Fixing the column names and then renaming the elements in four of the columns.
##Loading file:
mush<-read.table("https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data",header = FALSE,sep = ",")
###renaming columns
colnames(mush)<-c("edibility","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")
#setting the columns as ordered factors so that I can then rename them without turning everything into strings
#I don't feel like ordering all 23 columns, writing a function to do it for me
orderme <- function(factcol){
factcol<-factor(factcol, levels(factcol),ordered=TRUE)
return(factcol)
}
##there's probably a neater and faster way to do this, but this works
for (i in 1:23) {
mush[,i]<-orderme(mush[,i])
}
levels(mush$edibility)<-c("edible","poisonous")
levels(mush$`cap-shape`)<-c("bell","conical","flat","knobbed","sunken","convex")
levels(mush$`cap-surface`)<-c("fiborous","grooves","smooth","scaly")
levels(mush$odor)<-c("almond","creosote","foul","anise","musty","none","pungent","spicy","fishy")
summary(mush)
## edibility cap-shape cap-surface cap-color bruises
## edible :4208 bell : 452 fiborous:2320 n :2284 f:4748
## poisonous:3916 conical: 4 grooves : 4 g :1840 t:3376
## flat :3152 smooth :2556 e :1500
## knobbed: 828 scaly :3244 y :1072
## sunken : 32 w :1040
## convex :3656 b : 168
## (Other): 220
## odor gill-attachment gill-spacing gill-size gill-color
## none :3528 a: 210 c:6812 b:5612 b :1728
## foul :2160 f:7914 w:1312 n:2512 p :1492
## spicy : 576 w :1202
## fishy : 576 n :1048
## almond : 400 g : 752
## anise : 400 h : 732
## (Other): 484 (Other):1170
## stalk-shape stalk-root stalk-surface-above-ring stalk-surface-below-ring
## e:3516 ?:2480 f: 552 f: 600
## t:4608 b:3776 k:2372 k:2304
## c: 556 s:5176 s:4936
## e:1120 y: 24 y: 284
## r: 192
##
##
## stalk-color-above-ring stalk-color-below-ring veil-type veil-color
## w :4464 w :4384 p:8124 n: 96
## p :1872 p :1872 o: 96
## g : 576 g : 576 w:7924
## n : 448 n : 512 y: 8
## b : 432 b : 432
## o : 192 o : 192
## (Other): 140 (Other): 156
## ring-number ring-type spore-print-color population habitat
## n: 36 e:2776 w :2388 a: 384 d:3148
## o:7488 f: 48 n :1968 c: 340 g:2148
## t: 600 l:1296 k :1872 n: 400 l: 832
## n: 36 h :1632 s:1248 m: 292
## p:3968 r : 72 v:4040 p:1144
## b : 48 y:1712 u: 368
## (Other): 144 w: 192