Regression – How to program the Best Fit Line
Next part of the equation works out the y intercept…
So Y intercept (b) equals the mean of the Ys minus the slope (m) times the mean of the Xs…easy.
# Import Libs from statistics import mean import numpy as np import matplotlib.pyplot as plt # To set charts to save as images we need to change the default behaviour from matplotlib import style # inport style to change default behaviour of plot style.use('ggplot') # use ggplot # Define values xs = np.array([1,2,3,4,5,6], dtype=np.float64) # dtype lets you set the data type. Not needed for this example but useful in future ys = np.array([5,4,6,5,6,7], dtype=np.float64) def best_fit_slope_and_intercept(xs, ys): # defining function to calculate slope (m) - passing values of xs and ys m = ( ((mean(xs)*mean(ys)) - mean(xs * ys)) / # bracket space at the start and space slash at the end allows for a carridge return in the code ((mean(xs)**2)-mean(xs**2))) ## **2 raises to the power of 2 b = mean(ys) - (m * mean(xs)) return m, b # add in b to be returned as well as m m, b = best_fit_slope_and_intercept(xs,ys) # define both usinf the function print(m, b) #calculate the line regression_line = [(m*x)+b for x in xs] # one line for loop to create the line for illustration #plot the data plt.scatter(xs, ys) plt.plot(xs, regression_line) plt.savefig('ML_Tutorial9.png', bbox_inches='tight') #Sets the output to save an image plt.show() # exports the image