Read Data
data = read.csv('https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data', header = FALSE)Add Names
names(data) = c('poisonous','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')Take a look and make sure it looks right
head(data)Change factors to strings so that I can replace them without issue
data = data.frame(lapply(data, as.character), stringsAsFactors=FALSE)Going to just take in the factors that have to do with the gills.
keepers = names(data) %in% c('poisonous','gill.attachment','gill.spacing','gill.size','gill.color')
data.gill = data[keepers]Check on new data frame
head(data.gill)Check to see what values we have for the poisonous column
unique(data.gill$poisonous)## [1] "p" "e"replace all values with better descriptions.
data.gill$poisonous = replace(data.gill$poisonous, data.gill$poisonous=='p', 'poisonous')
data.gill$poisonous = replace(data.gill$poisonous, data.gill$poisonous=='e', 'unknown')
data.gill$gill.attachment = replace(data.gill$gill.attachment, data.gill$gill.attachment=='a', 'attached')
data.gill$gill.attachment = replace(data.gill$gill.attachment, data.gill$gill.attachment=='d', 'descending')
data.gill$gill.attachment = replace(data.gill$gill.attachment, data.gill$gill.attachment=='f', 'free')
data.gill$gill.attachment = replace(data.gill$gill.attachment, data.gill$gill.attachment=='n', 'notched')
data.gill$gill.spacing = replace(data.gill$gill.spacing, data.gill$gill.spacing=='c', 'close')
data.gill$gill.spacing = replace(data.gill$gill.spacing, data.gill$gill.spacing=='w', 'crowded')
data.gill$gill.spacing = replace(data.gill$gill.spacing, data.gill$gill.spacing=='d', 'distant')
data.gill$gill.size = replace(data.gill$gill.size, data.gill$gill.size=='b', 'broad')
data.gill$gill.size = replace(data.gill$gill.size, data.gill$gill.size=='n', 'narrow')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='k', 'black')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='n', 'brown')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='b', 'buff')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='h', 'chocolate')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='g', 'gray')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='r', 'green')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='o', 'orange')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='p', 'pink')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='u', 'purple')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='e', 'red')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='w', 'white')
data.gill$gill.color = replace(data.gill$gill.color, data.gill$gill.color=='y', 'yellow')List out the current values for the columns to make sure they were all changed
unique(data.gill$poisonous)## [1] "poisonous" "unknown"unique(data.gill$gill.attachment)## [1] "free" "attached"unique(data.gill$gill.spacing)## [1] "close" "crowded"unique(data.gill$gill.size)## [1] "narrow" "broad"unique(data.gill$gill.color)## [1] "black" "brown" "gray" "pink" "white"
## [6] "chocolate" "purple" "red" "buff" "green"
## [11] "yellow" "orange"