gobbios/elorating

Animal dominance hierarchies

elorating's Issues

seq.check does not detect NAs in sequence data

seq.check() should check that winner, loser and Date do not contain NAs

elo.seq(init = "bottom") not working as expected

Hi - I've been using the init = "bottom" argument in elo.seq() to calculate Elo Ratings and it doesn't seem to be working as expected. When I've been using the argument, animals entering the hierarchy are not assigned the lowest ratings - they are assigned the average rating. I've attached a pdf of code output to illustrate this. Any and all assistance would be greatly appreciated!
EloSeq-issue.pdf

Error in creatematrix() with single date

creatematrix() fails if the supplied daterange covers only one day, so the following results in a error:

data(adv)
SEQ <- elo.seq(winner = adv$winner, loser = adv$loser, Date = adv$Date)
creatematrix(SEQ, daterange = c("2010-01-26", "2010-01-26"))

add perfomance rating option

Calculate Elo-ratings from a matrix without transforming into a random sequence.

difference between .elo.seq_old and elo.seq

I do not see any difference between .elo.seq_old and elo.seq, however I cannot change the start value when I use elo.seq. The code I wrote and the output is below.

CODE:

res1 <- EloRating:::.elo.seq_old(
winner = season_1011_dates_elo$winner,
loser = season_1011_dates_elo$loser,
Date = season_1011_dates_elo$Date,
draw = season_1011_dates_elo$Draw,
startvalue = 500,
k = 2,
runcheck = TRUE,
progressbar = FALSE
)
summary(res1)

res_elo <- elo.seq(
winner = season_1011_dates_elo$winner,
loser = season_1011_dates_elo$loser,
Date = season_1011_dates_elo$Date,
draw = season_1011_dates_elo$Draw,
startvalue = 500,
k = 2,
runcheck = TRUE,
progressbar = FALSE
)
summary(res_elo)

SUMMARY OUTPUT:

summary(res1)
Elo ratings from 20 individuals
total (mean/median) number of interactions: 380 (38/38)
range of interactions: 38 - 38
date range: 2010-08-14 - 2011-05-22
startvalue: 500
uppon arrival treatment: average
k: 2
proportion of draws in the data set: 0.29

summary(res_elo)
Elo ratings from 20 individuals
total (mean/median) number of interactions: 380 (38/38)
range of interactions: 38 - 38
date range: 2010-08-14 - 2011-05-22
startvalue: 1000
uppon arrival treatment: average
k: 2
proportion of draws in the data set: 0.29

Also, I also noticed that optimizek does not work with .elo.seq_old.

the first interaction occurred before first presence error

When I use the elo.seq function from the gitbug version with presence data available I get an error code that says "for ID (VEL, DOV, VIN, OCH, ASH, ECH, OST) the first interaction occurred before first presence".

I checked my data and this is not the case.
tempelo
ELL ALF DOT VEN ORE VOR VIX VIV OMO VEL DOV VIN OCH ASH ECH OST
recelo 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000
present NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
firstIA 1 1 1 1 14 14 14 35 35 288 496 711 1047 1397 1507 1631
firstpres 1 1 1 1 1 1 1 1 1 283 494 691 1041 1388 1481 1631

When I run the elo.seq with the cran version it does work.

mention in documentation that data sequence is in correct order

ISI returns matrices with missing entries

when using ISI(), the returned matrix (or matrices) may have interactions missing. For example,

data("devries98")
res <- ISI(devries98)[[1]]
res[c("k", "c"), c("k", "c")]
k c
k 0 0
c 0 0

versus the original
devries98[c("k", "c"), c("k", "c")]
k c
k 0 2
c 2 0

randomsequence() spotty presence

Sometimes randomsequence() produces funky results where the presence for some individuals is a mix of 0 and 1, and not 'nice' sequences of 0 and 1. It's a bit hard to reproduce, but happens when group size goes below two individuals due to absence of some individuals.

During the following interactions, IDs were absent according to the presence data:...ERROR

I got the above error message but when I checked my data all of the IDs were present for the listed interactions.