Upload folder using huggingface_hub

Dockerfile

@@ -10,7 +10,4 @@ COPY . .
 RUN pip install --no-cache-dir --upgrade -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"]

app.py

@@ -16,11 +16,11 @@ def home():
 # Define an endpoint to predict for single customer
 @churn_predictor_api.post('/v1/customer')
 def predict_churn():
-  # Get JSON data from the request
-  customer_data = request.get_json()
+    # Get JSON data from the request
+    customer_data = request.get_json()
 
-  # Extract the relevant customer features from the input data
-  sample = {
+    # Extract the relevant customer features from the input data
+    sample = {
         'CreditScore': customer_data['CreditScore'],
         'Geography': customer_data['Geography'],
         'Age': customer_data['Age'],
@@ -32,39 +32,39 @@ def predict_churn():
         'EstimatedSalary': customer_data['EstimatedSalary']
     }
 
-  # Convert the extracted data into a dataframe
-  input_data = pd.DataFrame([sample])
+    # Convert the extracted data into a dataframe
+    input_data = pd.DataFrame([sample])
 
-  # Make predictions using the trained model
-  prediction = model.predict(input_data).tolist()[0]
+    # Make predictions 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"
+    # 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})
+    # Return the prediction as a JSON response
+    return jsonify({"Prediction": prediction_label})
 
 # Define an endpoint to predict 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']
+    # Get the uploaded csv file from the request
+    file = request.files['file']
 
-  # Read the file into a dataframe
-  input_data = pd.read_csv(file)
+    # Read the file into a dataframe
+    input_data = pd.read_csv(file)
 
-  # Make predictions to the batch data and convert raw predictions into a readable formate
-  predictions = [
-      'Churn' if x == 1
-      else 'Not Churn'
-      for x in model.predict(input_data.drop("CustomerId", axis=1)).tolist()
-  ]
+    # Make predictions to 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.tolist()
-  output_dict = dict(zip(cust_id_list, predictions))
+    cust_id_list = input_data.CustomerId.tolist()
+    output_dict = dict(zip(cust_id_list, predictions))
 
-  return output_dict
+    # CRITICAL FIX: Return JSON response
+    return jsonify(output_dict)
 
 # Run the flask app in debug mode
 if __name__ == "__main__":
-  churn_predictor_api.run(debug=True)
+    churn_predictor_api.run(debug=True)

requirements.txt

@@ -1,11 +1,7 @@
-pandas==2.2.2
-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
+pandas==2.0.3
+numpy==1.24.3
+scikit-learn==1.3.0
+xgboost==1.7.6
+joblib==1.3.2
+flask==2.3.3
 gunicorn==20.1.0
-requests==2.28.1
-uvicorn[standard]
-streamlit==1.43.2