Upload folder using huggingface_hub

Dockerfile

@@ -1,20 +1,23 @@
-FROM python:3.13.5-slim
+# Use a minimal base image with Python 3.9 installed
+FROM python:3.9
 
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY requirements.txt ./
-COPY src/ ./src/
+# Copy all files from the current directory on the host to the container's /app directory
+COPY . .
 
+# Install Python dependencies listed in requirements.txt
 RUN pip3 install -r requirements.txt
 
-EXPOSE 8501
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
 
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
+COPY --chown=user . $HOME/app
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# Define the command to run the Streamlit app on port "8501" and make it accessible externally
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]

app.py

@@ -0,0 +1,249 @@
+import streamlit as st
+import pandas as pd
+from huggingface_hub import hf_hub_download
+import joblib
+
+# Download and load the model
+model_path = hf_hub_download(repo_id="asvravi/asv-tourism-package", filename="best_toursim_package_model_v1.joblib")
+model = joblib.load(model_path)
+
+# Streamlit UI for Tourism Package Prediction
+st.title("Tourism Package Prediction App")
+st.write("""
+This application predicts the likelihood of a customer buying the new Tourism Package.
+Please enter the data below to get a prediction.
+""")
+
+# List of numerical features in the dataset
+numeric_features = [
+    'Age',       # Customer's credit score
+    'DurationOfPitch',
+    'NumberOfFollowups',
+    'PitchSatisfactionScore',
+    'NumberOfPersonVisiting',
+    'PreferredPropertyStar',
+    'NumberOfTrips',
+    'Passport',
+    'OwnCar',
+    'NumberOfChildrenVisiting',
+    'MonthlyIncome',
+    'CityTier',              # City category based on development, population, and living standards
+]
+
+# List of categorical features in the dataset
+categorical_features = [
+    'TypeofContact',         # Country where the customer resides
+    'Occupation',            # Customer's occupation
+    'Gender',                # Gender of the customer
+    'ProductPitched',
+    'MaritalStatus',         # Marital status of the customer
+    'Designation',           # Designation of the customer's current position
+]
+
+
+# User input
+st.header("Section 1 – Basic Information")
+
+# ---------- Row 1 ----------
+col1, col2, col3 = st.columns(3)
+
+with col1:
+    age = st.number_input(
+        "Age",
+        min_value=1,
+        max_value=150,
+        value=25
+    )
+
+with col2:
+    # Marital status alphabetically
+    marital_status_options = sorted(["Married", "Single", "Divorced", "Unmarried"])
+    marital_status = st.selectbox(
+        "Marital Status",
+        marital_status_options,
+        index=0
+    )
+
+with col3:
+    gender = st.radio(
+        "Gender",
+        ["Male", "Female"],
+        index=0
+    )
+
+# ---------- Row 2 ----------
+col4, col5, col6 = st.columns(3)
+
+with col4:
+    city_tier = st.selectbox(
+        "City Tier",
+        [1, 2, 3],
+        index=0
+    )
+
+with col5:
+    total_family = st.number_input(
+        "Total Family Members",
+        min_value=1,
+        max_value=50,
+        value=1,
+        step=1
+    )
+
+with col6:
+    children = st.number_input(
+        "No. of Children (age > 5)",
+        min_value=0,
+        max_value=20,
+        value=0,
+        step=1
+    )
+
+# ---------- Row 3 ----------
+col7, col8, col9 = st.columns(3)
+
+with col7:
+    own_car = st.selectbox(
+        "Own a Car",
+        ["Yes", "No"],
+        index=0
+    )
+
+st.header("Section 2 – Professional Details")
+
+# ---------- Row 1 ----------
+col1, col2, col3 = st.columns(3)
+
+with col1:
+    occupation_options = sorted(["Free Lancer", "Salaried", "Large Business", "Small Business"])
+    occupation = st.selectbox(
+        "Occupation",
+        occupation_options,
+        index=0
+    )
+
+with col2:
+    designation_options = sorted(["AVP", "Manager", "Senior Manager", "Executive", "VP"])
+    designation = st.selectbox(
+        "Designation",
+        designation_options,
+        index=0
+    )
+
+with col3:
+    monthly_salary = st.number_input(
+        "Monthly Salary",
+        min_value=1000,
+        max_value=100000,
+        value=1000,
+        step=100
+    )
+
+
+st.header("Section 3 – Travel Preferences")
+
+# ---------- Row 1 ----------
+col1, col2, col3 = st.columns(3)
+
+with col1:
+    property_star = st.selectbox(
+        "Preferred Property Star",
+        [3, 4, 5],
+        index=0
+    )
+
+with col2:
+    trips_per_year = st.number_input(
+        "Number of Trips per Year",
+        min_value=1,
+        max_value=50,
+        value=1,
+        step=1
+    )
+
+with col3:
+    passport = st.selectbox(
+        "Passport",
+        ["Yes", "No"],
+        index=0
+    )
+
+st.header("Section 4 – Sales Interaction Details")
+
+# ---------- Row 1 ----------
+col1, col2, col3 = st.columns(3)
+
+with col1:
+    type_of_contact = st.selectbox(
+        "Type of Contact",
+        ["Company Invited", "Self Enquiry"],
+        index=0
+    )
+
+with col2:
+    product_pitched = st.selectbox(
+        "Product Pitched",
+        ["Basic", "Deluxe", "King", "Standard", "Super Deluxe"],
+        index=0
+    )
+
+with col3:
+    pitch_duration = st.number_input(
+        "Duration of Pitch (minutes)",
+        min_value=1,
+        max_value=150,
+        value=1,
+        step=1
+    )
+
+# ---------- Row 2 ----------
+col4, col5, col6 = st.columns(3)
+
+with col4:
+    followups = st.number_input(
+        "Number of Follow-ups",
+        min_value=1,
+        max_value=10,
+        value=1,
+        step=1
+    )
+
+with col5:
+    pitch_satisfaction = st.selectbox(
+        "Pitch Satisfaction Score",
+        [1, 2, 3, 4, 5],
+        index=0
+    )
+
+
+own_car = 1 if own_car == "Yes" else 0
+passport = 1 if passport == "Yes" else 0
+
+# Assemble input into DataFrame
+input_data = pd.DataFrame([{
+    'Age': age,
+    'DurationOfPitch': pitch_duration,
+    'NumberOfFollowups': followups,
+    'PitchSatisfactionScore': pitch_satisfaction,
+    'NumberOfPersonVisiting': total_family,
+    'PreferredPropertyStar': property_star,
+    'NumberOfTrips': trips_per_year,
+    'Passport': passport,
+    'OwnCar': own_car,
+    'NumberOfChildrenVisiting': children,
+    'MonthlyIncome': monthly_salary,
+    'CityTier': city_tier,     
+    'TypeofContact': type_of_contact,         
+    'Occupation': occupation,            
+    'Gender': gender,              
+    'ProductPitched': product_pitched,
+    'MaritalStatus': marital_status,         
+    'Designation': designation                        
+}])
+
+# Predict button
+if st.button("Predict"):
+    prediction_proba = model.predict_proba(input_data)[0, 1]
+    prediction = (prediction_proba >= classification_threshold).astype(int)
+    result = "likely to buy" if prediction == 1 else "not likely to buy"
+    st.write(f"Based on the information provided, the customer is {result} the new tourism package.")

requirements.txt

@@ -1,3 +1,7 @@
-altair
-pandas
-streamlit
+pandas==2.2.2
+huggingface_hub==0.32.6
+streamlit==1.43.2
+joblib==1.5.1
+scikit-learn==1.6.0
+xgboost==2.1.4
+mlflow==3.0.1