update file

app.py

@@ -1,144 +1,157 @@
-import pandas as pd
-from transformers import pipeline
 import streamlit as st
-import datetime
-from huggingface_hub import hf_hub_download
+import numpy as np
 import joblib
+from sklearn.preprocessing import StandardScaler
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from huggingface_hub import hf_hub_download
 
-REPO_ID = "AlbieCofie/predict-customer-churn"
 
-num_imputer = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="numerical_imputer.joblib")
-)
+REPO_ID = "flokabukie/Credit_Card_Fraud_Detection"
 
-cat_imputer = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="categorical_imputer.joblib")
-)
+# Load the non-anomaly data
+non_anomaly_csv_filename = 'non_anomaly_data.csv'
+non_anomaly_csv_filename = hf_hub_download(repo_id=REPO_ID, filename=non_anomaly_csv_filename)
+non_anomaly_df = pd.read_csv(non_anomaly_csv_filename)
 
-encoder = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="encoder.joblib")
+# Load the Isolation Forest model
+model_filename = "IsolationForest.joblib"
+
+isolation_forest = joblib.load(
+    hf_hub_download(repo_id=REPO_ID, filename=model_filename)
 )
 
+# Load the StandardScaler
+scaler_filename = "StandardScaler.joblib"
+
 scaler = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="scaler.joblib")
+    hf_hub_download(repo_id=REPO_ID, filename=scaler_filename)
 )
 
-model = joblib.load(
-    hf_hub_download(repo_id=REPO_ID, filename="Final_model.joblib")
-)
+st.title("Anomaly Detection App with Isolation Forest")
+
+st.sidebar.title("Input Feature Values")
+transaction_dollar_amount = st.sidebar.slider("Transaction Dollar Amount", min_value=0.0, max_value=10000.0)
+longitude = st.sidebar.slider("Longitude (Long)", min_value=-180.0, max_value=180.0)
+latitude = st.sidebar.slider("Latitude (Lat)", min_value=-90.0, max_value=90.0)
+credit_card_limit = st.sidebar.slider("Credit Card Limit", min_value=0, max_value=50000)
+year = st.sidebar.slider("Year", min_value=2000, max_value=2030)
+month = st.sidebar.slider("Month", min_value=1, max_value=12)
+day = st.sidebar.slider("Day", min_value=1, max_value=31)
+
+submitted = st.sidebar.button("Submit")
 
-# 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)
+if submitted:
+    input_data = {
+        'transaction_dollar_amount': transaction_dollar_amount,
+        'Long': longitude,
+        'Lat': latitude,
+        'credit_card_limit': credit_card_limit,
+        'year': year,
+        'month': month,
+        'day': day
+    }
+
+    selected_columns = pd.DataFrame([input_data])
+
+    # Standardize the input data using the loaded StandardScaler
+    selected_columns_scaled = scaler.transform(selected_columns)
+
+    # Apply Isolation Forest for anomaly detection on the non-anomaly dataset
+    non_anomaly_scores = isolation_forest.decision_function(scaler.transform(non_anomaly_df))
+
+# Apply Isolation Forest for anomaly detection on your single input data
+    your_anomaly_score = isolation_forest.decision_function(selected_columns_scaled)[0]
+
+
+
+    # Calculate the minimum and maximum anomaly scores from non-anomaly data
+    min_non_anomaly_score = np.min(non_anomaly_scores)
+    max_non_anomaly_score = np.max(non_anomaly_scores)
+
+# Add a margin of error for the range
+    margin = 0.5
+    min_threshold = min_non_anomaly_score - margin
+    max_threshold = max_non_anomaly_score + margin
+
+    # Determine if the input data point is an anomaly based on the score
+    #is_anomaly = your_anomaly_score >= np.percentile(non_anomaly_scores, 95)
+
+    # Determine if the input data point is an anomaly based on the score
+    is_anomaly = your_anomaly_score < min_threshold or your_anomaly_score > max_threshold
+
+
+# Print the anomaly status
+    st.subheader("Anomaly Classification")
+    if is_anomaly:
+        st.write("Prediction Result: 🚨 Anomaly Detected!")
+    else:
+        st.write("Prediction Result: ✅ Not Anomaly")
+
+# Create a bar plot to visualize the anomaly score distribution and your data point's score
+    plt.figure(figsize=(8, 5))
+
+# Plot the distribution of anomaly scores from the non-anomaly dataset
+    sns.histplot(non_anomaly_scores, kde=True, color='gray', label='Non-Anomaly Score Distribution')
+
+# Plot your data point's anomaly score
+    plt.axvline(x=your_anomaly_score, color='blue', linestyle='dashed', label='Your Data Point')
+
+# Set labels and title
+    plt.xlabel('Anomaly Score')
+    plt.ylabel('Frequency')
+    plt.title('Anomaly Score Distribution and Your Data Point')
+    plt.legend()
+#plt.grid(True)
+
+# Display the histogram plot
+    st.pyplot(plt)
+
+
+# Explain the results
+    st.write("The input data point has been classified as an anomaly." if is_anomaly
+            else "The input data point is not classified as an anomaly.")
+    st.write("The anomaly score is:", your_anomaly_score)
+    st.write("The threshold for anomaly detection is:", min_threshold, "to", max_threshold)
+
+    # Create a scatter plot for longitude and latitude
+    fig, ax = plt.subplots(figsize=(10, 8))
+
+# Plot non-anomaly data
+    sns.scatterplot(data=non_anomaly_df, x='Long', y='Lat', color='lightgrey', label='Normal 🏙️', ax=ax)
+
+# Plot input data
+    if is_anomaly:
+        ax.scatter(selected_columns['Long'], selected_columns['Lat'], color='red', label='Suspicious 🚩', s=100, marker='x')
+        anomaly_marker = 'Suspicious 🚩'
+    else:
+        ax.scatter(selected_columns['Long'], selected_columns['Lat'], color='green', label='Valid ✅', s=100, marker='o')
+        anomaly_marker = 'Valid ✅'
+
+    ax.set_xlabel("Longitude")
+    ax.set_ylabel("Latitude")
+    ax.set_title("Location Plot: Anomaly Detection 🗺️")
+    ax.legend()
+    ax.grid(True)
+
+# Show the scatter plot in Streamlit
+    st.subheader("Location Plot: Anomaly Detection 🗺️")
+    st.pyplot(fig)
+
+# Explanation based on the anomaly classification
+    st.subheader("Anomaly Classification")
+    if your_anomaly_score < min_threshold or your_anomaly_score > max_threshold:
+        st.write("Prediction Result: 🚨 Anomaly Detected!")
+    else:
+        st.write("Prediction Result: ✅ Not Anomaly")
+
+# Explain the results
+    # Explain the results
+    st.write("The location plot visualizes the anomaly detection result based on longitude and latitude.")
+    if your_anomaly_score < min_threshold or your_anomaly_score > max_threshold:
+        st.write("The input data point is marked as Suspicious 🚩 due to its anomaly score.")
+        st.write("The red 'x' marker indicates a suspicious location.")
+    else:
+        st.write("The input data point is marked as Valid ✅ due to its anomaly score.")
+        st.write("The green 'o' marker indicates a valid location.")

app_.py

@@ -0,0 +1,144 @@
+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"
+
+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)[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_3.py

@@ -1,167 +0,0 @@
-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()

requirements.txt

@@ -1,15 +1,10 @@
-joblib==1.2.0
+streamlit==1.25.0
+numpy==1.23.5
+scikit-learn==1.2.2
+sklearn-pandas==2.2.0
+joblib==1.3.2
 matplotlib==3.7.1
 matplotlib-inline==0.1.6
-numpy==1.24.2
-pandas==1.5.3
-scikit-learn==1.2.2
-scipy==1.10.0
+matplotlib-venn==0.11.9
 seaborn==0.12.2
-streamlit==1.20.0
-fastapi==0.95.1
-uvicorn==0.22.0
-pydantic==1.10.7
-transformers==4.24.0
-tokenizers== 0.13.2
 huggingface_hub==0.11