Upload folder using huggingface_hub

Dockerfile

@@ -1,20 +1,26 @@
-FROM python:3.13.5-slim
+FROM python:3.9-slim
 
-WORKDIR /app
+# Create non-root user
+RUN useradd -m -u 1000 user
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+# Set environment variables
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
 
-COPY requirements.txt ./
-COPY src/ ./src/
+# Set working directory
+WORKDIR $HOME/app
 
-RUN pip3 install -r requirements.txt
+# Copy application files
+COPY --chown=user . .
 
-EXPOSE 8501
+# Switch to non-root user
+USER user
+
+# Install dependencies locally for the user
+RUN pip install --no-cache-dir -r requirements.txt
 
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+# Expose Streamlit port
+EXPOSE 8501
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# Run Streamlit app
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]

app.py

@@ -0,0 +1,140 @@
+import streamlit as st
+import pandas as pd
+from huggingface_hub import hf_hub_download
+import joblib
+
+# Download the model from Hugging Face Hub
+model_path = hf_hub_download(
+    repo_id="manyu007/tourism-model",
+    filename="model.joblib"
+)
+
+# Load the trained model
+model = joblib.load(model_path)
+
+# Streamlit UI
+st.title("MLOPS – Customer Package Purchase Prediction App")
+st.write(
+    "This internal application predicts whether a customer is likely to "
+    "purchase a travel package based on demographic and interaction details."
+)
+st.write("Please enter the customer details below.")
+
+# -----------------------------
+# Customer Details
+# -----------------------------
+Age = st.number_input("Age", min_value=18, max_value=100, value=30)
+
+TypeofContact = st.selectbox(
+    "Type of Contact",
+    ["Company Invited", "Self Inquiry"]
+)
+
+CityTier = st.selectbox("City Tier", [1, 2, 3])
+
+Occupation = st.selectbox(
+    "Occupation",
+    ["Salaried", "Freelancer", "Small Business", "Large Business"]
+)
+
+Gender = st.selectbox("Gender", ["Male", "Female"])
+
+NumberOfPersonVisiting = st.number_input(
+    "Number of Persons Visiting",
+    min_value=1, max_value=10, value=2
+)
+
+PreferredPropertyStar = st.selectbox(
+    "Preferred Property Star",
+    [1, 2, 3, 4, 5]
+)
+
+MaritalStatus = st.selectbox(
+    "Marital Status",
+    ["Single", "Married", "Divorced"]
+)
+
+NumberOfTrips = st.number_input(
+    "Number of Trips (per year)",
+    min_value=0, max_value=50, value=2
+)
+
+Passport = st.selectbox("Has Passport?", ["Yes", "No"])
+OwnCar = st.selectbox("Owns a Car?", ["Yes", "No"])
+
+NumberOfChildrenVisiting = st.number_input(
+    "Number of Children Visiting",
+    min_value=0, max_value=5, value=0
+)
+
+Designation = st.selectbox(
+    "Designation",
+    ["Executive", "Manager", "Senior Manager", "VP"]
+)
+
+MonthlyIncome = st.number_input(
+    "Monthly Income",
+    min_value=5000, max_value=500000, value=50000
+)
+
+# -----------------------------
+# Interaction Details
+# -----------------------------
+PitchSatisfactionScore = st.slider(
+    "Pitch Satisfaction Score",
+    min_value=1, max_value=5, value=3
+)
+
+ProductPitched = st.selectbox(
+    "Product Pitched",
+    ["Basic", "Standard", "Deluxe", "Super Deluxe"]
+)
+
+NumberOfFollowups = st.number_input(
+    "Number of Follow-ups",
+    min_value=0, max_value=20, value=2
+)
+
+DurationOfPitch = st.number_input(
+    "Duration of Pitch (minutes)",
+    min_value=1, max_value=120, value=15
+)
+
+# -----------------------------
+# Prepare input data
+# -----------------------------
+input_data = pd.DataFrame([{
+    "Age": Age,
+    "TypeofContact": TypeofContact,
+    "CityTier": CityTier,
+    "Occupation": Occupation,
+    "Gender": Gender,
+    "NumberOfPersonVisiting": NumberOfPersonVisiting,
+    "PreferredPropertyStar": PreferredPropertyStar,
+    "MaritalStatus": MaritalStatus,
+    "NumberOfTrips": NumberOfTrips,
+    "Passport": 1 if Passport == "Yes" else 0,
+    "OwnCar": 1 if OwnCar == "Yes" else 0,
+    "NumberOfChildrenVisiting": NumberOfChildrenVisiting,
+    "Designation": Designation,
+    "MonthlyIncome": MonthlyIncome,
+    "PitchSatisfactionScore": PitchSatisfactionScore,
+    "ProductPitched": ProductPitched,
+    "NumberOfFollowups": NumberOfFollowups,
+    "DurationOfPitch": DurationOfPitch
+}])
+
+# Classification threshold
+classification_threshold = 0.5
+
+# -----------------------------
+# Prediction
+# -----------------------------
+if st.button("Predict"):
+    prediction_proba = model.predict_proba(input_data)[0, 1]
+    prediction = (prediction_proba >= classification_threshold).astype(int)
+
+    if prediction == 1:
+        st.success("✅ The customer is likely to purchase the package.")
+    else:
+        st.error("❌ The customer is unlikely to purchase the package.")

requirements.txt

@@ -1,3 +1,7 @@
-altair
+streamlit
 pandas
-streamlit
+scikit-learn
+xgboost
+joblib
+huggingface_hub
+mlflow