Update app.py

app.py

@@ -16,7 +16,7 @@ model = joblib.load("typhoidguard_model_reduced.pkl")
 # Risk & Agentic Logic
 def predict_and_generate(name, age, gender, platelets, hb, duration, calcium, potassium):
 
-    # Prepare input
+    # 1️⃣ Prepare input DataFrame
     data = pd.DataFrame([{
         "Platelet Count": platelets,
         "Age": age,
@@ -27,17 +27,14 @@ def predict_and_generate(name, age, gender, platelets, hb, duration, calcium, po
         "Gender": gender
     }])
 
-    # 1️⃣ Model probability
-    # If your model is a pipeline: classifier is last step
-    try:
-        prob = model.predict_proba(data)[0][1]  # probability of treatment failure
-    except:
-        # fallback
-        prob = 0.0
+    # 2️⃣ Pass data through preprocessor
+    X_processed = model.named_steps["preprocessor"].transform(data)
 
+    # 3️⃣ Get probability from classifier
+    prob = model.named_steps["classifier"].predict_proba(X_processed)[0][1]  # probability of treatment failure
     prob_pct = round(prob * 100, 2)
 
-    # 2️⃣ Risk label
+    # 4️⃣ Risk label based on probability
     if prob > 0.65:
         risk_label = "🔴 HIGH RISK"
         color = "#d62828"
@@ -48,20 +45,29 @@ def predict_and_generate(name, age, gender, platelets, hb, duration, calcium, po
         risk_label = "🟢 LOW RISK"
         color = "#2a9d8f"
 
-    # 3️⃣ Agent triage logic (like your local function)
+    # 5️⃣ Agentic triage logic (include critical thresholds)
     patient_data = data.iloc[0].to_dict()
-    if (prob > 0.65 and patient_data.get("Platelet Count", 999999) < 150000):
+    low_platelets = patient_data.get("Platelet Count", 999999) < 150000
+    low_hb = patient_data.get("Hemoglobin (g/dL)", 999) < 10
+
+    if prob > 0.65 or low_platelets or low_hb:
         recommendation = "Immediate referral to secondary care facility recommended. Close monitoring required."
+        risk_label = "🔴 HIGH RISK"
+        color = "#d62828"
     elif 0.35 <= prob <= 0.65:
         recommendation = "Close monitoring advised. Repeat blood tests within 48 hours."
+        risk_label = "🟡 MODERATE RISK"
+        color = "#f4a261"
     else:
         recommendation = "Continue standard treatment protocol."
+        risk_label = "🟢 LOW RISK"
+        color = "#2a9d8f"
 
-    # 4️⃣ Top clinical risk factors
+    # 6️⃣ Top clinical factors
     factors = []
-    if platelets < 150000:
+    if low_platelets:
         factors.append("Low Platelet Count")
-    if hb < 10:
+    if low_hb:
         factors.append("Low Hemoglobin")
     if duration > 7:
         factors.append("Prolonged Treatment Duration")
@@ -70,7 +76,7 @@ def predict_and_generate(name, age, gender, platelets, hb, duration, calcium, po
     if potassium < 3.5 or potassium > 5.0:
         factors.append("Abnormal Potassium")
 
-    # 5️⃣ Construct HTML response
+    # 7️⃣ Construct HTML
     explanation = f"""
     <div style="font-family:Arial; padding:15px;">
         <h2 style="color:{color};">Patient: {name}</h2>
@@ -86,7 +92,6 @@ def predict_and_generate(name, age, gender, platelets, hb, duration, calcium, po
     """
 
     return explanation
-
 # PDF Generation
 def generate_pdf(name, age, gender, platelets, hb, duration, calcium, potassium):