feat: update assessment portal

app/prediction.py

@@ -23,6 +23,7 @@ from .config import IMAGE_DIR, UPLOAD_DIR
 
 CHINESE_FONT_CANDIDATES = [
     "Noto Sans CJK SC",
+    "Noto Sans SC",
     "Noto Sans CJK JP",
     "Noto Sans CJK TC",
     "Source Han Sans SC",
@@ -32,6 +33,17 @@ CHINESE_FONT_CANDIDATES = [
     "Arial Unicode MS",
 ]
 
+CHINESE_FONT_FILES = [
+    "/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc",
+    "/usr/share/fonts/truetype/noto/NotoSansSC-Regular.ttf",
+    "/usr/share/fonts/truetype/noto/NotoSansCJK-Regular.ttc",
+    "/usr/local/share/fonts/NotoSansCJK-Regular.ttc",
+    "/mnt/c/Windows/Fonts/NotoSansSC-VF.ttf",
+    "/mnt/c/Windows/Fonts/msyh.ttc",
+    "/mnt/c/Windows/Fonts/simhei.ttf",
+    "/mnt/c/Windows/Fonts/simsun.ttc",
+]
+
 FEATURES = [
     "管材",
     "管径",
@@ -47,6 +59,7 @@ FEATURES = [
 ID_COLUMN = "管道编号"
 PIPE_AGE_COLUMN = "管龄"
 SUPPORTED_EXTENSIONS = {".csv", ".xls", ".xlsx"}
+CHINESE_FONT_PROP = None
 
 
 class PredictionError(Exception):
@@ -69,14 +82,34 @@ class PredictionArtifacts:
     analysis_text: str
 
 
-def configure_matplotlib_fonts() -> None:
+def configure_matplotlib_fonts():
+    for font_path in CHINESE_FONT_FILES:
+        path = Path(font_path)
+        if path.exists():
+            font_manager.fontManager.addfont(str(path))
+            prop = font_manager.FontProperties(fname=str(path))
+            rcParams["font.family"] = [prop.get_name(), "sans-serif"]
+            rcParams["font.sans-serif"] = [prop.get_name(), *CHINESE_FONT_CANDIDATES, "DejaVu Sans"]
+            rcParams["axes.unicode_minus"] = False
+            return prop
+
     available_fonts = {font.name for font in font_manager.fontManager.ttflist}
     selected_fonts = [font for font in CHINESE_FONT_CANDIDATES if font in available_fonts]
+    if selected_fonts:
+        rcParams["font.family"] = [selected_fonts[0], "sans-serif"]
     rcParams["font.sans-serif"] = selected_fonts + ["DejaVu Sans"]
     rcParams["axes.unicode_minus"] = False
+    if selected_fonts:
+        return font_manager.FontProperties(family=selected_fonts[0])
+    logging.warning("未找到中文字体，生成的图表中文可能无法显示。")
+    return None
 
 
-configure_matplotlib_fonts()
+CHINESE_FONT_PROP = configure_matplotlib_fonts()
+
+
+def chinese_font_kwargs() -> dict[str, Any]:
+    return {"fontproperties": CHINESE_FONT_PROP} if CHINESE_FONT_PROP else {}
 
 
 def load_model(model_path: str):
@@ -105,7 +138,7 @@ def safe_unlink(path: Path) -> None:
 def secure_upload_name(original_filename: str, run_id: str) -> tuple[str, str]:
     suffix = Path(original_filename).suffix.lower()
     if suffix not in SUPPORTED_EXTENSIONS:
-        raise PredictionError("不支持的格式，仅支持 CSV / XLS / XLSX")
+        raise PredictionError("不支持的格式，仅支持逗号分隔值文件或电子表格文件")
 
     safe_full_name = secure_filename(original_filename)
     safe_stem = Path(safe_full_name).stem if safe_full_name else ""
@@ -228,10 +261,14 @@ def render_importance_chart(values: np.ndarray, save_path: Path) -> None:
     fig, ax = plt.subplots(figsize=(9, max(3.0, 0.62 * n + 1.6)))
     cmap = LinearSegmentedColormap.from_list("brand", ["#7fb2e6", "#005EB8", "#0c4188"])
     colors = cmap(np.linspace(0.15, 1.0, n)) if n else None
-    bars = ax.barh(sorted_feats, sorted_vals, color=colors, height=0.66, edgecolor="white", linewidth=0.8, zorder=3)
+    y_pos = np.arange(n)
+    bars = ax.barh(y_pos, sorted_vals, color=colors, height=0.66, edgecolor="white", linewidth=0.8, zorder=3)
 
-    ax.set_xlabel("相对重要性", fontsize=11, color="#475569")
-    ax.set_title("模型输入因素重要性排序", fontsize=15, fontweight="bold", color="#0f172a", pad=14)
+    font_kwargs = chinese_font_kwargs()
+    ax.set_xlabel("相对重要性", fontsize=11, color="#475569", **font_kwargs)
+    ax.set_title("模型输入因素重要性排序", fontsize=15, fontweight="bold", color="#0f172a", pad=14, **font_kwargs)
+    ax.set_yticks(y_pos)
+    ax.set_yticklabels(sorted_feats, **font_kwargs)
     ax.grid(axis="x", color="#e2e8f0", linewidth=1, zorder=0)
     ax.set_axisbelow(True)
     for spine in ("top", "right", "left"):
@@ -239,6 +276,9 @@ def render_importance_chart(values: np.ndarray, save_path: Path) -> None:
     ax.spines["bottom"].set_color("#cbd5e1")
     ax.tick_params(axis="y", length=0, labelsize=11)
     ax.tick_params(axis="x", colors="#94a3b8", labelsize=9)
+    if CHINESE_FONT_PROP:
+        for label in [*ax.get_yticklabels(), *ax.get_xticklabels()]:
+            label.set_fontproperties(CHINESE_FONT_PROP)
 
     max_val = float(sorted_vals.max()) if n else 0.0
     for bar, value in zip(bars, sorted_vals):
@@ -251,6 +291,7 @@ def render_importance_chart(values: np.ndarray, save_path: Path) -> None:
             fontsize=10,
             fontweight="bold",
             color="#1e293b",
+            **font_kwargs,
         )
     if max_val > 0:
         ax.set_xlim(0, max_val * 1.18)
@@ -352,12 +393,17 @@ def render_survival_chart(df: pd.DataFrame, curves, image_path: Path) -> tuple[l
         )
         plt.step(times, probs, where="post", linewidth=2, label=pipe_id)
 
-    plt.xlabel("预测时间轴（年）")
-    plt.ylabel("生存概率")
-    plt.title("预测分析图")
+    font_kwargs = chinese_font_kwargs()
+    plt.xlabel("预测时间轴（年）", **font_kwargs)
+    plt.ylabel("生存概率", **font_kwargs)
+    plt.title("预测分析图", **font_kwargs)
     plt.grid(alpha=0.18)
     if len(summary_rows) <= 12:
-        plt.legend(loc="best", fontsize=8)
+        plt.legend(loc="best", fontsize=8, prop=CHINESE_FONT_PROP)
+    ax = plt.gca()
+    if CHINESE_FONT_PROP:
+        for label in [*ax.get_xticklabels(), *ax.get_yticklabels()]:
+            label.set_fontproperties(CHINESE_FONT_PROP)
     plt.tight_layout()
     plt.savefig(image_path, dpi=160, bbox_inches="tight")
     plt.close()
@@ -370,11 +416,22 @@ def write_prediction_workbook(
     summary_rows: list[dict[str, Any]],
     summary_sheet_rows: list[dict[str, Any]],
 ) -> None:
-    with pd.ExcelWriter(excel_path, engine="xlsxwriter") as writer:
+    sample_data_rows: list[dict[str, Any]] = []
+    for i, curve in enumerate(curves):
+        times = [float(x) for x in list(curve.x)]
+        probs = [float(y) for y in list(curve.y)]
+        pipe_id = summary_rows[i]["pipe_id"]
+        for time, probability in zip(times, probs):
+            sample_data_rows.append(
+                {
+                    "管道编号": pipe_id,
+                    "样本序号": i + 1,
+                    "时间（年）": time,
+                    "生存概率": probability,
+                    "风险概率": 1 - probability,
+                }
+            )
+
+    with pd.ExcelWriter(excel_path, engine="openpyxl") as writer:
         pd.DataFrame(summary_sheet_rows).to_excel(writer, sheet_name="结果摘要", index=False)
-        for i, curve in enumerate(curves):
-            times = [float(x) for x in list(curve.x)]
-            probs = [float(y) for y in list(curve.y)]
-            pipe_id = summary_rows[i]["pipe_id"]
-            out_df = pd.DataFrame({"时间（年）": times, f"{pipe_id}生存概率": probs})
-            out_df.to_excel(writer, sheet_name=f"样本{i+1}", index=False)
+        pd.DataFrame(sample_data_rows).to_excel(writer, sheet_name="样本数据", index=False)