Update app.py

app.py

@@ -14,7 +14,7 @@ MODEL_PATH = "models/svm_pipeline.joblib"
 BG_PATH    = "data/bg.csv"
 
 # 模型最终需要的 8 个特征（顺序必须与训练一致）
-FEATURES = ["ALB", "TP", "TBA", "AST/ALT", "CREA", "PNI", "AAPR", "DBIL"]
+FEATURES = ["ALB", "TP", "TBA", "AST_ALT", "CREA", "PNI", "AAPR", "DBIL"]
 
 # 加载模型与背景
 pipeline = joblib.load(MODEL_PATH)
@@ -52,7 +52,7 @@ def _render_force_plot(base_val: float, shap_1d: np.ndarray, feat_1d: np.ndarray
     # ——将特征值按需四舍五入，减少标签长度（可根据需要微调每列小数位）
     feat = np.asarray(feat_1d, dtype=float).copy()
     round_map = {
-        "ALB": 2, "TP": 2, "TBA": 2, "AST/ALT": 2, "CREA": 1, "PNI": 1, "AAPR": 3, "DBIL": 1
+        "ALB": 2, "TP": 2, "TBA": 2, "AST_ALT": 2, "CREA": 1, "PNI": 1, "AAPR": 3, "DBIL": 1
     }
     feat_rounded = [
         np.round(val, round_map.get(name, 2)) for val, name in zip(feat, fnames)
@@ -78,20 +78,20 @@ def _coerce_float(x):
     return float(x) if x is not None and x != "" else np.nan
 
 
-def predict_and_explain(ALB, TP, TBA, AST/ALT, CREA, LYM, ALP, DBIL, nsamples=200):
+def predict_and_explain(ALB, TP, TBA, AST_ALT, CREA, LYM, ALP, DBIL, nsamples=200):
     status = []
     try:
         # ---- 1) 取数并校验 ----
         ALB     = _coerce_float(ALB)
         TP      = _coerce_float(TP)
         TBA     = _coerce_float(TBA)
-        AST/ALT = _coerce_float(AST/ALT)
+        AST_ALT = _coerce_float(AST_ALT)
         CREA    = _coerce_float(CREA)
         LYM     = _coerce_float(LYM)
         ALP     = _coerce_float(ALP)
         DBIL    = _coerce_float(DBIL)
 
-        vals = [ALB, TP, TBA, AST/ALT, CREA, LYM, ALP, DBIL]
+        vals = [ALB, TP, TBA, AST_ALT, CREA, LYM, ALP, DBIL]
         if any(np.isnan(v) for v in vals):
             return None, None, "Error: 所有输入必须为数值且不可缺失。"
 
@@ -106,7 +106,7 @@ def predict_and_explain(ALB, TP, TBA, AST/ALT, CREA, LYM, ALP, DBIL, nsamples=20
         status.append(f"Derived: PNI={PNI:.1f}, AAPR={AAPR:.3f}")
 
         # ---- 3) 组装最终 8 特征并预测 ----
-        x_row = np.array([[ALB, TP, TBA, AST/ALT, CREA, PNI, AAPR, DBIL]], dtype=np.float64)
+        x_row = np.array([[ALB, TP, TBA, AST_ALT, CREA, PNI, AAPR, DBIL]], dtype=np.float64)
 
         if hasattr(pipeline, "predict_proba"):
             classes_ = getattr(pipeline, "classes_", None)
@@ -227,4 +227,4 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()