update

app.py

@@ -1,21 +1,24 @@
-import streamlit as st
 import pandas as pd
-import joblib
-import matplotlib.pyplot as plt
+from transformers import pipeline
+import streamlit as st
+import datetime
 from huggingface_hub import hf_hub_download
-import time
-import base64
-from transformers import AutoTokenizer
-
-# Load the pre-trained numerical imputer, scaler, and model using joblib
+import joblib
 
-REPO_ID = "Abubakari/Sepsis-prediction-streamlit-app"
-tokenizer.push_to_hub(REPO_ID)
+REPO_ID = "AlbieCofie/predict-customer-churn"
 
 num_imputer = joblib.load(
     hf_hub_download(repo_id=REPO_ID, filename="numerical_imputer.joblib")
 )
 
+cat_imputer = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename="categorical_imputer.joblib")
+)
+
+encoder = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename="encoder.joblib")
+)
+
 scaler = joblib.load(
     hf_hub_download(repo_id=REPO_ID, filename="scaler.joblib")
 )
@@ -24,145 +27,118 @@ model = joblib.load(
     hf_hub_download(repo_id=REPO_ID, filename="Final_model.joblib")
 )
 
-# Define a function to preprocess the input data
-def preprocess_input_data(input_data):
-    input_data_df = pd.DataFrame(input_data, columns=['PRG', 'PL', 'PR', 'SK', 'TS', 'M11', 'BD2', 'Age', 'Insurance'])
-    num_columns = input_data_df.select_dtypes(include='number').columns
-
-    input_data_imputed_num = num_imputer.transform(input_data_df[num_columns])
-    input_scaled_df = pd.DataFrame(scaler.transform(input_data_imputed_num), columns=num_columns)
-
-    return input_scaled_df
-
-
-# Define a function to make the sepsis prediction
-def predict_sepsis(input_data):
-    input_scaled_df = preprocess_input_data(input_data)
-    prediction = model.predict(input_scaled_df)[0]
-    probabilities = model.predict_proba(input_scaled_df)[0]
-    sepsis_status = "Positive" if prediction == 1 else "Negative"
-    
-    status_icon = "✔" if prediction == 1 else "✘"  # Red 'X' icon for positive sepsis prediction, green checkmark icon for negative sepsis prediction
-    sepsis_explanation = "Sepsis is a life-threatening condition caused by an infection. A positive prediction suggests that the patient might be exhibiting sepsis symptoms and requires immediate medical attention." if prediction == 1 else "Sepsis is a life-threatening condition caused by an infection. A negative prediction suggests that the patient is not currently exhibiting sepsis symptoms."
-
-    output_df = pd.DataFrame(input_data, columns=['PRG', 'PL', 'PR', 'SK', 'TS', 'M11', 'BD2', 'Age', 'Insurance'])
-    output_df['Prediction'] = sepsis_status
-    output_df['Negative Probability'] = probabilities[0]
-    output_df['Positive Probability'] = probabilities[1]
-
-    return output_df, probabilities, status_icon, sepsis_explanation
-
-# Create a Streamlit app
-def main():
-    st.title('Sepsis Prediction App')
-
-    st.image("Strealit_.jpg")
-
-    # How to use
-    st.sidebar.title('How to Use')
-    st.sidebar.markdown('1. Adjust the input parameters on the left sidebar.')
-    st.sidebar.markdown('2. Click the "Predict" button to initiate the prediction.')
-    st.sidebar.markdown('3. The app will simulate a prediction process with a progress bar.')
-    st.sidebar.markdown('4. Once the prediction is complete, the results will be displayed below.')
-
-
-    st.sidebar.title('Input Parameters')
-
-    # Input parameter explanations
-    st.sidebar.markdown('**PRG:** Plasma Glucose')
-    PRG = st.sidebar.number_input('PRG', value=0.0)
-
-    st.sidebar.markdown('**PL:** Blood Work Result 1')
-    PL = st.sidebar.number_input('PL', value=0.0)
-
-    st.sidebar.markdown('**PR:** Blood Pressure Measured')
-    PR = st.sidebar.number_input('PR', value=0.0)
-
-    st.sidebar.markdown('**SK:** Blood Work Result 2')
-    SK = st.sidebar.number_input('SK', value=0.0)
-
-    st.sidebar.markdown('**TS:** Blood Work Result 3')
-    TS = st.sidebar.number_input('TS', value=0.0)
-
-    st.sidebar.markdown('**M11:** BMI')
-    M11 = st.sidebar.number_input('M11', value=0.0)
-
-    st.sidebar.markdown('**BD2:** Blood Work Result 4')
-    BD2 = st.sidebar.number_input('BD2', value=0.0)
-
-    st.sidebar.markdown('**Age:** What is the Age of the Patient: ')
-    Age = st.sidebar.number_input('Age', value=0.0)
-
-    st.sidebar.markdown('**Insurance:** Does the patient have Insurance?')
-    insurance_options = {0: 'NO', 1: 'YES'}
-    Insurance = st.sidebar.radio('Insurance', list(insurance_options.keys()), format_func=lambda x: insurance_options[x])
-
-
-    input_data = [[PRG, PL, PR, SK, TS, M11, BD2, Age, Insurance]]
-
-    if st.sidebar.button('Predict'):
-        with st.spinner("Predicting..."):
-            # Simulate a long-running process
-            progress_bar = st.progress(0)
-            step = 20 # A big step will reduce the execution time
-            for i in range(0, 100, step):
-                time.sleep(0.1)
-                progress_bar.progress(i + step)
-
-            output_df, probabilities, status_icon, sepsis_explanation = predict_sepsis(input_data)
-
-            st.subheader('Prediction Result')
-            prediction_text = "Positive" if status_icon == "✔" else "Negative"
-            st.markdown(f"Prediction: **{prediction_text}**")
-            st.markdown(f"{status_icon} {sepsis_explanation}")
-            st.write(output_df)
-
-            # Add a download button for output_df
-            csv = output_df.to_csv(index=False)
-            b64 = base64.b64encode(csv.encode()).decode()
-            href = f'<a href="data:file/csv;base64,{b64}" download="output.csv">Download Output CSV</a>'
-            st.markdown(href, unsafe_allow_html=True)
-            
-
-            # Plot the probabilities
-            fig, ax = plt.subplots()
-            ax.bar(['Negative', 'Positive'], probabilities)
-            ax.set_xlabel('Sepsis Status')
-            ax.set_ylabel('Probability')
-            ax.set_title('Sepsis Prediction Probabilities')
-            st.pyplot(fig)
-
-            # Print feature importance
-            if hasattr(model, 'coef_'):
-                feature_importances = model.coef_[0]
-                feature_names = ['PRG', 'PL', 'PR', 'SK', 'TS', 'M11', 'BD2', 'Age', 'Insurance']
-
-                importance_df = pd.DataFrame({'Feature': feature_names, 'Importance': feature_importances})
-                importance_df = importance_df.sort_values('Importance', ascending=False)
-
-                st.subheader('Feature Importance')
-                fig, ax = plt.subplots()
-                bars = ax.bar(importance_df['Feature'], importance_df['Importance'])
-                ax.set_xlabel('Feature')
-                ax.set_ylabel('Importance')
-                ax.set_title('Feature Importance')
-                ax.tick_params(axis='x', rotation=45)
-
-                # Add data labels to the bars
-                for bar in bars:
-                    height = bar.get_height()
-                    ax.annotate(f'{height:.2f}', xy=(bar.get_x() + bar.get_width() / 2, height),
-                    xytext=(0, 3),  # 3 points vertical offset
-                    textcoords="offset points",
-                    ha='center', va='bottom')
-                st.pyplot(fig)
-
-            else:
-                st.write('Feature importance is not available for this model.')
-
-            #st.subheader('Sepsis Explanation')
-            #st.markdown(f"{status_icon} {sepsis_explanation}")
-
-
-if __name__ == '__main__':
-    main()
+# Create a function that applies the ML pipeline and makes predictions
+def predict(gender,SeniorCitizen,Partner,Dependents, tenure, PhoneService,MultipleLines,
+                       InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,
+                       Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges):
+
+
+
+    # Create a dataframe with the input data
+    input_df = pd.DataFrame({
+        'gender': [gender],
+        'SeniorCitizen': [SeniorCitizen],
+        'Partner': [Partner],
+        'Dependents': [Dependents],
+        'tenure': [tenure],
+        'PhoneService': [PhoneService],
+        'MultipleLines': [MultipleLines],
+        'InternetService': [InternetService],
+        'OnlineSecurity': [OnlineSecurity],
+        'OnlineBackup': [OnlineBackup],
+        'DeviceProtection': [DeviceProtection],
+        'TechSupport': [TechSupport],
+        'StreamingTV': [StreamingTV],
+        'StreamingMovies': [StreamingMovies],
+        'Contract': [Contract],
+        'PaperlessBilling': [PaperlessBilling],
+        'PaymentMethod': [PaymentMethod],
+        'MonthlyCharges': [MonthlyCharges],
+        'TotalCharges': [TotalCharges]
+        })
+
+# Selecting categorical and numerical columns separately
+    cat_columns = [col for col in input_df.columns if input_df[col].dtype == 'object']
+    num_columns = [col for col in input_df.columns if input_df[col].dtype != 'object']
+
+    # Apply the imputers on the input data
+    input_df_imputed_cat = cat_imputer.transform(input_df[cat_columns])
+    input_df_imputed_num = num_imputer.transform(input_df[num_columns])
+
+    # Encode the categorical columns
+    input_encoded_df = pd.DataFrame(encoder.transform(input_df_imputed_cat).toarray(),
+                                   columns=encoder.get_feature_names_out(cat_columns))
+
+    # Scale the numerical columns
+    input_df_scaled = scaler.transform(input_df_imputed_num)
+    input_scaled_df = pd.DataFrame(input_df_scaled , columns = num_columns)
+
+
+    #joining the cat encoded and num scaled
+    final_df = pd.concat([input_encoded_df, input_scaled_df], axis=1)
+
+    final_df = final_df.reindex(columns=['SeniorCitizen','tenure','MonthlyCharges','TotalCharges',
+     'gender_Female','gender_Male','Partner_No','Partner_Yes','Dependents_No','Dependents_Yes','PhoneService_No',
+     'PhoneService_Yes','MultipleLines_No','MultipleLines_Yes','InternetService_DSL','InternetService_Fiber optic',
+     'InternetService_No','OnlineSecurity_No','OnlineSecurity_Yes','OnlineBackup_No','OnlineBackup_Yes','DeviceProtection_No',
+     'DeviceProtection_Yes','TechSupport_No','TechSupport_Yes','StreamingTV_No','StreamingTV_Yes','StreamingMovies_No',
+     'StreamingMovies_Yes','Contract_Month-to-month','Contract_One year','Contract_Two year','PaperlessBilling_No',
+     'PaperlessBilling_Yes','PaymentMethod_Bank transfer (automatic)','PaymentMethod_Credit card (automatic)','PaymentMethod_Electronic check',
+     'PaymentMethod_Mailed check'])
+
+    # Make predictions using the model
+    predictions = model.predict(final_df)[0]
+    #prediction = model.predict(final_df)[0]
+
+     # Make predictions using the model
+     #predictions = model.predict(final_df)
+
+     # Convert the numpy array to an integer
+     #prediction_label = int(predictions.item())
+
+    prediction_label = "Beware!!! This customer is likely to Churn" if predictions.item() == "Yes" else "This customer is Not likely churn"
+
+
+    return prediction_label
+
+     #return predictions    
+
+
+if 'clicked' not in st.session_state:
+    st.session_state.clicked = False
+
+def click_button():
+    st.session_state.clicked = True
+
+
+st.title("CUSTOMER CHURN PREDICTION APP")
+
+with st.form(key="customer-information"):
+    st.markdown("This app predicts whether a customer will leave your company or not. Enter the details of the customer below to see the result")
+    gender = st.radio('Select your gender', ('male', 'female'))
+    SeniorCitizen = st.radio("Are you a Seniorcitizen; No=0 and Yes=1", ('0', '1'))
+    Partner = st.radio('Do you have Partner', ('Yes', 'No'))
+    Dependents = st.selectbox('Do you have any Dependents?', ('No', 'Yes'))
+    tenure = st.number_input('Lenght of tenure (no. of months with Telco)', min_value=0, max_value=90, value=1, step=1)
+    PhoneService = st.radio('Do you have PhoneService? ', ('No', 'Yes'))
+    MultipleLines = st.radio('Do you have MultipleLines', ('No', 'Yes'))
+    InternetService = st.radio('Do you have InternetService', ('DSL', 'Fiber optic', 'No'))
+    OnlineSecurity = st.radio('Do you have OnlineSecurity?', ('No', 'Yes'))
+    OnlineBackup = st.radio('Do you have OnlineBackup?', ('No', 'Yes'))
+    DeviceProtection = st.radio('Do you have DeviceProtection?', ('No', 'Yes'))
+    TechSupport = st.radio('Do you have TechSupport?', ('No', 'Yes'))
+    StreamingTV = st.radio('Do you have StreamingTV?', ('No', 'Yes'))
+    StreamingMovies = st.radio('Do you have StreamingMovies?', ('No', 'Yes'))
+    Contract = st.selectbox('which Contract do you use?', ('Month-to-month', 'One year', 'Two year'))
+    PaperlessBilling = st.radio('Do you prefer PaperlessBilling?', ('Yes', 'No'))
+    PaymentMethod = st.selectbox('Which PaymentMethod do you prefer?', ('Electronic check', 'Mailed check', 'Bank transfer (automatic)',
+                                        'Credit card (automatic)'))
+    MonthlyCharges = st.number_input("Enter monthly charges (the range should between 0-120)")
+    TotalCharges = st.number_input("Enter total charges (the range should between 0-10.000)")           
+    st.form_submit_button('Predict', on_click=click_button)
+
+    if st.session_state.clicked:
+    # The message and nested widget will remain on the page
+        predict(gender,SeniorCitizen,Partner,Dependents, tenure, PhoneService,MultipleLines,
+                       InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,
+                       Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges)

app_.py

@@ -1,144 +0,0 @@
-import pandas as pd
-from transformers import pipeline
-import streamlit as st
-import datetime
-from huggingface_hub import hf_hub_download
-import joblib
-
-REPO_ID = "AlbieCofie/predict-customer-churn"
-FILENAME = "sklearn_model.joblib"
-
-num_imputer = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="numerical_imputer.joblib")
-)
-
-cat_imputer = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="categorical_imputer.joblib")
-)
-
-encoder = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="encoder.joblib")
-)
-
-scaler = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="scaler.joblib")
-)
-
-model = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="Final_model.joblib")
-)
-
-# Create a function that applies the ML pipeline and makes predictions
-def predict(gender,SeniorCitizen,Partner,Dependents, tenure, PhoneService,MultipleLines,
-                       InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,
-                       Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges):
-
-
-
-    # Create a dataframe with the input data
-    input_df = pd.DataFrame({
-        'gender': [gender],
-        'SeniorCitizen': [SeniorCitizen],
-        'Partner': [Partner],
-        'Dependents': [Dependents],
-        'tenure': [tenure],
-        'PhoneService': [PhoneService],
-        'MultipleLines': [MultipleLines],
-        'InternetService': [InternetService],
-        'OnlineSecurity': [OnlineSecurity],
-        'OnlineBackup': [OnlineBackup],
-        'DeviceProtection': [DeviceProtection],
-        'TechSupport': [TechSupport],
-        'StreamingTV': [StreamingTV],
-        'StreamingMovies': [StreamingMovies],
-        'Contract': [Contract],
-        'PaperlessBilling': [PaperlessBilling],
-        'PaymentMethod': [PaymentMethod],
-        'MonthlyCharges': [MonthlyCharges],
-        'TotalCharges': [TotalCharges]
-        })
-
-# Selecting categorical and numerical columns separately
-    cat_columns = [col for col in input_df.columns if input_df[col].dtype == 'object']
-    num_columns = [col for col in input_df.columns if input_df[col].dtype != 'object']
-
-    # Apply the imputers on the input data
-    input_df_imputed_cat = cat_imputer.transform(input_df[cat_columns])
-    input_df_imputed_num = num_imputer.transform(input_df[num_columns])
-
-    # Encode the categorical columns
-    input_encoded_df = pd.DataFrame(encoder.transform(input_df_imputed_cat).toarray(),
-                                   columns=encoder.get_feature_names_out(cat_columns))
-
-    # Scale the numerical columns
-    input_df_scaled = scaler.transform(input_df_imputed_num)
-    input_scaled_df = pd.DataFrame(input_df_scaled , columns = num_columns)
-
-
-    #joining the cat encoded and num scaled
-    final_df = pd.concat([input_encoded_df, input_scaled_df], axis=1)
-
-    final_df = final_df.reindex(columns=['SeniorCitizen','tenure','MonthlyCharges','TotalCharges',
-     'gender_Female','gender_Male','Partner_No','Partner_Yes','Dependents_No','Dependents_Yes','PhoneService_No',
-     'PhoneService_Yes','MultipleLines_No','MultipleLines_Yes','InternetService_DSL','InternetService_Fiber optic',
-     'InternetService_No','OnlineSecurity_No','OnlineSecurity_Yes','OnlineBackup_No','OnlineBackup_Yes','DeviceProtection_No',
-     'DeviceProtection_Yes','TechSupport_No','TechSupport_Yes','StreamingTV_No','StreamingTV_Yes','StreamingMovies_No',
-     'StreamingMovies_Yes','Contract_Month-to-month','Contract_One year','Contract_Two year','PaperlessBilling_No',
-     'PaperlessBilling_Yes','PaymentMethod_Bank transfer (automatic)','PaymentMethod_Credit card (automatic)','PaymentMethod_Electronic check',
-     'PaymentMethod_Mailed check'])
-
-    # Make predictions using the model
-    predictions = model.predict(final_df)
-
-     # Make predictions using the model
-     #predictions = model.predict(final_df)
-
-     # Convert the numpy array to an integer
-     #prediction_label = int(predictions.item())
-
-    prediction_label = "Beware!!! This customer is likely to Churn" if predictions.item() == "Yes" else "This customer is Not likely churn"
-
-
-    return prediction_label
-
-     #return predictions    
-
-
-if 'clicked' not in st.session_state:
-    st.session_state.clicked = False
-
-def click_button():
-    st.session_state.clicked = True
-
-
-st.title("CUSTOMER CHURN PREDICTION APP")
-
-with st.form(key="customer-information"):
-    st.markdown("This app predicts whether a customer will leave your company or not. Enter the details of the customer below to see the result")
-    gender = st.radio('Select your gender', ('male', 'female'))
-    SeniorCitizen = st.radio("Are you a Seniorcitizen; No=0 and Yes=1", ('0', '1'))
-    Partner = st.radio('Do you have Partner', ('Yes', 'No'))
-    Dependents = st.selectbox('Do you have any Dependents?', ('No', 'Yes'))
-    tenure = st.number_input('Lenght of tenure (no. of months with Telco)', min_value=0, max_value=90, value=1, step=1)
-    PhoneService = st.radio('Do you have PhoneService? ', ('No', 'Yes'))
-    MultipleLines = st.radio('Do you have MultipleLines', ('No', 'Yes'))
-    InternetService = st.radio('Do you have InternetService', ('DSL', 'Fiber optic', 'No'))
-    OnlineSecurity = st.radio('Do you have OnlineSecurity?', ('No', 'Yes'))
-    OnlineBackup = st.radio('Do you have OnlineBackup?', ('No', 'Yes'))
-    DeviceProtection = st.radio('Do you have DeviceProtection?', ('No', 'Yes'))
-    TechSupport = st.radio('Do you have TechSupport?', ('No', 'Yes'))
-    StreamingTV = st.radio('Do you have StreamingTV?', ('No', 'Yes'))
-    StreamingMovies = st.radio('Do you have StreamingMovies?', ('No', 'Yes'))
-    Contract = st.selectbox('which Contract do you use?', ('Month-to-month', 'One year', 'Two year'))
-    PaperlessBilling = st.radio('Do you prefer PaperlessBilling?', ('Yes', 'No'))
-    PaymentMethod = st.selectbox('Which PaymentMethod do you prefer?', ('Electronic check', 'Mailed check', 'Bank transfer (automatic)',
-                                        'Credit card (automatic)'))
-    MonthlyCharges = st.number_input("Enter monthly charges (the range should between 0-120)")
-    TotalCharges = st.number_input("Enter total charges (the range should between 0-10.000)")           
-    st.form_submit_button('Predict', on_click=click_button)
-
-    if st.session_state.clicked:
-    # The message and nested widget will remain on the page
-        predict(gender,SeniorCitizen,Partner,Dependents, tenure, PhoneService,MultipleLines,
-                       InternetService,OnlineSecurity,OnlineBackup,DeviceProtection,TechSupport,StreamingTV,StreamingMovies,
-                       Contract,PaperlessBilling,PaymentMethod,MonthlyCharges,TotalCharges)

app_3.py

@@ -0,0 +1,167 @@
+import streamlit as st
+import pandas as pd
+import joblib
+import matplotlib.pyplot as plt
+from huggingface_hub import hf_hub_download
+import time
+import base64
+from transformers import AutoTokenizer
+
+# Load the pre-trained numerical imputer, scaler, and model using joblib
+
+REPO_ID = "AlbieCofie/predict-customer-churn"
+
+num_imputer = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename="numerical_imputer.joblib")
+)
+
+scaler = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename="scaler.joblib")
+)
+
+model = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename="Final_model.joblib")
+)
+
+# Define a function to preprocess the input data
+def preprocess_input_data(input_data):
+    input_data_df = pd.DataFrame(input_data, columns=['PRG', 'PL', 'PR', 'SK', 'TS', 'M11', 'BD2', 'Age', 'Insurance'])
+    num_columns = input_data_df.select_dtypes(include='number').columns
+
+    input_data_imputed_num = num_imputer.transform(input_data_df[num_columns])
+    input_scaled_df = pd.DataFrame(scaler.transform(input_data_imputed_num), columns=num_columns)
+
+    return input_scaled_df
+
+
+# Define a function to make the sepsis prediction
+def predict_sepsis(input_data):
+    input_scaled_df = preprocess_input_data(input_data)
+    prediction = model.predict(input_scaled_df)[0]
+    probabilities = model.predict_proba(input_scaled_df)[0]
+    sepsis_status = "Positive" if prediction == 1 else "Negative"
+    
+    status_icon = "✔" if prediction == 1 else "✘"  # Red 'X' icon for positive sepsis prediction, green checkmark icon for negative sepsis prediction
+    sepsis_explanation = "Sepsis is a life-threatening condition caused by an infection. A positive prediction suggests that the patient might be exhibiting sepsis symptoms and requires immediate medical attention." if prediction == 1 else "Sepsis is a life-threatening condition caused by an infection. A negative prediction suggests that the patient is not currently exhibiting sepsis symptoms."
+
+    output_df = pd.DataFrame(input_data, columns=['PRG', 'PL', 'PR', 'SK', 'TS', 'M11', 'BD2', 'Age', 'Insurance'])
+    output_df['Prediction'] = sepsis_status
+    output_df['Negative Probability'] = probabilities[0]
+    output_df['Positive Probability'] = probabilities[1]
+
+    return output_df, probabilities, status_icon, sepsis_explanation
+
+# Create a Streamlit app
+def main():
+    st.title('Sepsis Prediction App')
+
+    st.image("Strealit_.jpg")
+
+    # How to use
+    st.sidebar.title('How to Use')
+    st.sidebar.markdown('1. Adjust the input parameters on the left sidebar.')
+    st.sidebar.markdown('2. Click the "Predict" button to initiate the prediction.')
+    st.sidebar.markdown('3. The app will simulate a prediction process with a progress bar.')
+    st.sidebar.markdown('4. Once the prediction is complete, the results will be displayed below.')
+
+
+    st.sidebar.title('Input Parameters')
+
+    # Input parameter explanations
+    st.sidebar.markdown('**PRG:** Plasma Glucose')
+    PRG = st.sidebar.number_input('PRG', value=0.0)
+
+    st.sidebar.markdown('**PL:** Blood Work Result 1')
+    PL = st.sidebar.number_input('PL', value=0.0)
+
+    st.sidebar.markdown('**PR:** Blood Pressure Measured')
+    PR = st.sidebar.number_input('PR', value=0.0)
+
+    st.sidebar.markdown('**SK:** Blood Work Result 2')
+    SK = st.sidebar.number_input('SK', value=0.0)
+
+    st.sidebar.markdown('**TS:** Blood Work Result 3')
+    TS = st.sidebar.number_input('TS', value=0.0)
+
+    st.sidebar.markdown('**M11:** BMI')
+    M11 = st.sidebar.number_input('M11', value=0.0)
+
+    st.sidebar.markdown('**BD2:** Blood Work Result 4')
+    BD2 = st.sidebar.number_input('BD2', value=0.0)
+
+    st.sidebar.markdown('**Age:** What is the Age of the Patient: ')
+    Age = st.sidebar.number_input('Age', value=0.0)
+
+    st.sidebar.markdown('**Insurance:** Does the patient have Insurance?')
+    insurance_options = {0: 'NO', 1: 'YES'}
+    Insurance = st.sidebar.radio('Insurance', list(insurance_options.keys()), format_func=lambda x: insurance_options[x])
+
+
+    input_data = [[PRG, PL, PR, SK, TS, M11, BD2, Age, Insurance]]
+
+    if st.sidebar.button('Predict'):
+        with st.spinner("Predicting..."):
+            # Simulate a long-running process
+            progress_bar = st.progress(0)
+            step = 20 # A big step will reduce the execution time
+            for i in range(0, 100, step):
+                time.sleep(0.1)
+                progress_bar.progress(i + step)
+
+            output_df, probabilities, status_icon, sepsis_explanation = predict_sepsis(input_data)
+
+            st.subheader('Prediction Result')
+            prediction_text = "Positive" if status_icon == "✔" else "Negative"
+            st.markdown(f"Prediction: **{prediction_text}**")
+            st.markdown(f"{status_icon} {sepsis_explanation}")
+            st.write(output_df)
+
+            # Add a download button for output_df
+            csv = output_df.to_csv(index=False)
+            b64 = base64.b64encode(csv.encode()).decode()
+            href = f'<a href="data:file/csv;base64,{b64}" download="output.csv">Download Output CSV</a>'
+            st.markdown(href, unsafe_allow_html=True)
+            
+
+            # Plot the probabilities
+            fig, ax = plt.subplots()
+            ax.bar(['Negative', 'Positive'], probabilities)
+            ax.set_xlabel('Sepsis Status')
+            ax.set_ylabel('Probability')
+            ax.set_title('Sepsis Prediction Probabilities')
+            st.pyplot(fig)
+
+            # Print feature importance
+            if hasattr(model, 'coef_'):
+                feature_importances = model.coef_[0]
+                feature_names = ['PRG', 'PL', 'PR', 'SK', 'TS', 'M11', 'BD2', 'Age', 'Insurance']
+
+                importance_df = pd.DataFrame({'Feature': feature_names, 'Importance': feature_importances})
+                importance_df = importance_df.sort_values('Importance', ascending=False)
+
+                st.subheader('Feature Importance')
+                fig, ax = plt.subplots()
+                bars = ax.bar(importance_df['Feature'], importance_df['Importance'])
+                ax.set_xlabel('Feature')
+                ax.set_ylabel('Importance')
+                ax.set_title('Feature Importance')
+                ax.tick_params(axis='x', rotation=45)
+
+                # Add data labels to the bars
+                for bar in bars:
+                    height = bar.get_height()
+                    ax.annotate(f'{height:.2f}', xy=(bar.get_x() + bar.get_width() / 2, height),
+                    xytext=(0, 3),  # 3 points vertical offset
+                    textcoords="offset points",
+                    ha='center', va='bottom')
+                st.pyplot(fig)
+
+            else:
+                st.write('Feature importance is not available for this model.')
+
+            #st.subheader('Sepsis Explanation')
+            #st.markdown(f"{status_icon} {sepsis_explanation}")
+
+
+if __name__ == '__main__':
+    main()