heirarchial clustering of pokemon by attributes

poke_clusters.R

library(RCurl)
library(reshape2)
library(plyr)
library(ggplot2)

pokemon <- read.csv(text = getURL("https://raw.github.com/veekun/pokedex/master/pokedex/data/csv/pokemon_species.csv", ssl.verifypeer=FALSE))
pokemon_stats <- read.csv(text = getURL("https://raw.github.com/veekun/pokedex/master/pokedex/data/csv/pokemon_stats.csv", ssl.verifypeer=FALSE))
stat_names <- read.csv(text = getURL("https://raw.github.com/veekun/pokedex/master/pokedex/data/csv/stat_names.csv", ssl.verifypeer=FALSE))

pokemon <- ddply(pokemon, .(evolution_chain_id), subset, evolves_from_species_id == max(evolves_from_species_id, na.rm=T))

stat_names <- stat_names[stat_names$local_language_id == 9, c("stat_id", "name")]

pokemon_stats <- merge(pokemon_stats, stat_names)
pokemon_stats <- pokemon_stats[, c("pokemon_id", "base_stat", "name")]

colnames(pokemon_stats) <- c("pokemon_id", "value", "name")
pokemon_stats <- dcast(pokemon_stats, pokemon_id ~ name, mean )

colnames(pokemon_stats)[[1]] <- "id"

pokemon <- merge(pokemon, pokemon_stats)

pokemon <- pokemon[, c("identifier", "Attack", "Defense", "HP", "Special Attack", "Special Defense", "Speed")]



pokemon.scaled <- scale(pokemon[, -1])

hc <- hclust(dist(pokemon.scaled))
plot(hc, labels=pokemon$identifier, hang=-1)

pokemon$groups <- cutree(hc, k=6)

df <- melt(ddply(pokemon[, 2:8], .(groups), numcolwise(mean)), id=c("groups"))

ggplot(df, aes(variable, value, fill=variable)) + geom_bar(stat="identity") + facet_grid(groups ~ .) + coord_flip() + theme(legend.position="none")

pokemon$class <- factor(pokemon$groups, labels=c("Middle Road", "Speed Demons", "Bench", "Hard Knocks", "Meat Shield", "Bulky Attackers"))
pokemon$identifier <- as.character(pokemon$identifier)
split(pokemon$identifier, pokemon$class)

# part 2
v <- function(n) {
  pokemon$groups <- cutree(hc, k=n)
	dd <- ddply(pokemon, .(groups), numcolwise(var))
	return(mean(colMeans(dd[, 2:7], na.rm=T), na.rm=T))
}

dv <- data.frame(n=1:nrow(pokemon), var=sapply(1:nrow(pokemon), function (x) { v(x) }))

ggplot(dv, aes(n, var)) + geom_line()