Update app.py

app.py

@@ -7,54 +7,62 @@ import joblib
 # Load the saved model
 #model = joblib.load("HistGradientBoostingClassifier.joblib")
 
-# Load the trained model
-model = joblib.load("HistGradientBoostingClassifier.joblib")
-
-# Define categorical columns based on the dataset
-categorical_columns = ['job', 'marital', 'education', 'default', 'housing', 'loan', 'poutcome']
-
-# Sidebar for user input
-st.sidebar.header("Client Input Features")
-def user_input_features():
-    job = st.sidebar.selectbox('Job', bank_df_cleaned['job'].unique())
-    marital = st.sidebar.selectbox('Marital', bank_df_cleaned['marital'].unique())
-    education = st.sidebar.selectbox('Education', bank_df_cleaned['education'].unique())
-    default = st.sidebar.selectbox('Default', bank_df_cleaned['default'].unique())
-    housing = st.sidebar.selectbox('Housing Loan', bank_df_cleaned['housing'].unique())
-    loan = st.sidebar.selectbox('Personal Loan', bank_df_cleaned['loan'].unique())
-    poutcome = st.sidebar.selectbox('Previous Outcome', bank_df_cleaned['poutcome'].unique())
-    log_campaign = st.sidebar.slider('Log Campaign', float(bank_df_cleaned['log_campaign'].min()), float(bank_df_cleaned['log_campaign'].max()))
-    log_duration = st.sidebar.slider('Log Duration', float(bank_df_cleaned['log_duration'].min()), float(bank_df_cleaned['log_duration'].max()))
-    log_age = st.sidebar.slider('Log Age', float(bank_df_cleaned['log_age'].min()), float(bank_df_cleaned['log_age'].max()))
-    campaign_duration_interaction = log_campaign * log_duration
-    contact_is_cellular = st.sidebar.selectbox('Contact is Cellular', [0, 1])
-    total_loans = st.sidebar.selectbox('Total Loans', [0, 1, 2])
-
-    data = {
-        'job': job,
-        'marital': marital,
-        'education': education,
-        'default': default,
-        'housing': housing,
-        'loan': loan,
-        'poutcome': poutcome,
-        'log_campaign': log_campaign,
-        'log_duration': log_duration,
-        'log_age': log_age,
-        'campaign_duration_interaction': campaign_duration_interaction,
-        'contact_is_cellular': contact_is_cellular,
-        'total_loans': total_loans
-    }
-    return pd.DataFrame(data, index=[0])
-
-df = user_input_features()
-
-
-# Predict
-prediction = model.predict(df)
-prediction_proba = model.predict_proba(df)
-
-# Display result
-st.header("Term Deposit Subscription Prediction")
-st.write(f"Prediction: {'Yes' if prediction[0] == 1 else 'No'}")
-st.write(f"Prediction Probability: {prediction_proba[0]}")
+import streamlit as st
+import joblib
+import pandas as pd
+
+# Load the model
+model = joblib.load('HistGradientBoostingClassifier.joblib')
+
+# Title of the app
+st.title('Bank Term Deposit Prediction App')
+
+# Input fields for user data
+age = st.number_input('Age', min_value=18, max_value=100, value=30)
+job = st.selectbox('Job', ['admin.', 'blue-collar', 'entrepreneur', 'housemaid', 'management', 'retired', 'self-employed', 'services', 'student', 'technician', 'unemployed', 'unknown'])
+marital = st.selectbox('Marital Status', ['divorced', 'married', 'single', 'unknown'])
+education = st.selectbox('Education', ['primary', 'secondary', 'tertiary', 'unknown'])
+default = st.selectbox('Default', ['no', 'yes'])
+balance = st.number_input('Balance', value=0)
+housing = st.selectbox('Housing Loan', ['no', 'yes'])
+loan = st.selectbox('Personal Loan', ['no', 'yes'])
+contact = st.selectbox('Contact Communication Type', ['cellular', 'telephone', 'unknown'])
+day = st.number_input('Last Contact Day', min_value=1, max_value=31, value=15)
+month = st.selectbox('Last Contact Month', ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul', 'aug', 'sep', 'oct', 'nov', 'dec'])
+duration = st.number_input('Last Contact Duration', value=0)
+campaign = st.number_input('Number of Contacts Performed', value=1)
+pdays = st.number_input('Number of Days Passed After Last Contact', value=-1)
+previous = st.number_input('Number of Contacts Performed Before', value=0)
+poutcome = st.selectbox('Outcome of Previous Marketing Campaign', ['failure', 'nonexistent', 'success'])
+
+# Create a dataframe from user input
+data = {
+    'age': [age],
+    'job': [job],
+    'marital': [marital],
+    'education': [education],
+    'default': [default],
+    'balance': [balance],
+    'housing': [housing],
+    'loan': [loan],
+    'contact': [contact],
+    'day': [day],
+    'month': [month],
+    'duration': [duration],
+    'campaign': [campaign],
+    'pdays': [pdays],
+    'previous': [previous],
+    'poutcome': [poutcome]
+}
+
+input_df = pd.DataFrame(data)
+
+# Predict the outcome
+if st.button('Predict'):
+    prediction = model.predict(input_df)
+    if prediction[0] == 1:
+        st.success('The client is likely to subscribe for a term deposit.')
+    else:
+        st.error('The client is unlikely to subscribe for a term deposit.')
+
+