Assignment
Your task is to study the dataset and the associated description of the data (i.e. “data dictionary”). You may need to look around a bit, but it’s there! You should take the data, and create a data frame with a subset of the columns (and if you like rows) in the dataset. You should include the column that indicates edible or poisonous and three or four other columns. You should also add meaningful column names and replace the abbreviations used in the data—for example, in the appropriate column, “e” might become “edible.” Your deliverable is the R code to perform these transformation tasks.
Load Mushroom data from the Web
mushroomData <-
read.csv("https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data",
header=FALSE, stringsAsFactors=FALSE)
str(mushroomData)
## 'data.frame': 8124 obs. of 23 variables:
## $ V1 : chr "p" "e" "e" "p" ...
## $ V2 : chr "x" "x" "b" "x" ...
## $ V3 : chr "s" "s" "s" "y" ...
## $ V4 : chr "n" "y" "w" "w" ...
## $ V5 : chr "t" "t" "t" "t" ...
## $ V6 : chr "p" "a" "l" "p" ...
## $ V7 : chr "f" "f" "f" "f" ...
## $ V8 : chr "c" "c" "c" "c" ...
## $ V9 : chr "n" "b" "b" "n" ...
## $ V10: chr "k" "k" "n" "n" ...
## $ V11: chr "e" "e" "e" "e" ...
## $ V12: chr "e" "c" "c" "e" ...
## $ V13: chr "s" "s" "s" "s" ...
## $ V14: chr "s" "s" "s" "s" ...
## $ V15: chr "w" "w" "w" "w" ...
## $ V16: chr "w" "w" "w" "w" ...
## $ V17: chr "p" "p" "p" "p" ...
## $ V18: chr "w" "w" "w" "w" ...
## $ V19: chr "o" "o" "o" "o" ...
## $ V20: chr "p" "p" "p" "p" ...
## $ V21: chr "k" "n" "n" "k" ...
## $ V22: chr "s" "n" "n" "s" ...
## $ V23: chr "u" "g" "m" "u" ...
kable(head(mushroomData))
| p |
x |
s |
n |
t |
p |
f |
c |
n |
k |
e |
e |
s |
s |
w |
w |
p |
w |
o |
p |
k |
s |
u |
| e |
x |
s |
y |
t |
a |
f |
c |
b |
k |
e |
c |
s |
s |
w |
w |
p |
w |
o |
p |
n |
n |
g |
| e |
b |
s |
w |
t |
l |
f |
c |
b |
n |
e |
c |
s |
s |
w |
w |
p |
w |
o |
p |
n |
n |
m |
| p |
x |
y |
w |
t |
p |
f |
c |
n |
n |
e |
e |
s |
s |
w |
w |
p |
w |
o |
p |
k |
s |
u |
| e |
x |
s |
g |
f |
n |
f |
w |
b |
k |
t |
e |
s |
s |
w |
w |
p |
w |
o |
e |
n |
a |
g |
| e |
x |
y |
y |
t |
a |
f |
c |
b |
n |
e |
c |
s |
s |
w |
w |
p |
w |
o |
p |
k |
n |
g |
Add Column Headers
names(mushroomData)[1]<-"EdibleOrPoisonous"
names(mushroomData)[2]<-"CapShape"
names(mushroomData)[3]<-"CapSurface"
names(mushroomData)[4]<-"CapColor"
names(mushroomData)[5]<-"Bruises"
names(mushroomData)[6]<-"Odor"
names(mushroomData)[7]<-"GillAttachment"
names(mushroomData)[8]<-"GillSpacing"
names(mushroomData)[9]<-"FillSize"
names(mushroomData)[10]<-"GillColor"
names(mushroomData)[11]<-"StalkShape"
names(mushroomData)[12]<-"StalkRoot"
names(mushroomData)[13]<-"StalkSurfaceAboveRing"
names(mushroomData)[14]<-"StalkSurfaceBelowRing"
names(mushroomData)[15]<-"StalkColorAboveRing"
names(mushroomData)[16]<-"StalkColorBelowRing"
names(mushroomData)[17]<-"VielType"
names(mushroomData)[18]<-"VeilColor"
names(mushroomData)[19]<-"RingNumber"
names(mushroomData)[20]<-"RingType"
names(mushroomData)[21]<-"SporePrintColor"
names(mushroomData)[22]<-"Population"
names(mushroomData)[23]<-"Habitat"
kable( head(mushroomData) )
| p |
x |
s |
n |
t |
p |
f |
c |
n |
k |
e |
e |
s |
s |
w |
w |
p |
w |
o |
p |
k |
s |
u |
| e |
x |
s |
y |
t |
a |
f |
c |
b |
k |
e |
c |
s |
s |
w |
w |
p |
w |
o |
p |
n |
n |
g |
| e |
b |
s |
w |
t |
l |
f |
c |
b |
n |
e |
c |
s |
s |
w |
w |
p |
w |
o |
p |
n |
n |
m |
| p |
x |
y |
w |
t |
p |
f |
c |
n |
n |
e |
e |
s |
s |
w |
w |
p |
w |
o |
p |
k |
s |
u |
| e |
x |
s |
g |
f |
n |
f |
w |
b |
k |
t |
e |
s |
s |
w |
w |
p |
w |
o |
e |
n |
a |
g |
| e |
x |
y |
y |
t |
a |
f |
c |
b |
n |
e |
c |
s |
s |
w |
w |
p |
w |
o |
p |
k |
n |
g |
Subsetting columns that may determine edibility
mushroomData <- mushroomData[,c( "EdibleOrPoisonous", "CapSurface", "CapColor", "GillColor", "Odor" )]
kable( head(mushroomData) )
| p |
s |
n |
k |
p |
| e |
s |
y |
k |
a |
| e |
s |
w |
n |
l |
| p |
y |
w |
n |
p |
| e |
s |
g |
k |
n |
| e |
y |
y |
n |
a |
Change abbreviations to meaningful names
mushroomData$EdibleOrPoisonous[mushroomData$EdibleOrPoisonous =="e"] <- "edible"
mushroomData$EdibleOrPoisonous[mushroomData$EdibleOrPoisonous =="p"] <- "poisonous"
mushroomData$CapSurface[mushroomData$CapSurface =="f"] <- "fibrous"
mushroomData$CapSurface[mushroomData$CapSurface =="g"] <- "grooves"
mushroomData$CapSurface[mushroomData$CapSurface =="y"] <- "scaly"
mushroomData$CapSurface[mushroomData$CapSurface =="s"] <- "smooth"
mushroomData$CapColor[mushroomData$CapColor =="n"] <- "brown"
mushroomData$CapColor[mushroomData$CapColor =="b"] <- "buff"
mushroomData$CapColor[mushroomData$CapColor =="c"] <- "cinnamon"
mushroomData$CapColor[mushroomData$CapColor =="g"] <- "gray"
mushroomData$CapColor[mushroomData$CapColor =="r"] <- "green"
mushroomData$CapColor[mushroomData$CapColor =="p"] <- "pink"
mushroomData$CapColor[mushroomData$CapColor =="u"] <- "purple"
mushroomData$CapColor[mushroomData$CapColor =="e"] <- "red"
mushroomData$CapColor[mushroomData$CapColor =="w"] <- "white"
mushroomData$CapColor[mushroomData$CapColor =="y"] <- "yellow"
mushroomData$CapColor[mushroomData$CapColor =="f"] <- "no"
mushroomData$GillColor[mushroomData$GillColor =="k"] <- "black"
mushroomData$GillColor[mushroomData$GillColor =="n"] <- "brown"
mushroomData$GillColor[mushroomData$GillColor =="b"] <- "buff"
mushroomData$GillColor[mushroomData$GillColor =="h"] <- "chocolate"
mushroomData$GillColor[mushroomData$GillColor =="g"] <- "gray"
mushroomData$GillColor[mushroomData$GillColor =="r"] <- "green"
mushroomData$GillColor[mushroomData$GillColor =="o"] <- "orange"
mushroomData$GillColor[mushroomData$GillColor =="p"] <- "pink"
mushroomData$GillColor[mushroomData$GillColor =="u"] <- "purple"
mushroomData$GillColor[mushroomData$GillColor =="e"] <- "red"
mushroomData$GillColor[mushroomData$GillColor =="w"] <- "white"
mushroomData$GillColor[mushroomData$GillColor =="y"] <- "yellow"
mushroomData$Odor[mushroomData$Odor =="a"] <- "almond"
mushroomData$Odor[mushroomData$Odor =="l"] <- "anise"
mushroomData$Odor[mushroomData$Odor =="c"] <- "creosote"
mushroomData$Odor[mushroomData$Odor =="y"] <- "fishy"
mushroomData$Odor[mushroomData$Odor =="f"] <- "foul"
mushroomData$Odor[mushroomData$Odor =="m"] <- "musty"
mushroomData$Odor[mushroomData$Odor =="n"] <- "none"
mushroomData$Odor[mushroomData$Odor =="p"] <- "pungent"
mushroomData$Odor[mushroomData$Odor =="s"] <- "spicy"
datatable(mushroomData)