# Feedback for the US Medical Insurance Costs

Here is my portfolio project. It seems basic but I just wanted some feedback on the coding as well as the analysis. Overall the project was pretty basic. Nothing too challenging occurred and it was a good chance to brush up on some information.

I couldn’t get the Jupyter notebook to save as a PDF so I will just include my code below.

import pandas as pd insurance = pd.read_csv("insurance.csv") print(insurance.head()) import numpy as np ave_age = np.average(insurance.age) ave_bmi = np.average(insurance.bmi) ave_children = np.average(insurance.children) ave_charge = np.average(insurance.charges) print(ave_age) print(ave_bmi) print(ave_children) print(ave_charge) pivot_sex = insurance.pivot_table(index = ['sex'], values = ['charges'], aggfunc = {'mean', 'std'}) print(pivot_sex) pivot_region = insurance.pivot_table(index = ['region'], values = ['charges'], aggfunc = {'mean', 'std'}) print(pivot_region) insurance['age_range'] = ['0-19' if age < 20 else '20-29' if age < 30 else '30-39' if age < 40 else '40-49' if age < 50 else '50-59' if age < 60 else '60-69' if age < 70 else '70+' for age in insurance.age] print(insurance.head()) pivot_age = insurance.pivot_table(index = ['age_range'], values = ['charges'], aggfunc = {'mean', 'std','count'}) print(pivot_age) from matplotlib import pyplot as plt plt.scatter(insurance.age, insurance.charges) plt.show() print(np.corrcoef(insurance.age, insurance.charges)) plt.scatter(insurance.bmi, insurance.charges) plt.show() print(np.corrcoef(insurance.bmi, insurance.charges))