualityInversionPipeline:
step14_config['prediction_csv_path'] = pred_file
if 'output_image_path' not in step14_config:
step14_config['output_image_path'] = None
dist_map_path = self.step14_distribution_map(**step14_config)
dist_map_path = self.step10_map(**step14_config)
distribution_maps[target_name] = dist_map_path
self._notify("步骤14: 分布图生成", "completed", f"(生成{len(distribution_maps)}个分布图)")
else:
@ -2426,7 +2426,7 @@ def example_independent_steps():
# 示例3: 独立运行步骤4 - 数据预处理
print("\n示例3: 独立运行步骤4 - 数据预处理")
try:
processed_csv = pipeline.step4_process_csv(
processed_csv = pipeline.step5_process_csv(
csv_path="path/to/water_quality_data.csv"
)
print(f"处理后的CSV文件: {processed_csv}")
@ -2436,7 +2436,7 @@ def example_independent_steps():
# 示例4: 独立运行步骤5 - 光谱提取
print("\n示例4: 独立运行步骤5 - 光谱提取")
try:
training_spectra = pipeline.step5_extract_training_spectra(
training_spectra = pipeline.step6_extract_spectra(
deglint_img_path="path/to/deglint_image.bsq",
csv_path="path/to/processed_data.csv",
glint_mask_path="path/to/severe_glint_area.dat",
@ -2460,7 +2460,7 @@ def example_independent_steps():
# 示例6: 独立运行步骤10 - 采样点生成
print("\n示例6: 独立运行步骤10 - 采样点生成")
try:
sampling_csv = pipeline.step10_sampling(
sampling_csv = pipeline.step4_sampling(
deglint_img_path="path/to/deglint_image.bsq",
water_mask_path="path/to/water_mask.dat",
skip_dependency_check=True
@ -2472,7 +2472,7 @@ def example_independent_steps():
# 示例7: 独立运行步骤11 - 水质预测
print("\n示例7: 独立运行步骤11 - 水质预测")
try:
predictions = pipeline.step11_ml_prediction(
predictions = pipeline.step9_predict_ml(
sampling_csv_path="path/to/sampling_spectra.csv",
models_dir="path/to/models_directory",
skip_dependency_check=True
@ -2484,7 +2484,7 @@ def example_independent_steps():
# 示例8: 独立运行步骤14 - 分布图生成
print("\n示例8: 独立运行步骤14 - 分布图生成")
try:
distribution_map = pipeline.step14_distribution_map(
distribution_map = pipeline.step10_map(
prediction_csv_path="path/to/prediction_results.csv",
boundary_shp_path="path/to/boundary.shp",
skip_dependency_check=True

21
src/gui/core/worker_thread.py
View File

@ -323,18 +323,17 @@ class WorkerThread(QThread):
'step1': 'step1_generate_water_mask',
'step2': 'step2_find_glint_area',
'step3': 'step3_remove_glint',
'step4': 'step4_process_csv',
'step5': 'step5_extract_training_spectra',
'step7': 'step7_water_quality_indices',
'step8': 'step8_ml_modeling',
'step4': 'step5_process_csv',
'step5': 'step6_extract_spectra',
'step7': 'step7_calc_indices',
'step8': 'step8_train_ml',
'step8_non_empirical_modeling': 'step8_non_empirical_modeling',
'step8_qaa': 'step8_qaa_inversion',
'step9': 'step9_watercolor_inversion',
'step9_concentration': 'step9_concentration_inversion',
'step10': 'step10_sampling',
'step11_ml': 'step11_ml_prediction',
'step10': 'step4_sampling',
'step11_ml': 'step9_predict_ml',
'step11': 'step11_non_empirical_prediction',
'step14': 'step14_distribution_map'
'step14': 'step10_map'
}
if step_name not in step_method_map:
@ -350,12 +349,6 @@ class WorkerThread(QThread):
result = method(**config)
return result
# step9_concentration_inversion 同理，必须透传完整 config dict
if step_name == 'step9_concentration':
method = getattr(self.pipeline, method_name)
result = method(**config)
return result
# 透传面板顶层传入的外部预训练模型（GUI step11_prediction_panel 通过 config['_external_model'] 传入）
# 非空才覆盖（遵循 feedback_never_overwrite_with_empty 原则）
for key in ('_external_model', '_external_model_path',

2
src/gui/panels/step14_panel.py
View File

@ -68,7 +68,7 @@ class Step14BatchThread(QThread):
kw["output_image_path"] = str(Path(self.output_dir_optional) / f"{stem}_distribution.png")
else:
kw["output_image_path"] = None
pipeline.step14_distribution_map(**kw)
pipeline.step10_map(**kw)
self.finished_ok.emit(n)
except Exception as e:
self.failed.emit(f"{e}\n{traceback.format_exc()}")

2
src/gui/panels/step6_feature_panel.py
View File

@ -124,7 +124,7 @@ class Step6FeaturePanel(QWidget):
glint_mask_path = self.glint_mask_file.get_path()
if glint_mask_path:
config['glint_mask_path'] = glint_mask_path
# 注意：step5_extract_training_spectra 不接受 output_path / training_csv_path
# 注意：step6_extract_spectra 不接受 output_path / training_csv_path
# 参数，输出路径由 pipeline 内部根据 training_spectra_dir 自动生成。
return config