Deploy Docker-based Streamlit app

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY app.py .
+
+EXPOSE 8501
+
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,46 @@
+import pandas as pd
+import streamlit as st
+import joblib
+from huggingface_hub import hf_hub_download
+
+MODEL_REPO = "karthick2613/capstone_predictive_maintenance_model"
+
+st.set_page_config(page_title="Predictive Maintenance", layout="centered")
+
+st.title("🚗 Predictive Maintenance - Engine Failure Detection")
+st.write("Enter sensor readings to predict whether maintenance is required.")
+
+@st.cache_resource
+def load_model():
+    model_path = hf_hub_download(
+        repo_id=MODEL_REPO,
+        filename="best_model.joblib",
+        repo_type="model"
+    )
+    return joblib.load(model_path)
+
+model = load_model()
+
+engine_rpm = st.number_input("Engine RPM", value=750.0)
+lub_oil_pressure = st.number_input("Lub Oil Pressure", value=3.0)
+fuel_pressure = st.number_input("Fuel Pressure", value=6.0)
+coolant_pressure = st.number_input("Coolant Pressure", value=2.0)
+lub_oil_temp = st.number_input("Lub Oil Temperature", value=77.0)
+coolant_temp = st.number_input("Coolant Temperature", value=78.0)
+
+if st.button("Predict Engine Condition"):
+    input_df = 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
+    }])
+
+    pred = model.predict(input_df)[0]
+
+    if pred == 1:
+        st.error("⚠️ Faulty Engine Detected — Maintenance Required")
+    else:
+        st.success("✅ Engine Operating Normally")

push_to_hf_space.py

@@ -0,0 +1,28 @@
+import os
+from huggingface_hub import HfApi
+
+HF_SPACE_REPO = os.getenv("HF_SPACE_REPO")
+
+def main():
+    api = HfApi(token=os.getenv("HF_TOKEN"))
+
+    # Create Hugging Face Space as DOCKER (not streamlit)
+    api.create_repo(
+        repo_id=HF_SPACE_REPO,
+        repo_type="space",
+        space_sdk="docker",
+        exist_ok=True
+    )
+
+    # Upload deployment folder (Dockerfile + app + requirements)
+    api.upload_folder(
+        folder_path="deployment",
+        repo_id=HF_SPACE_REPO,
+        repo_type="space",
+        commit_message="Deploy Docker-based Streamlit app"
+    )
+
+    print("✅ Hugging Face Space deployment complete.")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+pandas
+scikit-learn
+joblib
+huggingface_hub
+xgboost
+datasets