1

I am doing a research about outlier detection in Multivariate Elliptically Shaped Numerical data and I have searched a lot for a matching dataset yet I couldn't find any. Any help will be appreciated in finding such dataset.

I mean if you visualize the data (in two dimensions) you would see the data points form an elliptic shape.

Improve this question
3
  • 3
    If you can explain in plain English what "multivariate elliptically shaped numerical data" means, that would increase the chances of getting good recommendations.
    – csk
    Commented Dec 16, 2019 at 18:38
  • Sure, I do mean if you actually visualize the data (two dimension) you would see the data points form an elliptic shape.
    – R_10
    Commented Jan 10, 2020 at 14:47
  • The planets move in nearly planar approximately elliptical orbits, but I'm not sure if that counts as "data", since it's highly predictable.
    – user3856
    Commented Jan 20, 2020 at 15:18

1 Answer 1

Reset to default
1

This answer may not fully answer your question.

Have you seen the Plot a confidence ellipse of a two-dimensional dataset? Here they use plotting an ellipse for a two-dimensional dataset.

or if you are looking for data points to plot

you can use the parametric equation of an ellipse and generate random datapoints

x = u+a.cos(t) ; y = v+b.sin(t)

import numpy as np
from matplotlib import pyplot as plt
from math import pi

u=1.     #x-position of the center
v=0.5    #y-position of the center
a=2.     #radius on the x-axis
b=1.5    #radius on the y-axis

t = np.linspace(0, 2*pi, 100)
plt.plot( u+a*np.cos(t) , v+b*np.sin(t) )
plt.grid(color='lightgray',linestyle='--')
plt.show()

Which gives :

enter image description here

Improve this answer

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.