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 +1,56 @@
+import streamlit as st
+import pandas as pd
+from huggingface_hub import hf_hub_download
+import joblib
+
+#common constants:
+GITHUB_REPO_NAME = 'CustomerChurnMLOps'
+HUGGINGFACE_SPACE_NAME = 'CustomerChurnMLOps'
+HUGGINGFACE_DATASET_NAME = 'bank_customer_churn'
+HUGGINGFACE_MODEL_NAME= 'churn-model'
+HUGGINGFACE_USER_NAME = 'AdarshRL'
+
+# Download the model from the Model Hub
+model_path = hf_hub_download(repo_id=f"{HUGGINGFACE_USER_NAME}/{HUGGINGFACE_MODEL_NAME}", filename="best_churn_model.joblib")
+
+# Load the model
+model = joblib.load(model_path)
+
+# Streamlit UI for Customer Churn Prediction
+st.title("Customer Churn Prediction App")
+st.write("The Customer Churn Prediction App is an internal tool for bank staff that predicts whether customers are at risk of churning based on their details.")
+st.write("Kindly enter the customer details to check whether they are likely to churn.")
+
+# Collect user input
+CreditScore = st.number_input("Credit Score (customer's credit score)", min_value=300, max_value=900, value=650)
+Geography = st.selectbox("Geography (country where the customer resides)", ["France", "Germany", "Spain"])
+Age = st.number_input("Age (customer's age in years)", min_value=18, max_value=100, value=30)
+Tenure = st.number_input("Tenure (number of years the customer has been with the bank)", value=12)
+Balance = st.number_input("Account Balance (customer’s account balance)", min_value=0.0, value=10000.0)
+NumOfProducts = st.number_input("Number of Products (number of products the customer has with the bank)", min_value=1, value=1)
+HasCrCard = st.selectbox("Has Credit Card?", ["Yes", "No"])
+IsActiveMember = st.selectbox("Is Active Member?", ["Yes", "No"])
+EstimatedSalary = st.number_input("Estimated Salary (customer’s estimated salary)", min_value=0.0, value=50000.0)
+
+# Convert categorical inputs to match model training
+input_data = pd.DataFrame([{
+    'CreditScore': CreditScore,
+    'Geography': Geography,
+    'Age': Age,
+    'Tenure': Tenure,
+    'Balance': Balance,
+    'NumOfProducts': NumOfProducts,
+    'HasCrCard': 1 if HasCrCard == "Yes" else 0,
+    'IsActiveMember': 1 if IsActiveMember == "Yes" else 0,
+    'EstimatedSalary': EstimatedSalary
+}])
+
+# Set the classification threshold
+classification_threshold = 0.45
+
+# Predict button
+if st.button("Predict"):
+    prediction_proba = model.predict_proba(input_data)[0, 1]
+    prediction = (prediction_proba >= classification_threshold).astype(int)
+    result = "churn" if prediction == 1 else "not churn"
+    st.write(f"Based on the information provided, the customer is likely to {result}.")

requirements.txt

@@ -1,3 +1,6 @@
-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