Hantz_Angrand_HW1

Load essential library

library(plyr)

Load the data

mushroom<-read.csv("https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data", header = FALSE, sep =",")

head(mushroom)

Rename column Headers

colnames(mushroom)<-c("class", "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", "habitats")

mush<-data.frame(mushroom)

head(mush)

Select a subset of the data

mush<-subset(mush, select=c("class","cap.shape", "cap.color","odor", "habitats"))
head(mush)

Modifying the data to make it more user friendly by replacing abbreviations

levels(mush$class)<-c("edible", "poisonous")
levels(mush$class)

## [1] "edible"    "poisonous"

levels(mush$cap.shape)<-c("bell","conical","flat","knobbed","sunken","convex")
levels(mush$cap.shape)

## [1] "bell"    "conical" "flat"    "knobbed" "sunken"  "convex"

levels(mush$cap.color)<-c("buff","cinnamon","red","gray","brown","pink","green","purple","white","yellow")
levels(mush$cap.color)

##  [1] "buff"     "cinnamon" "red"      "gray"     "brown"    "pink"    
##  [7] "green"    "purple"   "white"    "yellow"

levels(mush$odor)<-c("almond","creosote","foul","anise","musty","none","pungent","spicy","fishy")
levels(mush$odor)

## [1] "almond"   "creosote" "foul"     "anise"    "musty"    "none"    
## [7] "pungent"  "spicy"    "fishy"

levels(mush$habitats)<-c("woods","grasses","leaves","meadows","paths","urban","waste")
levels(mush$habitats)

## [1] "woods"   "grasses" "leaves"  "meadows" "paths"   "urban"   "waste"

head(mush)

Group the data by class

edible<-subset(mush,class="edible")
dim(edible)

## [1] 8124    5

summary(edible)

##        class        cap.shape      cap.color         odor     
##  edible   :4208   bell   : 452   brown  :2284   none   :3528  
##  poisonous:3916   conical:   4   gray   :1840   foul   :2160  
##                   flat   :3152   red    :1500   spicy  : 576  
##                   knobbed: 828   yellow :1072   fishy  : 576  
##                   sunken :  32   white  :1040   almond : 400  
##                   convex :3656   buff   : 168   anise  : 400  
##                                  (Other): 220   (Other): 484  
##     habitats   
##  woods  :3148  
##  grasses:2148  
##  leaves : 832  
##  meadows: 292  
##  paths  :1144  
##  urban  : 368  
##  waste  : 192

poisonous<-subset(mush, class="poisonous")
dim(poisonous)

## [1] 8124    5

summary(poisonous)

##        class        cap.shape      cap.color         odor     
##  edible   :4208   bell   : 452   brown  :2284   none   :3528  
##  poisonous:3916   conical:   4   gray   :1840   foul   :2160  
##                   flat   :3152   red    :1500   spicy  : 576  
##                   knobbed: 828   yellow :1072   fishy  : 576  
##                   sunken :  32   white  :1040   almond : 400  
##                   convex :3656   buff   : 168   anise  : 400  
##                                  (Other): 220   (Other): 484  
##     habitats   
##  woods  :3148  
##  grasses:2148  
##  leaves : 832  
##  meadows: 292  
##  paths  :1144  
##  urban  : 368  
##  waste  : 192

Plotting some data

plot(edible$habitats, las=3)

plot(poisonous$habitats, las=3)