Last active
July 20, 2018 11:38
-
-
Save newton-migosi/df736ab094da29bc7c679a042bff88a3 to your computer and use it in GitHub Desktop.
Plotting scatter plot and line of best fit using python (turtle and math modules). Run the code online: https://trinket.io/python/d43cc2dddf
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
44 71 | |
79 37 | |
78 24 | |
41 76 | |
19 12 | |
19 32 | |
28 36 | |
22 58 | |
89 92 | |
91 6 | |
53 7 | |
27 80 | |
14 34 | |
8 81 | |
80 19 | |
46 72 | |
83 96 | |
88 18 | |
96 48 | |
77 67 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import turtle | |
import math | |
def main(datafile): | |
dataset = retrieveData(datafile) | |
wn = turtle.Screen() | |
wn.setworldcoordinates(0,0,1,1) | |
kurt = turtle.Turtle() | |
plotRegression(kurt, dataset) | |
def retrieveData(filename): | |
data = [] | |
with open(filename, 'r') as datafile: | |
for line in datafile: | |
datapoint = tuple([int(i) for i in line.split()]) | |
data.append(datapoint) | |
return data | |
def plotRegression(t, dataset): | |
plotPoints(t, dataset) | |
m, c = bestfit(dataset) | |
plotLine(t, m, c) | |
def plotPoints(t, dataset): | |
t.up() | |
for datapoint in dataset: | |
point = tuple([cord/100 for cord in datapoint]) | |
t.goto(*point); t.dot() | |
t.goto(0,0); t.down() | |
def plotLine(t, m, c): | |
t.up(); t.goto(0, c); t.down() | |
angle = math.degrees(math.atan(m)) | |
t.seth(angle) | |
while t.xcor() < 1 and t.ycor() < 1: | |
t.forward(1) | |
def bestfit(dataset): | |
average = lambda a : sum(a)/len(a) | |
x_vals, y_vals = zip(*dataset) | |
sum_of_products = sum([x*y for x, y in dataset]) | |
sum_of_x_squares = sum([x*x for x in x_vals]) | |
x_mean = average(x_vals) | |
y_mean = average(y_vals) | |
n = len(dataset) | |
m = ((sum_of_products - (n * x_mean * y_mean))/ | |
(sum_of_x_squares - (n * x_mean ** 2))) | |
c = (y_mean - (m * x_mean))/100 | |
return m, c | |
if __name__ == '__main__': | |
main('labdata.txt') | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment