From 549ddd39a8b9eb9789c9b44e4a96569bf08ec26c Mon Sep 17 00:00:00 2001 From: Gertjan van den Burg Date: Fri, 7 Jun 2019 12:57:08 +0100 Subject: Minor clarifications in demo --- app/main/demo.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'app') diff --git a/app/main/demo.py b/app/main/demo.py index ff13351..afb7f61 100644 --- a/app/main/demo.py +++ b/app/main/demo.py @@ -76,8 +76,10 @@ DEMO_DATA = { Don't worry if you weren't exactly correct on the first try. The goal of this introduction is to familiarise yourself with - time series data and with change point detection in - particular.""" + time series data and with change point detection in particular. + Note that in general we consider the change point to be the + point where the new behaviour starts, not the last point of the + current behaviour.""" ) ) }, @@ -212,7 +214,7 @@ DEMO_DATA = { """ What we see here is a change in *trend*. Changes in trend are not always change points: gradual changes in direction are - common and should not be considered *abrupt* changes. + common and should not be considered to be *abrupt* changes. For trend changes it's not always easy to figure out exactly where the change occurs, so it's harder to get it exactly -- cgit v1.2.3