bestFitSlope.py~

from statistics import mean
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import style

style.use('fivethirtyeight')
#a regression line is just like a straight line (same as best fit line)

xs = np.array([1,2,3,4,5,6], dtype=np.float64)
ys = np.array([5,4,6,5,6,7], dtype=np.float64)

#finding m for best fit slope and y for intercept in eq y = mx + b
def best_fit_slopeIntercept(xs,ys):
    m = ( (mean(xs) * mean(ys)) - mean(xs*ys) ) / ( mean(xs)**2 - mean(xs**2) )
    b = mean(ys) - m*mean(xs)
    return m,b

m,b = best_fit_slopeIntercept(xs,ys)

print(m,b)

#do mx+b for each x in xs
regressionLine = [(m*x)+b for x in xs]

#going to predict the y value where x = 8
predictX = 8
predictY = (m*predictX)+b

plt.scatter(xs,ys)
plt.scatter(predictX,predictY, color='red')
plt.plot(xs, regressionLine)
plt.show()


# using coefficient of determination or squared error to see how good our prediction is
#sqaured error is the dist between our point and our line squared
#squared since we want pos values and if point is above line then it would be a neg value


print("done")