File size: 2,998 Bytes
60434a7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
import streamlit as st
import pandas as pd
from predict import InsuranceClaimPredictor
# Initialize the predictor
predictor = InsuranceClaimPredictor('model/insurance_claim_prediction_model.joblib')
# Title of the Streamlit app
st.title('Insurance Claim Prediction')
# Sidebar for user input
st.sidebar.header('User Input Parameters')
def user_input_features():
age = st.sidebar.number_input('Age (in years)', min_value=0, max_value=100, value=40)
sex = st.sidebar.selectbox('Sex', ['male', 'female'])
bmi = st.sidebar.number_input('BMI (Body Mass Index)', min_value=0.0, max_value=50.0, value=25.3)
children = st.sidebar.number_input('Number of Children', min_value=0, max_value=10, value=2)
smoker = st.sidebar.selectbox('Smoker', ['yes', 'no'])
region = st.sidebar.selectbox('Region', ['northeast', 'northwest', 'southeast', 'southwest'])
charges = st.sidebar.number_input('Medical Charges ($)', min_value=0.0, max_value=100000.0, value=2900.0)
data = {'age': age,
'sex': sex,
'bmi': bmi,
'children': children,
'smoker': smoker,
'region': region,
'charges': charges}
features = pd.DataFrame(data, index=[0])
return features
df = user_input_features()
# Button for prediction
if st.sidebar.button('Predict'):
# Make prediction
prediction = predictor.predict(df)
# Display the prediction
if prediction[0] == 1:
st.sidebar.success('This person is likely to make an insurance claim.')
else:
st.sidebar.info('This person is less likely to make an insurance claim.')
# Display user input
st.subheader('User Input Parameters')
# Add descriptions for each input
st.write("""
- **Age**: The age of the individual.
- **Sex**: The gender of the individual.
- **BMI**: Body Mass Index, a measure of body fat based on height and weight.
- **Number of Children**: Number of children or dependents.
- **Smoker**: Whether the individual is a smoker.
- **Region**: The geographical region where the individual resides.
- **Medical Charges**: Annual medical charges billed.
""")
# Demo data
st.subheader('Demo Data')
# Sample data for demo
demo_data = pd.DataFrame({
'age': [23, 45],
'sex': ['female', 'male'],
'bmi': [22.0, 30.0],
'children': [0, 2],
'smoker': ['no', 'yes'],
'region': ['southeast', 'northwest'],
'charges': [2000.0, 12000.0],
'claim': ['No', 'Yes']
})
st.write(demo_data)
# Notifications for analysis
st.subheader('Analysis Dashboard')
claimed_data = demo_data[demo_data['claim'] == 'Yes']
not_claimed_data = demo_data[demo_data['claim'] == 'No']
st.write(f"### Charges Analysis")
st.write(f"- **Average charges for claims made**: ${claimed_data['charges'].mean():.2f}")
st.write(f"- **Average charges for claims not made**: ${not_claimed_data['charges'].mean():.2f}")
|