feat: 报告生成器自动检测水色指数模式 — 支持非 ML 管线
问题: 报告模板仅适配 ML 管线 (steps 5-9+13),
用户跑 1,2,3,4,10,11,12 (水色指数公式管线) 时大量显示
[图片未找到]。
修复: 自动模式检测 + 分支逻辑
1. _detect_pipeline_mode(): 检测 scatter_with_confidence 文件
不存在 → 水色指数模式
2. _get_available_image_types(): 扫描实际存在的图片类型,
只报告确实生成的内容
3. 统计表格: ML→5_Data_Cleaning, 水色指数→10_WaterIndex_CSV
水色指数模式遍历所有公式 CSV 生成统计汇总表
4. 相关性热力图: 水色指数模式跳过并注明原因
5. 分布图: 利用已有 fallback 从 11_Thematic_Map 读取
This commit is contained in:
duxin
@ -268,6 +268,38 @@ class WaterQualityReportGenerator:
|
|||||||
if cfg.enable_ai_analysis is not None:
|
if cfg.enable_ai_analysis is not None:
|
||||||
self.enable_ai_analysis = bool(cfg.enable_ai_analysis)
|
self.enable_ai_analysis = bool(cfg.enable_ai_analysis)
|
||||||
|
|
||||||
|
def _detect_pipeline_mode(self, vis_dir, parameters):
|
||||||
|
"""检测管线模式：ML 还是水色指数公式
|
||||||
|
|
||||||
|
ML 模式标志：vis_dir 中存在 {param}_scatter_with_confidence.png。
|
||||||
|
若不存在 → 水色指数模式 (steps 10,11,12 无 ML)。
|
||||||
|
"""
|
||||||
|
for p in parameters[:3]: # 检查前 3 个参数即可
|
||||||
|
if (vis_dir / f"{p}_scatter_with_confidence.png").exists():
|
||||||
|
return "ml"
|
||||||
|
return "water_index"
|
||||||
|
|
||||||
|
def _get_available_image_types(self, vis_dir, parameters):
|
||||||
|
"""扫描 vis_dir 中实际存在的图片类型，返回类型名列表"""
|
||||||
|
_all_types = ["histogram", "spectrum_comparison", "scatter_with_confidence",
|
||||||
|
"boxplot", "distribution_rendered"]
|
||||||
|
available = set()
|
||||||
|
for p in parameters[:3]:
|
||||||
|
for t in _all_types:
|
||||||
|
fname = f"{p}_{t}.png"
|
||||||
|
if (vis_dir / fname).exists():
|
||||||
|
available.add(t)
|
||||||
|
# 也检查子目录
|
||||||
|
if not available or t not in available:
|
||||||
|
for sub in ("boxplots", "scatter_plots", "distribution_maps"):
|
||||||
|
if (vis_dir / sub / fname).exists():
|
||||||
|
available.add(t)
|
||||||
|
break
|
||||||
|
# 保证至少有 distribution_rendered（来自 11_Thematic_Map）
|
||||||
|
if "distribution_rendered" not in available:
|
||||||
|
available.add("distribution_rendered")
|
||||||
|
return sorted(available)
|
||||||
|
|
||||||
def _style_heading(self, heading, level: int):
|
def _style_heading(self, heading, level: int):
|
||||||
"""统一一级/二级/三级标题字体（黑体）与字号。"""
|
"""统一一级/二级/三级标题字体（黑体）与字号。"""
|
||||||
size_map = {1: Pt(16), 2: Pt(14), 3: Pt(12)}
|
size_map = {1: Pt(16), 2: Pt(14), 3: Pt(12)}
|
||||||
@ -759,6 +791,18 @@ class WaterQualityReportGenerator:
|
|||||||
|
|
||||||
if not vis_dir.exists():
|
if not vis_dir.exists():
|
||||||
raise FileNotFoundError(f"可视化目录不存在: {vis_dir}")
|
raise FileNotFoundError(f"可视化目录不存在: {vis_dir}")
|
||||||
|
|
||||||
|
# ── 管线模式自动检测 ──
|
||||||
|
self._pipeline_mode = self._detect_pipeline_mode(vis_dir, parameters)
|
||||||
|
print(f"[报告] 管线模式: {self._pipeline_mode}")
|
||||||
|
if self._pipeline_mode == "water_index":
|
||||||
|
# 水色指数模式：只保留实际存在的图片类型
|
||||||
|
_available_types = self._get_available_image_types(vis_dir, parameters)
|
||||||
|
self.parameter_images = {
|
||||||
|
p: [f"{p}_{t}.png" for t in _available_types]
|
||||||
|
for p in parameters
|
||||||
|
}
|
||||||
|
print(f"[报告] 水色指数可用图片类型: {_available_types}")
|
||||||
|
|
||||||
if output_path is None:
|
if output_path is None:
|
||||||
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||||||
@ -1613,65 +1657,113 @@ class WaterQualityReportGenerator:
|
|||||||
h2 = doc.add_heading("4.1 水质参数统计分析", level=2)
|
h2 = doc.add_heading("4.1 水质参数统计分析", level=2)
|
||||||
self._style_heading(h2, level=2)
|
self._style_heading(h2, level=2)
|
||||||
|
|
||||||
# 从工作目录的4_processed_data文件夹查找CSV文件
|
# 从工作目录查找 CSV 统计数据文件（根据管线模式选择不同目录）
|
||||||
work_dir_path = vis_dir.parent
|
work_dir_path = vis_dir.parent
|
||||||
processed_data_dir = work_dir_path / "5_Data_Cleaning"
|
if getattr(self, '_pipeline_mode', 'ml') == 'water_index':
|
||||||
|
stats_dir = work_dir_path / "10_WaterIndex_CSV"
|
||||||
if not processed_data_dir.exists():
|
else:
|
||||||
doc.add_paragraph(f"未找到数据处理目录: {processed_data_dir}")
|
stats_dir = work_dir_path / "5_Data_Cleaning"
|
||||||
|
|
||||||
|
if not stats_dir.exists():
|
||||||
|
alt_name = "10_WaterIndex_CSV" if self._pipeline_mode == 'water_index' else "5_Data_Cleaning"
|
||||||
|
doc.add_paragraph(f"未找到数据目录: {stats_dir}")
|
||||||
doc.add_page_break()
|
doc.add_page_break()
|
||||||
return start_figure_num
|
return start_figure_num
|
||||||
|
|
||||||
csv_files = list(processed_data_dir.glob("*.csv"))
|
csv_files = list(stats_dir.glob("*.csv"))
|
||||||
if not csv_files:
|
if not csv_files:
|
||||||
doc.add_paragraph(f"在 {processed_data_dir} 目录下未找到CSV统计数据文件。")
|
doc.add_paragraph(f"在 {stats_dir} 目录下未找到CSV统计数据文件。")
|
||||||
doc.add_page_break()
|
doc.add_page_break()
|
||||||
return start_figure_num
|
return start_figure_num
|
||||||
|
|
||||||
csv_path = csv_files[0] # 使用找到的第一个CSV文件
|
csv_path = csv_files[0] # 使用找到的第一个CSV文件
|
||||||
|
|
||||||
try:
|
try:
|
||||||
df_full = pd.read_csv(csv_path, sep=',')
|
if getattr(self, '_pipeline_mode', 'ml') == 'water_index':
|
||||||
df = df_full.iloc[:, 2:] # 跳过前两列（纬度、经度），直接用列号
|
# 水色指数模式：遍历所有 CSV，每个公式一行统计
|
||||||
|
stats_rows = []
|
||||||
# 自动统计剩余列
|
for cp in sorted(csv_files):
|
||||||
stats_data = []
|
try:
|
||||||
for i in range(df.shape[1]):
|
df_one = pd.read_csv(cp, sep=',')
|
||||||
col = df.columns[i]
|
# 水色指数 CSV: proj_x, proj_y, longitude, latitude, value
|
||||||
clean_col = str(col).strip()
|
# 取最后一列作为参数值
|
||||||
try:
|
val_col = df_one.columns[-1]
|
||||||
data = df.iloc[:, i].dropna()
|
vals = pd.to_numeric(df_one[val_col], errors='coerce').dropna()
|
||||||
if len(data) > 0:
|
if len(vals) > 0:
|
||||||
stats_data.append({
|
stats_rows.append({
|
||||||
'参数': clean_col,
|
'参数': Path(cp).stem,
|
||||||
'点位数': len(data),
|
'数量': len(vals),
|
||||||
'最大值': f"{data.max():.4f}",
|
'最小值': round(float(vals.min()), 4),
|
||||||
'最小值': f"{data.min():.4f}",
|
'最大值': round(float(vals.max()), 4),
|
||||||
'平均值': f"{data.mean():.4f}",
|
'平均值': round(float(vals.mean()), 4),
|
||||||
'标准差': f"{data.std():.4f}"
|
'标准差': round(float(vals.std(ddof=0)), 4) if len(vals) > 1 else 0,
|
||||||
})
|
})
|
||||||
except Exception as e:
|
except Exception:
|
||||||
print(f"跳过列 {col}: {e}")
|
pass
|
||||||
|
if stats_rows:
|
||||||
if stats_data:
|
df = pd.DataFrame(stats_rows)
|
||||||
# 创建统计表格
|
else:
|
||||||
|
doc.add_paragraph("水色指数 CSV 文件无法解析。")
|
||||||
|
doc.add_page_break()
|
||||||
|
return start_figure_num
|
||||||
|
else:
|
||||||
|
df_full = pd.read_csv(csv_path, sep=',')
|
||||||
|
df = df_full.iloc[:, 2:] # 跳过前两列（纬度、经度），直接用列号
|
||||||
|
|
||||||
|
if getattr(self, '_pipeline_mode', 'ml') == 'water_index':
|
||||||
|
# 水色指数模式：df 已是统计汇总表，直接写出
|
||||||
|
if not stats_rows:
|
||||||
|
raise ValueError("无水色指数统计数据")
|
||||||
table = doc.add_table(rows=1, cols=6, style='Table Grid')
|
table = doc.add_table(rows=1, cols=6, style='Table Grid')
|
||||||
hdr_cells = table.rows[0].cells
|
hdr_cells = table.rows[0].cells
|
||||||
hdr_cells[0].text = '参数'
|
for j, h in enumerate(['参数', '点位数', '最小值', '最大值', '平均值', '标准差']):
|
||||||
hdr_cells[1].text = '点位数'
|
hdr_cells[j].text = h
|
||||||
hdr_cells[2].text = '最大值'
|
header_map = {'参数': '参数', '数量': '点位数', '最小值': '最小值',
|
||||||
hdr_cells[3].text = '最小值'
|
'最大值': '最大值', '平均值': '平均值', '标准差': '标准差'}
|
||||||
hdr_cells[4].text = '平均值'
|
for row_dict in stats_rows:
|
||||||
hdr_cells[5].text = '标准差'
|
|
||||||
|
|
||||||
for stat in stats_data:
|
|
||||||
row_cells = table.add_row().cells
|
row_cells = table.add_row().cells
|
||||||
row_cells[0].text = stat['参数']
|
for j, (col_name, hdr_name) in enumerate(header_map.items()):
|
||||||
row_cells[1].text = str(stat['点位数'])
|
row_cells[j].text = str(row_dict.get(col_name, ''))
|
||||||
row_cells[2].text = stat['最大值']
|
stats_data = [{'参数': r['参数'], '点位数': r['数量']} for r in stats_rows]
|
||||||
row_cells[3].text = stat['最小值']
|
else:
|
||||||
row_cells[4].text = stat['平均值']
|
# ML 模式：逐列统计
|
||||||
row_cells[5].text = stat['标准差']
|
stats_data = []
|
||||||
|
for i in range(df.shape[1]):
|
||||||
|
col = df.columns[i]
|
||||||
|
clean_col = str(col).strip()
|
||||||
|
try:
|
||||||
|
data = df.iloc[:, i].dropna()
|
||||||
|
if len(data) > 0:
|
||||||
|
stats_data.append({
|
||||||
|
'参数': clean_col,
|
||||||
|
'点位数': len(data),
|
||||||
|
'最大值': f"{data.max():.4f}",
|
||||||
|
'最小值': f"{data.min():.4f}",
|
||||||
|
'平均值': f"{data.mean():.4f}",
|
||||||
|
'标准差': f"{data.std():.4f}"
|
||||||
|
})
|
||||||
|
except Exception as e:
|
||||||
|
print(f"跳过列 {col}: {e}")
|
||||||
|
|
||||||
|
if stats_data:
|
||||||
|
if getattr(self, '_pipeline_mode', 'ml') != 'water_index':
|
||||||
|
# ML 模式创建表格（水色指数模式表格已在上方创建）
|
||||||
|
table = doc.add_table(rows=1, cols=6, style='Table Grid')
|
||||||
|
hdr_cells = table.rows[0].cells
|
||||||
|
hdr_cells[0].text = '参数'
|
||||||
|
hdr_cells[1].text = '点位数'
|
||||||
|
hdr_cells[2].text = '最大值'
|
||||||
|
hdr_cells[3].text = '最小值'
|
||||||
|
hdr_cells[4].text = '平均值'
|
||||||
|
hdr_cells[5].text = '标准差'
|
||||||
|
for stat in stats_data:
|
||||||
|
row_cells = table.add_row().cells
|
||||||
|
row_cells[0].text = stat['参数']
|
||||||
|
row_cells[1].text = str(stat['点位数'])
|
||||||
|
row_cells[2].text = stat['最大值']
|
||||||
|
row_cells[3].text = stat['最小值']
|
||||||
|
row_cells[4].text = stat['平均值']
|
||||||
|
row_cells[5].text = stat['标准差']
|
||||||
|
|
||||||
else:
|
else:
|
||||||
doc.add_paragraph("CSV文件中未找到有效的参数数据。")
|
doc.add_paragraph("CSV文件中未找到有效的参数数据。")
|
||||||
@ -1687,39 +1779,41 @@ class WaterQualityReportGenerator:
|
|||||||
|
|
||||||
doc.add_paragraph() # 表格和热力图之间的空行
|
doc.add_paragraph() # 表格和热力图之间的空行
|
||||||
|
|
||||||
# 2. 添加相关性热力图（放在表格下方）
|
# 2. 添加相关性热力图（放在表格下方）—— 仅 ML 模式
|
||||||
h3 = doc.add_heading("4.2 水质参数相关性分析", level=2)
|
if getattr(self, '_pipeline_mode', 'ml') == 'ml':
|
||||||
self._style_heading(h3, level=2)
|
h3 = doc.add_heading("4.2 水质参数相关性分析", level=2)
|
||||||
heatmap_path = vis_dir / "correlation_heatmap.png"
|
self._style_heading(h3, level=2)
|
||||||
figure_num = start_figure_num
|
heatmap_path = vis_dir / "correlation_heatmap.png"
|
||||||
if heatmap_path.exists():
|
figure_num = start_figure_num
|
||||||
try:
|
if heatmap_path.exists():
|
||||||
# 使用统一的图像插入方法
|
try:
|
||||||
caption_text = f"图{figure_num} 水质参数相关性热力图"
|
caption_text = f"图{figure_num} 水质参数相关性热力图"
|
||||||
self._add_image_with_caption(doc, str(heatmap_path), caption_text, width=Inches(6.0))
|
self._add_image_with_caption(doc, str(heatmap_path), caption_text, width=Inches(6.0))
|
||||||
doc.add_paragraph("（颜色越深表示相关性越强，红色为正相关，蓝色为负相关）")
|
doc.add_paragraph("（颜色越深表示相关性越强，红色为正相关，蓝色为负相关）")
|
||||||
|
|
||||||
analysis_text = self._analyze_and_cache_image(
|
analysis_text = self._analyze_and_cache_image(
|
||||||
image_path=heatmap_path,
|
image_path=heatmap_path,
|
||||||
image_type="correlation_heatmap",
|
image_type="correlation_heatmap",
|
||||||
param="综合",
|
param="综合",
|
||||||
figure_num=figure_num,
|
figure_num=figure_num,
|
||||||
)
|
|
||||||
self._add_ai_analysis_paragraph(doc, analysis_text)
|
|
||||||
if all_image_analyses is not None:
|
|
||||||
all_image_analyses.append(
|
|
||||||
{
|
|
||||||
"figure_num": figure_num,
|
|
||||||
"param": "综合",
|
|
||||||
"image_type": "correlation_heatmap",
|
|
||||||
"image_name": heatmap_path.name,
|
|
||||||
"analysis": analysis_text,
|
|
||||||
}
|
|
||||||
)
|
)
|
||||||
except Exception as e:
|
self._add_ai_analysis_paragraph(doc, analysis_text)
|
||||||
doc.add_paragraph(f"[相关性热力图插入失败: {e}]")
|
if all_image_analyses is not None:
|
||||||
|
all_image_analyses.append(
|
||||||
|
{
|
||||||
|
"figure_num": figure_num,
|
||||||
|
"param": "综合",
|
||||||
|
"image_type": "correlation_heatmap",
|
||||||
|
"image_name": heatmap_path.name,
|
||||||
|
"analysis": analysis_text,
|
||||||
|
}
|
||||||
|
)
|
||||||
|
except Exception as e:
|
||||||
|
doc.add_paragraph(f"[相关性热力图插入失败: {e}]")
|
||||||
|
else:
|
||||||
|
doc.add_paragraph(f"[未找到相关性热力图: {heatmap_path.name}]")
|
||||||
else:
|
else:
|
||||||
doc.add_paragraph(f"[未找到相关性热力图: {heatmap_path.name}]")
|
doc.add_paragraph("（水色指数模式：参数相关性分析仅适用于机器学习预测流程，当前为非 ML 模式，已跳过。）")
|
||||||
|
|
||||||
# 热力图处理结束（无论成功/失败）更新进度条
|
# 热力图处理结束（无论成功/失败）更新进度条
|
||||||
try:
|
try:
|
||||||
|
|||||||
Reference in New Issue
Block a user