DATA 607 Assignment 1

Get Data & Names

MushroomData <- as.data.frame(read.csv(url("https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data"), header = F))

names(MushroomData) <- c(
"classes",
"cap-shape",
"cap-surface",
"cap-color",
"bruises?",
"odor",
"gill-attachment",
"gill-spacing",
"gill-size",
"gill-color",
"stalk-shape",
"stalk-root",
"stalk-surface-above-ring",
"stalk-surface-below-ring",
"stalk-color-above-ring",
"stalk-color-below-ring",
"veil-type",
"veil-color",
"ring-number",
"ring-type",
"spore-print-color",
"population",
"habitat")

Subset Data

CondensedMushroomData <- MushroomData[, c("classes", "odor", "stalk-root", "population", "habitat")]

Recode Data

CondensedMushroomData$classes <- as.character(CondensedMushroomData$classes)
CondensedMushroomData$population <- as.character(CondensedMushroomData$population)
CondensedMushroomData$odor <- as.character(CondensedMushroomData$odor)
CondensedMushroomData$habitat <- as.character(CondensedMushroomData$habitat)
CondensedMushroomData$`stalk-root` <- as.character(CondensedMushroomData$`stalk-root`)


CondensedMushroomData$classes[CondensedMushroomData$classes == "e"] <- "edible"
CondensedMushroomData$classes[CondensedMushroomData$classes == "p"] <- "poisonous"

CondensedMushroomData$population[CondensedMushroomData$population == "a"] <- "abundant"
CondensedMushroomData$population[CondensedMushroomData$population == "c"] <- "clustered"
CondensedMushroomData$population[CondensedMushroomData$population == "n"] <- "numerous"
CondensedMushroomData$population[CondensedMushroomData$population == "s"] <- "scattered"
CondensedMushroomData$population[CondensedMushroomData$population == "v"] <- "several"
CondensedMushroomData$population[CondensedMushroomData$population == "y"] <- "solitary"

CondensedMushroomData$odor[CondensedMushroomData$odor == "a"] <- "almond"
CondensedMushroomData$odor[CondensedMushroomData$odor == "l"] <- "anise"
CondensedMushroomData$odor[CondensedMushroomData$odor == "c"] <- "creosote"
CondensedMushroomData$odor[CondensedMushroomData$odor == "y"] <- "fishy"
CondensedMushroomData$odor[CondensedMushroomData$odor == "f"] <- "foul"
CondensedMushroomData$odor[CondensedMushroomData$odor == "m"] <- "musty"
CondensedMushroomData$odor[CondensedMushroomData$odor == "n"] <- "none"
CondensedMushroomData$odor[CondensedMushroomData$odor == "p"] <- "pungent"
CondensedMushroomData$odor[CondensedMushroomData$odor == "s"] <- "spicy"

CondensedMushroomData$habitat[CondensedMushroomData$habitat == "g"] <- "grasses"
CondensedMushroomData$habitat[CondensedMushroomData$habitat == "l"] <- "leaves"
CondensedMushroomData$habitat[CondensedMushroomData$habitat == "m"] <- "meadows"
CondensedMushroomData$habitat[CondensedMushroomData$habitat == "p"] <- "paths"
CondensedMushroomData$habitat[CondensedMushroomData$habitat == "u"] <- "urban"
CondensedMushroomData$habitat[CondensedMushroomData$habitat == "w"] <- "waste"
CondensedMushroomData$habitat[CondensedMushroomData$habitat == "d"] <- "woods"

CondensedMushroomData$`stalk-root`[CondensedMushroomData$`stalk-root` == "b"] <- "bulbous"
CondensedMushroomData$`stalk-root`[CondensedMushroomData$`stalk-root` == "c"] <- "club"
CondensedMushroomData$`stalk-root`[CondensedMushroomData$`stalk-root` == "u"] <- "cup"
CondensedMushroomData$`stalk-root`[CondensedMushroomData$`stalk-root` == "e"] <- "equal"
CondensedMushroomData$`stalk-root`[CondensedMushroomData$`stalk-root` == "z"] <- "rhizomorphs"
CondensedMushroomData$`stalk-root`[CondensedMushroomData$`stalk-root` == "r"] <- "rootes"
CondensedMushroomData$`stalk-root`[CondensedMushroomData$`stalk-root` == "?"] <- "missing"

(classes: edible=e, poisonous=p) 21. population: abundant=a,clustered=c,numerous=n, scattered=s,several=v,solitary=y 22. habitat: grasses=g,leaves=l,meadows=m,paths=p, urban=u,waste=w,woods=d 5. odor: almond=a,anise=l,creosote=c,fishy=y,foul=f, musty=m,none=n,pungent=p,spicy=s 11. stalk-root: bulbous=b,club=c,cup=u,equal=e, rhizomorphs=z,rooted=r,missing=?