Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +1,14 @@
+# Use a minimal base image with Python 3.9 installed
 FROM python:3.9-slim
 
-# Set the working directory inside the container
+# Set the working directory inside the container to /app
 WORKDIR /app
 
-# Copy all files from the current directory to the container's working directory
+# Copy all files from the current directory on the host to the container's /app directory
 COPY . .
 
-# Install dependencies from the requirements file without using cache to reduce image size
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
+# Install Python dependencies listed in requirements.txt
+RUN pip3 install -r requirements.txt
 
-# Define the command to start the application using Gunicorn with 4 worker processes
-# - `-w 4`: Uses 4 worker processes for handling requests
-# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
-# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
-CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:churn_predictor_api"]
+# 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

@@ -1,70 +1,49 @@
-import joblib
-import pandas as pd
-from flask import Flask, request, jsonify
-
-# Initialize Flask app with a name
-churn_predictor_api = Flask("Customer Churn Predictor")
-
-# Load the trained churn prediction model
-model = joblib.load("churn_prediction_model_v1_0.joblib")
-
-# Define a route for the home page
-@churn_predictor_api.get('/')
-def home():
-    return "Welcome to the Customer Churn Prediction API!"
-
-# Define an endpoint to predict churn for a single customer
-@churn_predictor_api.post('/v1/customer')
-def predict_churn():
-    # Get JSON data from the request
-    customer_data = request.get_json()
-
-    # Extract relevant customer features from the input data
-    sample = {
-        'CreditScore': customer_data['CreditScore'],
-        'Geography': customer_data['Geography'],
-        'Age': customer_data['Age'],
-        'Tenure': customer_data['Tenure'],
-        'Balance': customer_data['Balance'],
-        'NumOfProducts': customer_data['NumOfProducts'],
-        'HasCrCard': customer_data['HasCrCard'],
-        'IsActiveMember': customer_data['IsActiveMember'],
-        'EstimatedSalary': customer_data['EstimatedSalary']
-    }
-
-    # Convert the extracted data into a DataFrame
-    input_data = pd.DataFrame([sample])
-
-    # Make a churn prediction using the trained model
-    prediction = model.predict(input_data).tolist()[0]
 
-    # Map prediction result to a human-readable label
-    prediction_label = "churn" if prediction == 1 else "not churn"
-
-    # Return the prediction as a JSON response
-    return jsonify({'Prediction': prediction_label})
-
-# Define an endpoint to predict churn for a batch of customers
-@churn_predictor_api.post('/v1/customerbatch')
-def predict_churn_batch():
-    # Get the uploaded CSV file from the request
-    file = request.files['file']
-
-    # Read the file into a DataFrame
-    input_data = pd.read_csv(file)
-
-    # Make predictions for the batch data and convert raw predictions into a readable format
-    predictions = [
-        'Churn' if x == 1
-        else "Not Churn"
-        for x in model.predict(input_data.drop("CustomerId",axis=1)).tolist()
-    ]
-
-    cust_id_list = input_data.CustomerId.values.tolist()
-    output_dict = dict(zip(cust_id_list, predictions))
-
-    return output_dict
+import streamlit as st
+import pandas as pd
+import joblib
 
-# Run the Flask app in debug mode
-if __name__ == '__main__':
-    app.run(debug=True)
+# Load the trained model
+def load_model():
+    return joblib.load("churn_prediction_model_v1_0.joblib")
+
+model = load_model()
+
+# 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}.")

churn_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfe0e0f47d3294eab34fe663bdf36d11f18930601e6258872ce4edf0b881ac4
+size 302538

requirements.txt

@@ -3,9 +3,4 @@ numpy==2.0.2
 scikit-learn==1.6.1
 xgboost==2.1.4
 joblib==1.4.2
-Werkzeug==2.2.2
-flask==2.2.2
-gunicorn==20.1.0
-requests==2.28.1
-uvicorn[standard]
 streamlit==1.43.2