Create app.py

app.py

@@ -0,0 +1,137 @@
+import streamlit as st
+import pandas as pd
+import lightgbm as lgb
+import pickle
+
+# Load the trained LightGBM model
+with open('lgb.pkl', 'rb') as model_file:
+    model = pickle.load(model_file)
+
+# Define mappings
+workclass_map = {
+    'Private': 1,
+    'State-gov': 2,
+    'Federal-gov': 3,
+    'Self-emp-not-inc': 4,
+    'Self-emp-inc': 5,
+    'Local-gov': 6,
+    'Without-pay': 7,
+    'Never-worked': 8,
+    '?': 9
+}
+
+education_ranks = {
+    'Preschool': 1,
+    '1st-4th': 2,
+    '5th-6th': 3,
+    '7th-8th': 4,
+    '9th': 5,
+    '10th': 6,
+    '11th': 7,
+    '12th': 8,
+    'HS-grad': 9,
+    'Some-college': 10,
+    'Assoc-voc': 11,
+    'Assoc-acdm': 12,
+    'Bachelors': 13,
+    'Masters': 14,
+    'Prof-school': 15,
+    'Doctorate': 16
+}
+
+marital_map = {
+    'Married-civ-spouse': 1,
+    'Married-spouse-absent': 1,
+    'Married-AF-spouse': 1,
+    'Widowed': 2,
+    'Divorced': 2,
+    'Separated': 2,
+    'Never-married': 2
+}
+
+occupation_map = {
+    'Exec-managerial': 1,
+    'Machine-op-inspct': 2,
+    'Prof-specialty': 3,
+    'Other-service': 4,
+    'Adm-clerical': 5,
+    'Craft-repair': 6,
+    'Transport-moving': 7,
+    'Handlers-cleaners': 8,
+    'Sales': 9,
+    'Farming-fishing': 10,
+    'Tech-support': 11,
+    'Protective-serv': 12,
+    'Armed-Forces': 13,
+    'Priv-house-serv': 14
+}
+
+relationship_map = {
+    'Not-in-family': 1,
+    'Unmarried': 2,
+    'Own-child': 3,
+    'Other-relative': 4,
+    'Husband': 5,
+    'Wife': 6
+}
+
+income_map = {
+    '<=50K': 0,
+    '>50K': 1
+}
+
+# Define the input fields for the user to provide data
+def get_user_input():
+    age = st.number_input('Age', min_value=0, max_value=120, value=30)
+    workclass = st.selectbox('Workclass', list(workclass_map.keys()))
+    fnlwgt = st.number_input('Fnlwgt', min_value=0, value=100000)
+    education = st.selectbox('Education', list(education_ranks.keys()))
+    education_num = st.number_input('Education Num', min_value=0, max_value=20, value=10)
+    marital_status = st.selectbox('Marital Status', list(marital_map.keys()))
+    occupation = st.selectbox('Occupation', list(occupation_map.keys()))
+    relationship = st.selectbox('Relationship', list(relationship_map.keys()))
+    capital_gain = st.number_input('Capital Gain', min_value=0, value=0)
+    capital_loss = st.number_input('Capital Loss', min_value=0, value=0)
+    hours_per_week = st.number_input('Hours Per Week', min_value=0, max_value=168, value=40)
+
+    user_data = {
+        'age': age,
+        'workclass_rank': workclass_map[workclass],
+        'fnlwgt': fnlwgt,
+        'education_rank': education_ranks[education],
+        'education.num': education_num,
+        'marital_status_binary': marital_map[marital_status],
+        'occupation_rank': occupation_map[occupation],
+        'relationship_rank': relationship_map[relationship],
+        'capital.gain': capital_gain,
+        'capital.loss': capital_loss,
+        'hours.per.week': hours_per_week
+    }
+    
+    features = pd.DataFrame(user_data, index=[0])
+    return features
+
+# Main function to run the app
+def main():
+    st.title('Income Prediction App')
+    st.write('This app predicts whether a person makes over $50K a year based on their demographics and work information.')
+
+    user_input = get_user_input()
+    
+    st.subheader('User Input:')
+    st.write(user_input)
+    
+    prediction = model.predict(user_input)
+    prediction_proba = model.predict_proba(user_input)[:, 1]
+
+    st.subheader('Prediction:')
+    if prediction[0] == 1:
+        st.write('The model predicts: Income > $50K')
+    else:
+        st.write('The model predicts: Income <= $50K')
+
+    st.subheader('Prediction Probability:')
+    st.write(f'Probability of making over $50K: {prediction_proba[0]:.2f}')
+
+if __name__ == '__main__':
+    main()