Upload folder using huggingface_hub

Dockerfile

@@ -1,10 +1,7 @@
 FROM python:3.10-slim
-
 WORKDIR /app
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
-
 COPY app.py .
-
 EXPOSE 7860
 CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]

README.md

@@ -1,5 +1,4 @@
 ---
----
 title: Predictive Maintenance
 emoji: 🔧
 colorFrom: blue
@@ -12,7 +11,6 @@ pinned: false
 
 ## Predictive Maintenance – Engine Failure Prediction
 
-Streamlit app deployed on **Hugging Face Spaces** using Docker.
+Streamlit app deployed on Hugging Face Spaces.
 
 Author: Sharley Kulkarni
-

app.py

@@ -1,30 +1,112 @@
+
 import streamlit as st
 import pandas as pd
+import numpy as np
 import joblib
 from huggingface_hub import hf_hub_download
+import json
+
+# =============================================================================
+# STREAMLIT CONFIG
+# =============================================================================
 
-st.set_page_config(page_title="Predictive Maintenance", layout="wide")
+st.set_page_config(
+    page_title="Predictive Maintenance",
+    layout="wide",
+    page_icon="🛠️"
+)
+
+# =============================================================================
+# LOAD MODEL
+# =============================================================================
 
 @st.cache_resource
-def load_model():
-    repo = "SharleyK/predictive-maintenance-model"
-    model = joblib.load(hf_hub_download(repo, "best_model.pkl"))
-    scaler = joblib.load(hf_hub_download(repo, "scaler.pkl"))
-    return model, scaler
+def load_artifacts():
+    repo_id = "SharleyK/PredictiveMaintenance"
+
+    model = joblib.load(hf_hub_download(repo_id, "best_model.pkl"))
+    scaler = joblib.load(hf_hub_download(repo_id, "scaler.pkl"))
+    metadata = json.load(open(hf_hub_download(repo_id, "metadata.json")))
+
+    return model, scaler, metadata
+
+
+model, scaler, metadata = load_artifacts()
+MODEL_NAME = metadata.get("model_name", "Unknown Model")
 
-model, scaler = load_model()
+# =============================================================================
+# FEATURE ENGINEERING
+# =============================================================================
 
-st.title("Predictive Maintenance - Engine Failure Prediction")
+def engineer_features(df):
+    df = df.copy()
 
-engine_rpm = st.slider("Engine RPM", 100, 2500, 800)
-lub_oil_pressure = st.slider("Lub Oil Pressure", 0.0, 8.0, 3.0)
-fuel_pressure = st.slider("Fuel Pressure", 0.0, 22.0, 6.0)
-coolant_pressure = st.slider("Coolant Pressure", 0.0, 8.0, 2.5)
-lub_oil_temp = st.slider("Lub Oil Temp", 70.0, 95.0, 80.0)
-coolant_temp = st.slider("Coolant Temp", 60.0, 200.0, 85.0)
+    df["temp_pressure_ratio"] = df["coolant_temp"] / (df["coolant_pressure"] + 1e-6)
+    df["oil_temp_pressure_ratio"] = df["lub_oil_temp"] / (df["lub_oil_pressure"] + 1e-6)
 
-if st.button("Predict"):
-    X = pd.DataFrame([{
+    df["pressure_diff_oil_coolant"] = df["lub_oil_pressure"] - df["coolant_pressure"]
+    df["pressure_diff_fuel_oil"] = df["fuel_pressure"] - df["lub_oil_pressure"]
+
+    df["temp_diff_oil_coolant"] = df["lub_oil_temp"] - df["coolant_temp"]
+
+    df["avg_temp"] = (df["lub_oil_temp"] + df["coolant_temp"]) / 2
+    df["avg_pressure"] = (
+        df["lub_oil_pressure"] +
+        df["fuel_pressure"] +
+        df["coolant_pressure"]
+    ) / 3
+
+    df["high_rpm"] = (df["engine_rpm"] > 934).astype(int)
+    df["high_temp"] = (df["coolant_temp"] > 82.9).astype(int)
+    df["operating_stress"] = df["high_rpm"] * df["high_temp"]
+    df["low_oil_pressure"] = (df["lub_oil_pressure"] < 2.52).astype(int)
+
+    return df
+
+# =============================================================================
+# PREDICTION
+# =============================================================================
+
+def predict(df):
+    df_eng = engineer_features(df)
+    X_scaled = scaler.transform(df_eng)
+    pred = model.predict(X_scaled)[0]
+
+    if hasattr(model, "predict_proba"):
+        confidence = model.predict_proba(X_scaled)[0][pred]
+    else:
+        confidence = 0.85
+
+    return pred, confidence
+
+# =============================================================================
+# UI
+# =============================================================================
+
+st.title("🛠️ Predictive Maintenance – Engine Failure Prediction")
+st.caption("AI-powered real-time engine health assessment")
+
+st.markdown(f"""
+**Model:** {MODEL_NAME}  
+**Accuracy:** 66.68% | **Recall:** 87.13%
+""")
+
+st.divider()
+
+col1, col2 = st.columns(2)
+
+with col1:
+    engine_rpm = st.slider("Engine RPM", 50, 2500, 800, step=10)
+    lub_oil_pressure = st.slider("Lub Oil Pressure", 0.0, 8.0, 3.3)
+    fuel_pressure = st.slider("Fuel Pressure", 0.0, 22.0, 6.5)
+
+with col2:
+    coolant_pressure = st.slider("Coolant Pressure", 0.0, 8.0, 2.3)
+    lub_oil_temp = st.slider("Lub Oil Temp (°C)", 70.0, 95.0, 77.0)
+    coolant_temp = st.slider("Coolant Temp (°C)", 60.0, 200.0, 78.0)
+
+if st.button("Predict Engine Condition"):
+    df = pd.DataFrame([{
         "engine_rpm": engine_rpm,
         "lub_oil_pressure": lub_oil_pressure,
         "fuel_pressure": fuel_pressure,
@@ -33,10 +115,11 @@ if st.button("Predict"):
         "coolant_temp": coolant_temp
     }])
 
-    X_scaled = scaler.transform(X)
-    pred = model.predict(X_scaled)[0]
+    pred, conf = predict(df)
 
     if pred == 1:
-        st.error("Engine Failure Detected")
+        st.error("🚨 FAULTY ENGINE DETECTED")
     else:
-        st.success("Engine Operating Normally")
+        st.success("✅ ENGINE OPERATING NORMALLY")
+
+    st.metric("Confidence", f"{conf*100:.1f}%")