Update app.py

app.py

@@ -3,31 +3,60 @@ import pandas as pd
 import joblib
 from huggingface_hub import hf_hub_download
 
-# ----------------------------------------
-# Page Configuration
-# ----------------------------------------
+# ==========================================================
+# PAGE CONFIGURATION
+# ==========================================================
 
 st.set_page_config(
-    page_title="Predictive Maintenance",
+    page_title="Predictive Maintenance System",
     page_icon="🚗",
     layout="centered"
 )
 
+# ==========================================================
+# TITLE
+# ==========================================================
+
 st.title("🚗 Predictive Maintenance System")
+
 st.write(
     """
-    This application predicts whether an engine requires maintenance
-    based on its sensor readings using the trained AdaBoost model.
-    """
+This application predicts whether an engine requires maintenance
+based on its sensor readings using a trained **AdaBoost Classifier**.
+"""
 )
 
-# ----------------------------------------
-# Load Model from Hugging Face
-# ----------------------------------------
+# ==========================================================
+# SIDEBAR
+# ==========================================================
+
+st.sidebar.title("📌 Project Information")
+
+st.sidebar.markdown("""
+### 🤖 Model
+AdaBoost Classifier
+
+### 🎯 Model Accuracy
+**66.75%**
+
+### 📊 Dataset
+Predictive Maintenance Dataset
+
+### 🚀 Deployment
+Hugging Face Spaces
+
+### 👩‍💻 Developed By
+Barnali Nayak
+""")
+
+# ==========================================================
+# LOAD MODEL
+# ==========================================================
 
 MODEL_REPO = "killswitch009/predictive-maintenance-model"
 MODEL_FILE = "best_model.pkl"
 
+
 @st.cache_resource
 def load_model():
     model_path = hf_hub_download(
@@ -36,21 +65,31 @@ def load_model():
     )
     return joblib.load(model_path)
 
-#model = load_model()
 
 try:
     model = load_model()
     st.success("✅ Model loaded successfully!")
 except Exception as e:
-    st.error(f"Error loading model: {e}")
+    st.error(f"Unable to load model.\n\n{e}")
     st.stop()
 
-# ----------------------------------------
-# User Inputs
-# ----------------------------------------
+# ==========================================================
+# USER INPUTS
+# ==========================================================
 
 st.header("Enter Engine Sensor Values")
 
+st.info("""
+### Example Sensor Values
+
+- Engine RPM : **700**
+- Lub Oil Pressure : **2.5**
+- Fuel Pressure : **12**
+- Coolant Pressure : **3.2**
+- Lub Oil Temperature : **84**
+- Coolant Temperature : **82**
+""")
+
 engine_rpm = st.number_input(
     "Engine RPM",
     min_value=0,
@@ -60,59 +99,87 @@ engine_rpm = st.number_input(
 lub_pressure = st.number_input(
     "Lub Oil Pressure",
     min_value=0.0,
-    value=3.2
+    value=3.20
 )
 
 fuel_pressure = st.number_input(
     "Fuel Pressure",
     min_value=0.0,
-    value=6.5
+    value=6.50
 )
 
 coolant_pressure = st.number_input(
     "Coolant Pressure",
     min_value=0.0,
-    value=2.3
+    value=2.30
 )
 
 lub_temp = st.number_input(
     "Lub Oil Temperature",
     min_value=0.0,
-    value=77.0
+    value=77.00
 )
 
 coolant_temp = st.number_input(
     "Coolant Temperature",
     min_value=0.0,
-    value=78.0
+    value=78.00
 )
 
-# ----------------------------------------
-# Prediction
-# ----------------------------------------
+# ==========================================================
+# PREDICTION
+# ==========================================================
 
-if st.button("Predict Engine Condition"):
+if st.button("🔍 Predict Engine Condition", use_container_width=True):
 
     input_data = pd.DataFrame({
-        "Engine rpm":[engine_rpm],
-        "Lub oil pressure":[lub_pressure],
-        "Fuel pressure":[fuel_pressure],
-        "Coolant pressure":[coolant_pressure],
-        "lub oil temp":[lub_temp],
-        "Coolant temp":[coolant_temp]
+        "Engine rpm": [engine_rpm],
+        "Lub oil pressure": [lub_pressure],
+        "Fuel pressure": [fuel_pressure],
+        "Coolant pressure": [coolant_pressure],
+        "lub oil temp": [lub_temp],
+        "Coolant temp": [coolant_temp]
     })
 
     prediction = model.predict(input_data)[0]
     probability = model.predict_proba(input_data)[0]
 
-    st.subheader("Prediction Result")
+    st.divider()
+
+    st.header("Prediction Result")
 
     if prediction == 1:
         st.error("⚠️ Engine Requires Maintenance")
+        st.warning(
+            "The sensor readings indicate that the engine may require maintenance. "
+            "A detailed inspection is recommended."
+        )
     else:
-        st.success("✅ Engine Operating Normally")
+        st.success("✅ Engine is Operating Normally")
+        st.balloons()
+
+    st.divider()
+
+    st.header("Prediction Confidence")
+
+    st.metric(
+        "Healthy Engine Probability",
+        f"{probability[0]*100:.2f}%"
+    )
+    st.progress(float(probability[0]))
+
+    st.metric(
+        "Maintenance Required Probability",
+        f"{probability[1]*100:.2f}%"
+    )
+    st.progress(float(probability[1]))
+
+# ==========================================================
+# FOOTER
+# ==========================================================
 
-    st.write("### Prediction Confidence")
+st.markdown("---")
 
-    st.write(f"Normal : {probability[0]*100:.2f}%")
-    st.write(f"Maintenance Required : {probability[1]*100:.2f}%")
+st.caption(
+    "Developed by **Brijesh Pandey** | Python • Scikit-learn • Streamlit • Hugging Face"
+)