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 +1,70 @@
+import streamlit as st
+import pandas as pd
+from huggingface_hub import hf_hub_download
+import joblib
+
+# Download and load the model from Hugging Face Hub
+model_path = hf_hub_download(
+    repo_id="Sudu1976/tourismpkg_prediction_model", # Corrected repo_id
+    filename="tourismpkg_prediction_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 whether a customer will purchase the **Wellness Tourism Package** based on their details.
+Please enter the required information below to get a prediction.
+""")
+
+# User input
+age = st.number_input("Age", min_value=18, max_value=100, value=30, step=1)
+typeofcontact = st.selectbox("TypeofContact", ["Company Invited", "Self Inquiry"])
+citytier = st.number_input("CityTier", min_value=1, max_value=3, value=1, step=1)
+occupation = st.selectbox("Occupation", ["Salaried", "Free Lancer", "Small Business", "Large Business"])
+gender = st.selectbox("Gender", ["male", "female"])
+nrofpersonvisiting = st.number_input("NumberOfPersonVisiting", min_value=1, max_value=8, value=2, step=1)
+prfpropertystar = st.number_input("PreferredPropertyStar", min_value=3, max_value=5, value=3, step=1)
+maritalstatus = st.selectbox("MaritalStatus", ["Single", "Married", "Unmarried", "Divorced"])
+nroftrips = st.number_input("NumberOfTrips", min_value=1, max_value=20, value=3, step=1)
+passport =  st.number_input("Passport", min_value=0, max_value=1, value=1, step=1)
+designation = st.selectbox("Designation", ["Manager", "Senior Manager", "Executive", "AVP", "VP"])
+monthlyincome = st.number_input("MonthlyIncome", min_value=1000, max_value=40000, value=5000, step=100)
+csi = st.number_input("PitchSatisfactionScore", min_value=1, max_value=5, value=2, step=1)
+productpitched = st.selectbox("ProductPitched", ["Basic", "Standard", "Deluxe", "Super Deluxe", "King"])
+nroffups = st.number_input("NumberOfFollowups", min_value=1, max_value=6, value=2, step=1)
+pitchduration = st.number_input("DurationOfPitch", min_value=5, max_value=40, value=10, step=1)
+
+# Assemble input into DataFrame
+input_data = pd.DataFrame([
+    {
+    'Age': age,
+    'TypeofContact': typeofcontact,
+    'CityTier': citytier,
+    'Occupation': occupation,
+    'Gender': gender,
+    'NumberOfPersonVisiting': nrofpersonvisiting,
+    'PreferredPropertyStar': prfpropertystar,
+    'MaritalStatus': maritalstatus,
+    'NumberOfTrips': nroftrips,
+    'Passport': passport,
+    'Designation': designation,
+    'MonthlyIncome': monthlyincome, # Fixed typo here
+    'PitchSatisfactionScore': csi,
+    'ProductPitched' : productpitched,
+    'NumberOfFollowups' : nroffups,
+    'DurationOfPitch' :pitchduration
+
+}])
+
+# Prediction
+if st.button("Predict Purchase"):
+    # The model expects raw categorical features, which its internal preprocessor will handle.
+    # The model's predict method should handle the transformation.
+    prediction_proba = model.predict_proba(input_data)[:, 1]
+    # Using a classification threshold, let's say 0.45, to decide on the class.
+    classification_threshold = 0.45
+    if prediction_proba[0] >= classification_threshold:
+        st.success(f"Prediction: Customer is likely to purchase the Wellness Tourism Package (Probability: {prediction_proba[0]:.2f})")
+    else:
+        st.info(f"Prediction: Customer is unlikely to purchase the Wellness Tourism Package (Probability: {prediction_proba[0]:.2f})")

requirements.txt

@@ -1,3 +1,7 @@
-altair
-pandas
-streamlit
+pandas==2.2.2
+huggingface_hub==0.34.0
+streamlit==1.43.2
+joblib==1.5.1
+scikit-learn==1.4.2
+xgboost==2.1.4
+scipy==1.13.1