File size: 5,668 Bytes
c115711 |
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 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 |
import streamlit as st
import pandas as pd
import numpy as np
import joblib
from sklearn.preprocessing import LabelEncoder
class FraudDetectionApp:
def __init__(self):
self.model = joblib.load('model/only_model.joblib')
# Assuming the model has an attribute 'feature_names_in_' which stores the feature names used during training
self.feature_names = self.model.feature_names_in_ if hasattr(self.model, 'feature_names_in_') else [
'incident_severity', 'insured_hobbies', 'total_claim_amount', 'months_as_customer', 'policy_annual_premium',
'incident_date', 'capital-loss', 'capital-gains', 'insured_education_level', 'incident_city'
]
self.categorical_columns = ['incident_severity', 'insured_hobbies', 'insured_education_level', 'incident_city']
self.encoders = {col: LabelEncoder() for col in self.categorical_columns}
self.fit_encoders()
def fit_encoders(self):
# Example unique values for fitting the encoders
example_data = {
'incident_severity': ['Minor Damage', 'Major Damage', 'Total Loss', 'Trivial Damage'],
'insured_hobbies': ['sleeping', 'reading', 'board-games', 'bungie-jumping', 'base-jumping', 'golf', 'camping', 'dancing', 'skydiving', 'movies', 'hiking', 'yachting', 'paintball', 'chess', 'kayaking', 'polo', 'basketball', 'video-games', 'cross-fit', 'exercise'],
'insured_education_level': ['MD', 'PhD', 'Associate', 'Masters', 'High School', 'College', 'JD'],
'incident_city': ['Columbus', 'Riverwood', 'Arlington', 'Springfield', 'Hillsdale', 'Northbend', 'Northbrook']
}
for col in self.categorical_columns:
self.encoders[col].fit(example_data[col])
def preprocess_single_data(self, data):
if not isinstance(data, pd.DataFrame):
data = pd.DataFrame(data, index=[0])
for col in self.categorical_columns:
if col in data.columns:
data[col] = self.encoders[col].transform(data[col])
# Ensure the column order matches the training data
data = data[self.feature_names]
return data
def predict_single_fraud(self, data):
data_processed = self.preprocess_single_data(data)
prediction = self.model.predict(data_processed)[0]
return prediction
def run(self):
st.title('Insurance Fraud Prediction')
# Input fields
incident_severity = st.selectbox('Incident Severity', ['Minor Damage', 'Major Damage', 'Total Loss', 'Trivial Damage'])
insured_hobbies = st.selectbox('Insured Hobbies', ['sleeping', 'reading', 'board-games', 'bungie-jumping', 'base-jumping', 'golf', 'camping', 'dancing', 'skydiving', 'movies', 'hiking', 'yachting', 'paintball', 'chess', 'kayaking', 'polo', 'basketball', 'video-games', 'cross-fit', 'exercise'])
total_claim_amount = st.number_input('Total Claim Amount')
months_as_customer = st.number_input('Months as Customer')
policy_annual_premium = st.number_input('Policy Annual Premium')
incident_date = st.number_input('Incident Date', min_value=1, max_value=31, step=1)
capital_loss = st.number_input('Capital Loss')
capital_gains = st.number_input('Capital Gains')
insured_education_level = st.selectbox('Insured Education Level', ['MD', 'PhD', 'Associate', 'Masters', 'High School', 'College', 'JD'])
incident_city = st.selectbox('Incident City', ['Columbus', 'Riverwood', 'Arlington', 'Springfield', 'Hillsdale', 'Northbend', 'Northbrook'])
# Collecting user input
new_data_point = {
'incident_severity': incident_severity,
'insured_hobbies': insured_hobbies,
'total_claim_amount': total_claim_amount,
'months_as_customer': months_as_customer,
'policy_annual_premium': policy_annual_premium,
'incident_date': incident_date,
'capital-loss': capital_loss,
'capital-gains': capital_gains,
'insured_education_level': insured_education_level,
'incident_city': incident_city,
}
# Prediction button
if st.button('Predict'):
prediction = self.predict_single_fraud(new_data_point)
if prediction == 0:
st.write('The applied application is not fraud.')
else:
st.write('The applied application is fraud.')
# Generate sample data
if st.button('Generate Sample Data'):
sample_non_fraud = self.generate_sample_data(fraud=False)
sample_fraud = self.generate_sample_data(fraud=True)
st.write("Non-Fraud Sample Data:")
st.write(sample_non_fraud)
st.write("Fraud Sample Data:")
st.write(sample_fraud)
def generate_sample_data(self, fraud=False):
sample_data = {
'incident_severity': ['Major Damage' if fraud else 'Minor Damage'],
'insured_hobbies': ['skydiving' if fraud else 'reading'],
'total_claim_amount': [50000 if fraud else 1000],
'months_as_customer': [1 if fraud else 60],
'policy_annual_premium': [10000 if fraud else 200],
'incident_date': [15],
'capital-loss': [1000 if fraud else 0],
'capital-gains': [5000 if fraud else 0],
'insured_education_level': ['PhD' if fraud else 'College'],
'incident_city': ['Riverwood' if fraud else 'Northbrook']
}
return pd.DataFrame(sample_data)
if __name__ == '__main__':
app = FraudDetectionApp()
app.run()
|