import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns

df = pd.read_csv('travel_insurance.csv') df.head()

df.info() df.describe(include='all')

df_dummy = pd.get_dummies(df, drop_first=True) # Rename columns for readability; attempted to keep the same naming convention used df_dummy.columns = ['Age', 'AnnualIncome(k$)', 'FamilyMembers', 'HealthIssues', 'Insured', 'PrivateSector', 'Graduate', 'FrequentFlyer', 'TravelledAbroad'] # Converting AnnualIncome to be in k$ df_dummy['AnnualIncome(k$)'] = df_dummy['AnnualIncome(k$)'] / 1000 # Data after column rename df_dummy.describe().round(3)

sns.countplot(x='Insured', data=df_dummy) plt.title('Distribution of Insured Status') plt.ylabel('Count') plt.xticks([0, 1], ['No', 'Yes'])

df_dummy.hist('Age') plt.title('Distribution of Age') plt.xlabel('Age') plt.ylabel('Count') plt.grid(b=None) plt.savefig('age_distribution.png')

age_28 = df_dummy[(df_dummy['Age'] == 28)] age_28.describe().round(3)

plt.hist('AnnualIncome(k$)', data=not_28, label='Other ages', alpha=0.4) plt.hist('AnnualIncome(k$)', data=age_28, label='28 year olds', alpha=0.4) plt.legend()

# Separate by insured vs uninsured insured = df_dummy[df_dummy['Insured'] == 1] uninsured = df_dummy[df_dummy['Insured'] == 0] # Drop the insured columns insured = insured.drop(columns='Insured') uninsured = uninsured.drop(columns='Insured')

plt.hist('Age', data=df_dummy[df_dummy['Insured']==0], alpha=0.5, label='Uninsured') plt.hist('Age', data=df_dummy[df_dummy['Insured']==1], alpha=0.5, label='Insured') plt.title('Distribution of Age by Insured Status') plt.xlabel('Age') plt.ylabel('Count') plt.legend() plt.savefig('age_distribution_insured.png')

plt.hist('AnnualIncome(k$)', data=uninsured, alpha=0.5, label='Uninsured') plt.hist('AnnualIncome(k$)', data=insured, alpha=0.5, label='Insured') plt.title('Distribution of Income by Insured Status') plt.xlabel('Annual Income (Thousands of $)') plt.ylabel('Count') plt.legend() plt.savefig('age_distribution_income.png')

# Annual income by insured status scatterplot sns.scatterplot(x='Age', y='AnnualIncome(k$)', hue='Insured', data=df_dummy, legend=True) plt.legend(labels=['Uninsured', 'Insured']) plt.title('Age to Income, Colored by Insured Status') # plt.savefig('age_income_scatterplot.png')

sns.catplot(x='TravelledAbroad', y='AnnualIncome(k$)', data=df_dummy, alpha=0.3, col='Insured', row='FrequentFlyer')

under_130k = df_dummy[df_dummy['AnnualIncome(k$)'] < 1300] over_130k = df_dummy[df_dummy['AnnualIncome(k$)'] > 1300]

under_130k.describe().round(3)

over_130k.describe().round(3)

sns.heatmap(df_dummy.corr(), annot=True) plt.title('Correlation Heatmap - All') plt.savefig('Correlation Heatmap - All.png')

sns.catplot(x='TravelledAbroad', y='AnnualIncome(k$)', hue='Insured', kind='box', data=df_dummy) plt.ylabel('Annual Income (Thousands of $)') plt.title('Travelled Abroad vs Income by Insured Status') plt.xticks([0, 1], ['No', 'Yes']) plt.savefig('ta_income.png')

sns.catplot(x='FrequentFlyer', y='AnnualIncome(k$)', hue='Insured', kind='box', data=df_dummy) plt.ylabel('Annual Income (Thousands of $)') plt.xticks([0, 1], ['No', 'Yes']) plt.title('Frequent Flyers vs Income by Insured Status') plt.savefig('ff_income.png')

sns.catplot(x='PrivateSector', y='AnnualIncome(k$)', hue='Insured', kind='box', data=df_dummy) plt.ylabel('Annual Income (Thousands of $)') plt.xlabel('Sector') plt.xticks([0, 1], ['Government', 'Private']) plt.title('Private Sector vs Income by Insured Status') plt.savefig('privatesec_income.png')

sns.heatmap(insured.corr(), annot=True) plt.title('Correlation Heatmap - Insured') plt.savefig('insured_heatmap.png')

sns.heatmap(uninsured.corr(), annot=True) plt.title('Correlation Heatmap - Uninsured') plt.savefig('uninsured_heatmap.png')

insured.describe().round(3)

uninsured.describe().round(3)