Regression Line Plotting Python

Question

I am attempting to plot a regression line based on the below. This code works; however it plots the regression line to the right of the scatter plot.

My question is how do we get the regression line to plot correctly. I borrowed the plotting code from this website.

http://matthiaseisen.com/pp/patterns/p0170/

import numpy.linalg
import matplotlib.pyplot as plt

def regression_model():
    L_1 = numpy.array([38.83, 37.8, 34.41, 30.95, 23.00, 31.75, 36.59, 41.15])
    y_d = [1,2,3,4,5,6,7,8]
    n=len(L_1)

    B=numpy.array(y_d)
    A=numpy.array(([[L_1[j], 1] for j in range(n)]))
    X=numpy.linalg.lstsq(A,B)[0]
    a=X[0]; b=X[1]
    print ("Line is: y=",a,"x+",b)
    r_9 = a * L_1[7] + 4.92
    print ('Predicited value at period 9 is ' + str(r_9) +  ' using regression')

    fig, ax = plt.subplots()
    fit = numpy.polyfit(y_d, L_1, deg=1)
    ax.plot(L_1, fit[0] * L_1 + fit[1], color='red')
    ax.scatter(y_d, L_1)
    plt.show()

I think you want y_d on the x axis, so: ax.plot(y_d, fit[0] * L_1 + fit[1], color='red') — user2314737
– user2314737, Commented Dec 12, 2017 at 12:41

Norrius · Accepted Answer · 2017-12-12 20:35:02Z

1

You plotted that line against your Y-axis L_1, whereas what you need is the X-axis y_d. We need a numpy array for that to work, but you already have one:

fit = numpy.polyfit(y_d, L_1, deg=1)
ax.plot(B, fit[0] * B + fit[1], color='red')

answered Dec 12, 2017 at 20:35

Norrius

7,9795 gold badges46 silver badges52 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Regression Line Plotting Python

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related