Update app.py

app.py

@@ -8,6 +8,7 @@ import time
 import matplotlib.pyplot as plt
 import qrcode
 from io import BytesIO
+import csv
 
 # Load the trained models and transformers
 num_imputer = joblib.load('numerical_imputer.joblib')
@@ -55,16 +56,34 @@ st.title('📞 EXPRESSO TELECOM CUSTOMER CHURN PREDICTION APP 📞')
 
 # Main page - Churn Prediction
 st.image("banner.png", use_column_width=True)
+st.markdown("This app predicts whether a customer will leave your company ❌ or not 🎉. Enter the details of the customer on the left sidebar to see the result")
+
 
     # How to use
-st.sidebar.title('How to Use')
-st.sidebar.markdown('1. Select your model of choice on the left sidebar.')
-st.sidebar.markdown('2. Adjust the input parameters based on customer details')
-st.sidebar.markdown('3. Click the "Predict" button to initiate the prediction.')
-st.sidebar.markdown('4. The app will simulate a prediction process with a progress bar.')
-st.sidebar.markdown('5. Once the prediction is complete, the results will be displayed below.')
+st.title('How to Use')
+st.markdown('1. Select your model of choice on the left sidebar.')
+st.markdown('2. Adjust the input parameters based on customer details')
+st.markdown('3. Click the "Predict" button to initiate the prediction.')
+st.markdown('4. The app will simulate a prediction process with a progress bar.')
+st.markdown('5. Once the prediction is complete, the results will be displayed below.')
+
+import csv
+import streamlit as st
 
-st.markdown("This app predicts whether a customer will leave your company ❌ or not 🎉. Enter the details of the customer on the left sidebar to see the result")
+# Add context text
+st.sidebar.markdown('**Welcome!**')
+st.sidebar.markdown('This is a work in progress, and we would love to hear your suggestions on how to improve the user experience. Please feel free to provide your feedback in the suggestion box below.')
+
+# Create the sidebar with a text input field for suggestions
+correction_text = st.sidebar.text_input('Enter your suggestion')
+
+# Button to submit the suggestion
+if st.sidebar.button('Submit'):
+    # Perform action on suggestion submission (e.g., save to a CSV file)
+    with open('suggestions.csv', 'a', newline='') as file:
+        writer = csv.writer(file)
+        writer.writerow([correction_text])
+    st.sidebar.info('Suggestion submitted successfully')
 
 # Define a dictionary of models with their names, actual models, and types
 models = {
@@ -73,7 +92,9 @@ models = {
 }
 
 # Allow the user to select a model from the sidebar
-model_name = st.sidebar.selectbox('Select Model', list(models.keys()))
+# Allow the user to select a model from the sidebar
+st.sidebar.title('Select Model')
+model_name = st.sidebar.selectbox('Choose a model', list(models.keys()))
 
 # Retrieve the selected model and its type from the dictionary
 model = models[model_name]['model']
@@ -158,6 +179,7 @@ def predict_churn(input_data, model):
     # Return churn labels, churn probabilities, churn indices, and churn index
     return churn_labels, churn_probability, churn_indices, churn_index
 
+
 # Predict churn based on user input
 if st.sidebar.button('Predict Churn'):
     try:
@@ -172,9 +194,7 @@ if st.sidebar.button('Predict Churn'):
                 #churn_labels, churn_probability = predict_churn(input_features, model)  # Pass model1 or model2 based on the selected model
         churn_labels, churn_probability, churn_indices, churn_index = predict_churn(input_features, model)
 
-        st.subheader('Main Churn Prediction Results')
-
-
+        st.subheader('Main Results')
 
         col1, col2 = st.columns(2)
 
@@ -281,6 +301,7 @@ if st.sidebar.button('Predict Churn'):
             else:
                 churn_comparison = "equal"
 
+
             explanation = f"This bar chart compares the churn probability of the selected customer " \
                             f"with the average churn rate of all customers. It provides insights into how the " \
                             f"individual customer's churn likelihood ({predicted_churn_prob:.2f}) compares to the " \
@@ -305,16 +326,21 @@ if st.sidebar.button('Predict Churn'):
             )
 
             explanation = f"This bar chart compares the churn probability of the selected customer " \
-                            f"with the average churn rate of all customers. It provides insights into how the " \
-                            f"individual customer's churn likelihood ({predicted_churn_prob:.2f}) compares to the " \
-                            f"overall trend." \
-                            f"The prediction indicates that the customer is not likely to churn. " \
-                        f"The churn probability is lower than the no-churn probability."
+              f"with the average churn rate of all customers. It provides insights into how the " \
+              f"individual customer's likelihood of churn ({1 - predicted_churn_prob:.2f}) compares to the " \
+              f"overall trend. A lower churn probability indicates that the customer is less likely to churn. " \
+              f"The chart shows that the churn probability ({1 - predicted_churn_prob:.2f}) is lower than the " \
+              f"average churn probability ({main_data_churn_probability:.2f}), suggesting that the customer " \
+              f"is predicted to stay with the company. Keep in mind that the prediction is based on the " \
+              f"available data and the applied model, and there might still be some uncertainty in the result."
+
 
             st.plotly_chart(fig)
             st.write(explanation)
 
         # Visualize Feature Importance
+
+        st.subheader('Feature Importance')
         if hasattr(model, 'coef_'):  # Check if the model has attribute 'coef_' to determine importance type
             feature_importances = model.coef_[0]
             importance_type = 'Coef'
@@ -329,8 +355,6 @@ if st.sidebar.button('Predict Churn'):
             importance_df = pd.DataFrame({'Feature': original_feature_names, importance_type: feature_importances})
             importance_df = importance_df.sort_values(importance_type, ascending=False)
 
-            st.subheader('Feature Importance')
-
             # Determine color for each bar based on positive or negative importance
             colors = ['green' if importance > 0 else 'red' for importance in importance_df[importance_type]]
 
@@ -357,55 +381,22 @@ if st.sidebar.button('Predict Churn'):
 
     # Explanation of feature importance
             importance_explanation = f"The feature importance plot shows the relative importance of each feature " \
-                             f"for predicting churn. The importance is calculated based on the " \
-                             f"{importance_type} value of each feature in the model. " \
-                             f"A higher {importance_type} value indicates a stronger influence " \
-                             f"of the corresponding feature on the prediction of churn.\n\n" \
-                             f"For logistic regression, positive {importance_type} values indicate " \
-                             f"features that positively contribute to predicting churn, " \
-                             f"while negative {importance_type} values indicate features that " \
-                             f"negatively contribute to predicting churn.\n\n" \
-                             f"For gradient boosting, higher {importance_type} values " \
-                             f"indicate features that have a greater importance in predicting churn.\n\n" \
-                             f"Note: The feature importance values may change depending on the model " \
-                             f"and the data used for training."
+                       f"for predicting churn. The importance is calculated based on the " \
+                       f"{importance_type} value of each feature in the model. " \
+                       f"A higher {importance_type} value indicates a stronger influence " \
+                       f"of the corresponding feature on the prediction of churn.\n\n" \
+                       f"For logistic regression, positive {importance_type} values indicate " \
+                       f"features that positively contribute to predicting churn, " \
+                       f"while negative {importance_type} values indicate features that " \
+                       f"negatively contribute to predicting churn.\n\n" \
+                       f"For gradient boosting, higher {importance_type} values " \
+                       f"indicate features that have a greater importance in predicting churn.\n\n" \
+                       f"Please note that the feature importance values may vary depending on the model " \
+                       f"and the data used for training."
+
 
             st.write(importance_explanation)
-        else:
-            st.write('Feature importance is not available for this model.')
 
-#        def generate_qr_code(churn_labels, churn_probability, average_churn_rate):
-#    # Create a string representation of the important results
-#            result_string = f"Churn Probability: {churn_probability:.2f}\n" \
-#                            f"Average Churn Rate: {average_churn_rate:.2f}"
-#
-#                        # Generate the QR code
-#            qr = qrcode.QRCode(
-#                version=1,
-#                error_correction=qrcode.constants.ERROR_CORRECT_L,
-#                box_size=10,
-#                border=4,)
-#            qr.add_data(result_string)
-#            qr.make(fit=True)
-
-            # Create an image from the QR code
-#            qr_image = qr.make_image(fill_color="black", back_color="white")
-
-    # Resize the image to a smaller size for mobile-friendly display
-#            qr_image = qr_image.resize((200, 200))
-
-    # Create a BytesIO object to store the image data
-#            image_stream = BytesIO()
-#            qr_image.save(image_stream, format='PNG')
-#            image_stream.seek(0)
-
-#            return image_stream
-
-        # Generate the QR code for the important results
-#        qr_image_stream = generate_qr_code(churn_labels, churn_probability, average_churn_rate)
-
-#        # Display the QR code using the Streamlit `image` function
-#        st.image(qr_image_stream, use_column_width=True)
 
     except Exception as e:
         st.error(f"An error occurred: {str(e)}")