0
$\begingroup$

I have the following dataframe:

Year        2000   2010   2011   2012
Feature1    13     45     55     43
Feature2    44     35     80     79
Feature3    40     43     34     30

I want to see which one of these features has the largest change (I don't want to ignore the inner values (2010 and 2011 here)).

Is there any metric or formula for measuring the general slope of each features' change over years or something like that?

$\endgroup$
2
  • 1
    $\begingroup$ Not too sure what you are hoping to measure exactly, but what about computing the sum of absolute changes from year to year for each feature? For example, for Feature 1, it would be $$|45-13|+|55-45|+|43-55|=32+10+12=54.$$ $\endgroup$
    – Minus One-Twelfth
    Jun 28, 2020 at 8:21
  • $\begingroup$ Hi and thanks for your response, I don't want to use lp-norms or similar difference metrics. $\endgroup$
    – Fatemeh Asgarinejad
    Jul 5, 2020 at 19:31

0

Reset to default

You must log in to answer this question.

Browse other questions tagged .