search

covid19-dash / covid-dashboard

Help welcomed if you have expertise in public health web technology, data modeling and munging, or visualization.
https://covid19-dash.github.io/
BSD 3-Clause "New" or "Revised" License
131 stars 41 forks source link

add information on rate of change (such as doubling time) #69

Open poldrack opened 4 years ago

poldrack commented 4 years ago

Currently, in order to compare the rates of change between countries one has to eyeball them. It could be useful to provide a measure such as doubling time (in days) to help better compare rates. This could be shown as fitted rates for each day with observed data, or as the estimated rate for the projection.

GaelVaroquaux commented 4 years ago

The growth rate is computed in the modeling.py script. We should compute the doubling time from it, and store it them in the pickle. After this, we should load them in get_all_data and show them in a the hover of the timeseries plots.

emmanuelle commented 4 years ago

do you think it should appear in the timeseries plot or in the map / table? Both are interesting, in the timeseries what is nice is that you can see if the doubling time changes but it may be hard for people to relate to a doubling time one week ago. We can do both of course.

poldrack commented 4 years ago

I think both is good

On Mon, Mar 23, 2020 at 9:41 AM Emmanuelle Gouillart < notifications@github.com> wrote:

do you think it should appear in the timeseries plot or in the map / table? Both are interesting, in the timeseries what is nice is that you can see if the doubling time changes but it may be hard for people to relate to a doubling time one week ago. We can do both of course.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/covid19-dash/covid-dashboard/issues/69#issuecomment-602717971, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAGUVEE72HXCRAG2CASP2XLRI6GLJANCNFSM4LPJ5H4Q .

-- Russell A. Poldrack Albert Ray Lang Professor of Psychology Professor (by courtesy) of Computer Science Bldg. 420, Jordan Hall Stanford University Stanford, CA 94305

poldrack@stanford.edu http://www.poldracklab.org/

GaelVaroquaux commented 4 years ago

Now that we can only plot the confirmed cases and not the active cases, this because awkward for the countries which have already flattened the curve.

The estimated growth rates are on https://covid19-dash.github.io/modeling_short.html but I hesitate to show them, as they cannot really be interpreted as growth rates.

Maybe an analysis on the new cases, as mentioned #91