Update src/streamlit_app.py

src/streamlit_app.py

@@ -4,92 +4,116 @@ import numpy as np
 import pandas as pd
 
 # ------------------------------
-# Load model & scaler
+# 1. Load Model & Scaler
 # ------------------------------
 MODEL_PATH = "src/voting_model.joblib"
 SCALER_PATH = "src/scaler.joblib"
 
 @st.cache_resource
-def load_model():
+def load_artifacts():
     try:
         model = joblib.load(MODEL_PATH)
         scaler = joblib.load(SCALER_PATH)
         return model, scaler
     except Exception as e:
-        st.error(f"Error loading model or scaler: {e}")
+        st.error(f"Error loading model: {e}")
         return None, None
 
-model, scaler = load_model()
-
-st.title("🧠 Stress Detection Model")
-st.write("Enter the required parameters and get the prediction.")
+model, scaler = load_artifacts()
 
 # ------------------------------
-# Input feature names
-# These MUST match the training dataset exactly
+# 2. Feature Engineering Function
 # ------------------------------
-FEATURES = [
-    "Column fy Mpa",
-    "Beam fy Mpa",
-    "Columns 1-3 I mm4*10^6",
-    "Columns 4-6 I mm4*10^6",
-    "Columns 1-3 A mm2",
-    "Columns 4-6 A mm2",
-    "Beam I mm4*10^6",
-    "Spans",
-    "Number of floors",
-    "Floor height m",
-    "Span width m",
-    "LLRS tributary width m",
-    "Floor mass kg",
-    "Facade Load kN/m",
-    "PGA g",
-    "Magnitude",
-    "Distance to fault km",
-    "Period s",
-    "Final Dead Load",
-    "Final Live Load",
-    "soil_class__B",
-    "soil_class__C",
-    "stiffness_low",
-    "stiffness_high",
-    "stiffness_diff",
-    "strength_ratio",
-    "total_height",
-    "total_width",
-    "slenderness",
-    "total_area_low",
-    "seismic_power",
-    "fault_attenuation",
-    "total_mass",
-    "base_shear"
-]
+def engineer_features(df):
+    data = df.copy()
+    epsilon = 1e-6  
+    
+    data['stiffness_low'] = data['Columns 1-3 I mm4*10^6'] / (data['Floor height m']**3 + epsilon)
+    data['stiffness_high'] = data['Columns 4-6 I mm4*10^6'] / (data['Floor height m']**3 + epsilon)
+    data['stiffness_diff'] = data['stiffness_low'] - data['stiffness_high']
+
+    data['strength_ratio'] = data['Column fy Mpa'] / (data['Beam fy Mpa'] + epsilon)
+
+    data['total_height'] = data['Number of floors'] * data['Floor height m']
+    data['total_width'] = data['Spans'] * data['Span width m']
+    data['slenderness'] = data['total_height'] / (data['total_width'] + epsilon)
+    data['total_area_low'] = data['Columns 1-3 A mm2'] * (data['Spans'] + 1)
+
+    data['seismic_power'] = data['PGA g'] * data['Magnitude']
+    data['fault_attenuation'] = data['Magnitude'] / np.log1p(data['Distance to fault km'])
+
+    data['total_mass'] = data['Floor mass kg'] * data['Number of floors']
+    data['base_shear'] = data['total_mass'] * data['PGA g']
+    
+    data = data.replace([np.inf, -np.inf], 0)
+    return data
 
 # ------------------------------
-# User input section
+# 3. User Input Section
 # ------------------------------
-inputs = {}
-st.subheader("📌 Input Features")
+st.title("🏢 Seismic Building Safety Prediction")
+st.write("""
+This AI model predicts the **Maximum Interstorey Drift (mm)** a building might experience during an earthquake.
+Lower drift values generally indicate safer buildings.
+""")
 
-for f in FEATURES:
-    inputs[f] = st.number_input(f, value=0.0)
+RAW_INPUTS = [
+    "Column fy Mpa", "Beam fy Mpa", 
+    "Columns 1-3 I mm4*10^6", "Columns 4-6 I mm4*10^6",
+    "Columns 1-3 A mm2", "Columns 4-6 A mm2", "Beam I mm4*10^6",
+    "Spans", "Number of floors", "Floor height m", "Span width m",
+    "LLRS tributary width m", "Floor mass kg", "Facade Load kN/m",
+    "PGA g", "Magnitude", "Distance to fault km", "Period s",
+    "Final Dead Load", "Final Live Load"
+]
 
-# Convert to dataframe
-input_df = pd.DataFrame([inputs])
+input_data = {}
+
+with st.form("input_form"):
+    c1, c2 = st.columns(2)
+    
+    for i, col_name in enumerate(RAW_INPUTS):
+        if i % 2 == 0:
+            with c1:
+                input_data[col_name] = st.number_input(col_name, value=0.0, format="%.2f")
+        else:
+            with c2:
+                input_data[col_name] = st.number_input(col_name, value=0.0, format="%.2f")
+
+    soil_class = st.selectbox("Soil Class", ["A (Other)", "B", "C"])
+    input_data['soil_class__B'] = 1.0 if soil_class == "B" else 0.0
+    input_data['soil_class__C'] = 1.0 if soil_class == "C" else 0.0
+
+    submitted = st.form_submit_button("Predict Max Drift")
 
 # ------------------------------
-# Prediction
+# 4. Prediction Logic
 # ------------------------------
-if st.button("Predict"):
+if submitted:
     if model is None or scaler is None:
-        st.error("Model is not loaded!")
+        st.error("Model could not be loaded!")
     else:
         try:
-            scaled = scaler.transform(input_df)
-            pred = model.predict(scaled)[0]
-            label = "Stress" if pred == 1 else "No Stress"
+            df_raw = pd.DataFrame([input_data])
+
+            df_engineered = engineer_features(df_raw)
+
+            X_scaled = scaler.transform(df_engineered)
+
+            log_pred = model.predict(X_scaled)
 
-            st.success(f"### 🎯 Prediction: **{label}**")
+            real_pred = np.expm1(log_pred)[0]
+            
+            st.divider()
+            st.success(f"### 🎯 Predicted Drift: **{real_pred:.2f} mm**")
+            
+            if real_pred < 10:
+                st.info("Risk: 🟢 Low (Safe)")
+            elif real_pred < 50:
+                st.warning("Risk: 🟡 Medium (Potential Damage)")
+            else:
+                st.error("Risk: 🔴 High (Collapse Hazard)")
 
         except Exception as e:
-            st.error(f"Processing error: {e}")
+            st.error(f"Calculation error: {e}")
+            st.write("Please ensure all values are entered correctly.")