Mage spec scaling

Fetching the data

Data is grabbed from WarcraftLogs via their API. We get the top 1k parses per spec/encounter/difficulty.

Source is at https://github.com/cheald/warcraftlogs-parses

$ API_KEY=your_key_here ruby grabber.rb shaman

Once we have the JSON files, we use a small script to boil them down into a CSV:

$ API_KEY=your_key_here ruby distill.rb mage

This results in the csv/mage.csv that we then consume in R.

Once in R, we load it up:

library(reshape2)
library(ggplot2)
library(dplyr)
library(broom)
data <- read.csv("csv/mage.csv")
data$date <- as.Date(data$date)
cutoff_date = "2016-10-15"

Filtering and plotting

Then we define a function that can be used to filter the dataset to a particular encounter and difficulty. It also performs outlier filtering - for each 5-ilvl bucket, for each spec, we compute the 95th percentile of DPS, then remove any parses from the dataset for that ilvl/spec above that cutoff.

get_encounter_data <- function(encounter_name, difficulty_name, dataset, cutoff=c(0.05, 0.95), bucket_size=1, min_ilvl=855, max_ilvl=875) {
  specs <- unique(dataset$spec)
  d <- filter(dataset, ilvl >= min_ilvl, ilvl <= max_ilvl, encounter == encounter_name, difficulty == difficulty_name, date >= cutoff_date)
  for(bucket in seq(800, 900, by=bucket_size)) {
    for(f_spec in specs) {
      q <- quantile(d[d$spec == f_spec & d$ilvl >= bucket & d$ilvl < bucket + bucket_size,]$dps, cutoff)
      if(!is.na(q[1])) {
        d <- filter(d, !(spec == f_spec & ilvl >= bucket & ilvl < bucket + bucket_size & (dps > q[2] | dps < q[1])))
      }
    }
  }
  return(d)
}

Plotting the data is straightforward. Here we plot both boxplots for each spec/ilvl bucket, as well as a smoothed moving average and a linear trendline.

plot_encounter <- function(encounter_name, difficulty_name, dataset=data, bucket_size=2, cutoff=c(0.05, 0.95)) {
  encounter_data <- get_encounter_data(encounter_name, difficulty_name, dataset=dataset, bucket_size=bucket_size, cutoff=cutoff)
  long_data <- melt(encounter_data, id.vars=c("spec", "ilvl"), measure.vars=c("dps"))
  p <- ggplot(data=long_data, aes(x=ilvl, y=value, group=spec, colour=spec)) +
    geom_boxplot(aes(group=interaction(spec, floor(ilvl/bucket_size) * bucket_size))) +
    geom_smooth() + # loess fit
    geom_smooth(linetype = "dashed", method = "lm", se = FALSE) + # linear fit
    labs(y="DPS", x="iLevel", title=paste("Performance:", encounter_name, difficulty_name))
  print(p)
  cat('\r\n\r\n')
  
  p <- ggplot(data=long_data, aes(x=ilvl, group=spec, colour=spec, fill=spec)) + geom_bar(position="dodge") +
    labs(y="Parses", x="iLevel", title=paste("Parses:", encounter_name, difficulty_name))
  print(p)
  cat('\r\n\r\n')
}

Results

plot_encounter("nythendra", "Normal")

plot_encounter("nythendra", "Heroic")

plot_encounter("nythendra", "Mythic")

plot_encounter("ursoc", "Normal")

plot_encounter("ursoc", "Heroic")

plot_encounter("ursoc", "Mythic")

plot_encounter("elerethe_renferal", "Normal")

plot_encounter("elerethe_renferal", "Heroic")

plot_encounter("elerethe_renferal", "Mythic")

plot_encounter("il_gynoth__heart_of_corruption", "Normal")

plot_encounter("il_gynoth__heart_of_corruption", "Heroic")

plot_encounter("il_gynoth__heart_of_corruption", "Mythic")

plot_encounter("dragons_of_nightmare", "Normal")

plot_encounter("dragons_of_nightmare", "Heroic")

plot_encounter("dragons_of_nightmare", "Mythic")

plot_encounter("cenarius", "Normal")

plot_encounter("cenarius", "Heroic")

plot_encounter("cenarius", "Mythic")

plot_encounter("xavius", "Normal")

plot_encounter("xavius", "Heroic")

plot_encounter("xavius", "Mythic")

Scaling

So we have the raw (smoothed) damage progressions, but how about scaling?

plot_dps_gain <- function(encounter, difficulty, dataset=data, bucket_size=1, cutoff=c(0.05, 0.95)) {
  d <- dataset[dataset$encounter == encounter & dataset$difficulty == difficulty & dataset$ilvl <= 870 & dataset$date >= cutoff_date, ]
  d <- aggregate(d$dps, by=list(ilvl=d$ilvl, spec=d$spec), FUN=mean)
  d$dps <- d$x
  d <- d[order(d$ilvl),]
  d$diff <- ave(d$dps, factor(d$spec), FUN=function(x) c(NA, diff(x)))
  d <- filter(d, !is.na(diff))
  ggplot(data=d, aes(x=ilvl, y=diff, group=interaction(spec, encounter), colour=spec)) + geom_smooth(se=FALSE, fullrange=TRUE) +
    labs(y="DPS gain per tier", x="iLevel", title=paste(encounter, difficulty, sep = " ")) + coord_cartesian(ylim = c(0, 15000))
}
# Commented fights have too little data to produce anything useful
plot_dps_gain("nythendra", "Normal")

plot_dps_gain("nythendra", "Heroic")

plot_dps_gain("nythendra", "Mythic")

plot_dps_gain("ursoc", "Normal")

plot_dps_gain("ursoc", "Heroic")

plot_dps_gain("ursoc", "Mythic")

plot_dps_gain("elerethe_renferal", "Normal")

plot_dps_gain("elerethe_renferal", "Heroic")

plot_dps_gain("elerethe_renferal", "Mythic")

plot_dps_gain("il_gynoth__heart_of_corruption", "Normal")

plot_dps_gain("il_gynoth__heart_of_corruption", "Heroic")

# plot_dps_gain("il_gynoth__heart_of_corruption", "Mythic")
plot_dps_gain("dragons_of_nightmare", "Normal")

plot_dps_gain("dragons_of_nightmare", "Heroic")

# plot_dps_gain("dragons_of_nightmare", "Mythic")
plot_dps_gain("cenarius", "Normal")

plot_dps_gain("cenarius", "Heroic")

# plot_dps_gain("cenarius", "Mythic")
plot_dps_gain("xavius", "Normal")

plot_dps_gain("xavius", "Heroic")

# plot_dps_gain("xavius", "Mythic")

Finally, here’s a really blunt linear regression of each encounter, with the scaling factor (slope of the regression line) plotted:

d <- data
m <- d %>% group_by(spec, encounter) %>% do(tidy(lm(dps ~ ilvl, data=.)))
slopes <- m[m$term == "ilvl",]
slopes$spec <- factor(slopes$spec, levels = slopes$spec[order(slopes$estimate)])

duplicated levels in factors are deprecated

ggplot(data=slopes, aes(x=encounter, y=estimate, group=interaction(spec, encounter), reorder=estimate, fill=spec)) + geom_bar(position="dodge", stat="identity") +
  labs(y="DPS gain/ilvl", x="Encounter", title="DPS scaling per ilvl: Overall")