Week 9 Practice Notebooks

# Import NumPy and matplotlib.pyplot import numpy as np import pandas as pd from matplotlib import pyplot as plt

# Read in the data for age, bmi and insurance charges in separate arrays. # Print out to check filename='insurance.csv' age=np.loadtxt(filename,usecols=0,delimiter=',',skiprows=1) print(age) bmi=np.loadtxt(filename,usecols=2,delimiter=',',skiprows=1) print(bmi) charges=np.loadtxt(filename,usecols=6,delimiter=',',skiprows=1) print(charges)

[19. 18. 28. ... 18. 21. 61.]
[27.9  33.77 33.   ... 36.85 25.8  29.07]
[16884.924   1725.5523  4449.462  ...  1629.8335  2007.945  29141.3603]

# print out the number of data instances print(len(age))

# plot charges vs age and add labels to axis and title plt.scatter(age,charges) plt.xlabel('Age') plt.ylabel('Charges')

# plot charges vs BMI; add axis labels and plot title plt.scatter(bmi,charges) plt.xlabel('BMI') plt.ylabel('Charges')

# Import NumPy and matplotlib.pyplot import numpy as np import matplotlib.pyplot as plt

# Read in the data for bmi and insurance charges in separate arrays. # Print out to check # filename='insurance.csv' bmi=np.loadtxt(filename,usecols=2,delimiter=',',skiprows=1) print(bmi) charges=np.loadtxt(filename,usecols=6,delimiter=',',skiprows=1) print(charges)

# Fit a line using linear regression coeff=np.polyfit(bmi,charges,1) f = np.poly1d(coeff) print(coeff)

[ 393.8730308  1192.93720896]

# Plot data and line on same graph plt.plot(bmi,charges,'ro') bmi_min=np.min(bmi) bmi_max=np.max(bmi) xx=np.linspace(bmi_min,bmi_max,2) yy=f(xx) plt.plot(xx,yy,'b') plt.show()

# Fit a parabola to data parab_coeff=np.polyfit(bmi,charges,2) g = np.poly1d(parab_coeff)

# Plot data and parabola on same graph plt.plot(bmi,charges,'ro') xxx=np.linspace(bmi_min,bmi_max) yyy=g(xxx) plt.plot(xxx,yyy,'b') plt.plot()