Update app.py

app.py

@@ -1,140 +1,54 @@
+%%writefile mlops/deployment/app.py
 import streamlit as st
 import pandas as pd
-import joblib
 from huggingface_hub import hf_hub_download
+import joblib
 
-# --------------------------------------------------
-# Page Configuration
-# --------------------------------------------------
-st.set_page_config(
-    page_title="Predictive Maintenance | Engine Health",
-    page_icon="🛠️",
-    layout="centered"
-)
-
-# --------------------------------------------------
-# Load Model (cached)
-# --------------------------------------------------
-@st.cache_resource
-def load_model():
-    model_path = hf_hub_download(
-        repo_id="csankaran3/engine-condition-prediction",
-        filename="best_engine_condition_prediction_model_v1.joblib"
-    )
-    return joblib.load(model_path)
-
-model = load_model()
-
-# --------------------------------------------------
-# Header
-# --------------------------------------------------
-st.title("🛠️ Predictive Maintenance – Engine Condition")
-st.markdown(
-    """
-    This **internal diagnostic tool** helps automobile companies  
-    predict **engine health (Active / Faulty)** using real-time sensor values.
-    """
-)
-
-st.divider()
-
-# --------------------------------------------------
-# Sidebar – Sensor Inputs
-# --------------------------------------------------
-st.sidebar.header("📊 Sensor Inputs")
-
-engine_rpm = st.sidebar.number_input(
-    "Engine RPM",
-    min_value=0.0,
-    value=1150.0,
-    step=10.0,
-    help="Rotational speed of the engine"
-)
-
-lub_oil_pressure = st.sidebar.number_input(
-    "Lub Oil Pressure (kPa)",
-    min_value=0.0,
-    value=3.63,
-    step=0.01
-)
+# Download the model from the Model Hub
+model_path = hf_hub_download(repo_id="csankaran3/engine-condition-prediction", filename="best_engine_condition_prediction_model_v1.joblib")
 
-fuel_pressure = st.sidebar.number_input(
-    "Fuel Pressure (kPa)",
-    min_value=0.0,
-    value=10.57,
-    step=0.01
-)
+# Load the model
+model = joblib.load(model_path)
 
-coolant_pressure = st.sidebar.number_input(
-    "Coolant Pressure (kPa)",
-    min_value=0.0,
-    value=7.48,
-    step=0.01
-)
+# Streamlit UI for Customer Churn Prediction
+st.set_page_config(page_title="Predictive Maintenance", layout="centered")
+st.title("Predictive Maintenance - Engine fault prediction application")
+st.write("This App is an internal tool for automobie companies to predict engine condition (Active / Faulty) based on the sensor values.")
+st.subheader("Kindly enter the sensor details to check whether engine condition is active or faulty.")
+st.subheader("📊 Sensor Inputs")
 
-lub_oil_temp = st.sidebar.number_input(
-    "Lub Oil Temperature (°C)",
-    min_value=0.0,
-    value=89.58,
-    step=0.01
-)
+# Setting the display value
+engine_rpm = st.number_input("Engine RPM", min_value=0.0, value=1150.0, step=10.0)
+lub_oil_pressure = st.number_input("Lub Oil Pressure (kPa)", min_value=0.0, value=3.63, step=0.01)
+fuel_pressure = st.number_input("Fuel Pressure (kPa)", min_value=0.0, value=10.57, step=0.01)
+coolant_pressure = st.number_input("Coolant Pressure (kPa)", min_value=0.0, value=7.48, step=0.01)
+lub_oil_temp = st.number_input("Lub Oil Temperature (°C)", min_value=0.32, value=89.58, step=0.01)
+coolant_temp = st.number_input("Coolant Temperature (°C)", min_value=0.67, value=128.60, step=0.01)
 
-coolant_temp = st.sidebar.number_input(
-    "Coolant Temperature (°C)",
-    min_value=0.0,
-    value=128.60,
-    step=0.01
-)
 
-# --------------------------------------------------
-# Prepare Input Data
-# --------------------------------------------------
+# Convert inputs to match model training
 input_data = pd.DataFrame([{
-    "Engine rpm": engine_rpm,
-    "Lub oil pressure": lub_oil_pressure,
-    "Fuel pressure": fuel_pressure,
-    "Coolant pressure": coolant_pressure,
-    "lub oil temp": lub_oil_temp,
-    "Coolant temp": coolant_temp
+        'Engine rpm': engine_rpm,
+        'Lub oil pressure': lub_oil_pressure,
+        'Fuel pressure': fuel_pressure,
+        'Coolant pressure': coolant_pressure,
+        'lub oil temp': lub_oil_temp,
+        'Coolant temp': coolant_temp
 }])
 
-# --------------------------------------------------
-# Prediction Section
-# --------------------------------------------------
-st.subheader("🔍 Engine Condition Prediction")
-
+# Set the classification threshold
 classification_threshold = 0.45
 
+# Predict button
 if st.button("🚀 Predict Engine Condition", use_container_width=True):
-    with st.spinner("Analyzing sensor data..."):
-        prediction_proba = model.predict_proba(input_data)[0, 1]
-        prediction = int(prediction_proba >= classification_threshold)
-
-    st.divider()
-
-    col1, col2 = st.columns(2)
-
-    with col1:
-        st.metric(
-            label="Fault Probability",
-            value=f"{prediction_proba:.2%}"
-        )
-
-    with col2:
-        st.metric(
-            label="Threshold",
-            value=f"{classification_threshold:.0%}"
-        )
-
-    st.divider()
-
-    if prediction == 1:
+    prediction_proba = model.predict_proba(input_data)[0, 1]
+    prediction = (prediction_proba >= classification_threshold).astype(int)
+    result = "Active" if prediction == 1 else "Faulty"
+    if result == "Active":
         st.success(
-            "✅ **Engine Status: ACTIVE**\n\n"
-            "The engine is operating within safe parameters."
+            f"Engine condition prediction completed!.. **✅ **Engine Status: ACTIVE**\n\n The engine is operating within safe parameters."
         )
     else:
         st.error(
-            "⚠️ **Engine Status: FAULTY**\n\n"
-            "Potential fault detected. Immediate inspection recommended."
+            f"Engine condition prediction completed!.. **⚠️ **Engine Status: FAULTY**\n\n Potential fault detected. Immediate inspection recommended."
         )