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 +1,97 @@
+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="SandeepMM/GL-MLOps-VisitWithUs", filename="best_visitwithus_model_v1.joblib")
+try:
+    model_repo_id = "SandeepMM/GL-MLOps-VisitWithUs"
+    model_filename = "best_visitwithus_model_v1.joblib"
+    
+    # Use hf_hub_download for reliable model artifact fetching
+    model_path = hf_hub_download(repo_id=model_repo_id, filename=model_filename)
+    model = joblib.load(model_path)
+    
+    st.sidebar.success("Model loaded successfully!")
+except Exception as e:
+    st.sidebar.error(f"Error loading model: {e}")
+    model = None
+
+# Streamlit UI for Machine Failure Prediction
+st.title("Visit With Us! Tourism App")
+st.write("""
+This application predicts the likelihood of a customer buying a tourism package.
+Please enter the customer data below to get a prediction.
+""")
+
+# --- User Input Fields (Using snake_case for variables) ---
+st.header("Customer Profile")
+
+age = st.number_input("Age", min_value=18, max_value=120, value=30, step=1)
+gender = st.selectbox("Gender", ['Female','Male'], index=0)
+marital_status = st.selectbox("Marital Status", ['Unmarried','Married','Divorced'], index=0)
+occupation = st.selectbox("Occupation", ['Large Business','Salaried','Small Business'], index=1)
+designation = st.selectbox("Designation", ['Executive','Manager','Senior Manager','AVP','VP'], index=0)
+monthly_income = st.number_input("Monthly Income", min_value=1000, max_value=100000, value=25000, step=1000)
+number_of_person_visiting = st.number_input("Number Of Person Visiting", min_value=1, max_value=5, value=2, step=1)
+number_of_children_visiting = st.number_input("Number Of Children Visiting", min_value=1, max_value=5, value=2, step=1)
+city_tier = st.number_input("City Tier", min_value=1, max_value=3, value=1, step=1)
+passport = st.number_input("Passport (0=No, 1=Yes)", min_value=0, max_value=1, value=0, step=1)
+own_car = st.number_input("Own a Car (0=No, 1=Yes)", min_value=0, max_value=1, value=0, step=1)
+preferred_property_star = st.number_input("Preferred Property Star (1 to 5)", min_value=1, max_value=5, value=3, step=1)
+
+st.header("Trip Details")
+
+number_of_trips = st.number_input("Number Of Trips Taken Previously", min_value=1, max_value=22, value=5, step=1)
+type_of_contact = st.selectbox("Type of Contact", ['Company Invited','Self Enquiry'], index=0)
+product_pitched = st.selectbox("Product Pitched", ['Basic','Deluxe','Standard','Super Deluxe','King'], index=1)
+duration_of_pitch = st.number_input("Duration Of Pitch (minutes)", min_value=5, max_value=127, value=15, step=1)
+pitch_satisfaction_score = st.number_input("Pitch Satisfaction Score (1 to 5)", min_value=1, max_value=5, value=3, step=1)
+number_of_followups = st.number_input("Number Of Followups", min_value=1, max_value=6, value=2, step=1)
+
+
+# Assemble input into DataFrame (column names must match training data features)
+input_data = pd.DataFrame([{
+    'Age': age,
+    'Gender': gender,
+    'MaritalStatus': marital_status,
+    'Occupation': occupation,
+    'Designation': designation,
+    'MonthlyIncome': monthly_income,
+    'NumberOfPersonVisiting': number_of_person_visiting,
+    'NumberOfChildrenVisiting': number_of_children_visiting,
+    'CityTier': city_tier,
+    'Passport': passport,
+    'OwnCar': own_car,
+    'PreferredPropertyStar': preferred_property_star,
+    'NumberOfTrips': number_of_trips,
+    'TypeofContact': type_of_contact,
+    'ProductPitched': product_pitched,
+    'DurationOfPitch': duration_of_pitch,
+    'PitchSatisfactionScore': pitch_satisfaction_score,
+    'NumberOfFollowups': number_of_followups,
+}])
+
+# Set a consistent classification threshold
+CLASSIFICATION_THRESHOLD = 0.4951
+if st.button("Predict Package Purchase"):
+    if model is not None:
+        
+        # Get the probability of the positive class (ProdTaken=1)
+        prediction_proba = model.predict_proba(input_data)[:, 1][0]
+        
+        # Apply the optimized classification threshold
+        prediction = 1 if prediction_proba >= CLASSIFICATION_THRESHOLD else 0
+        
+        result = "Customer Purchase Potential! (Likely to buy)" if prediction == 1 else "No Sale (Unlikely to buy)"
+        
+        st.subheader("Prediction Result:")
+        if prediction == 1:
+             st.success(f"The model predicts: **{result}**")
+        else:
+             st.warning(f"The model predicts: **{result}**")
+
+        st.info(f"Probability of Purchase: **{prediction_proba:.4f}**")
+    else:
+        st.error("Cannot predict: Model failed to load.")

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