Mushrooms

R Markdown

Load Data

Load mushrooms data from the site, rename columns and change values for cap color, odor, class and habitat

dataFile <-'https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data'
mushrooms <-read.csv(file=dataFile, header=FALSE, sep=",",  )
names(mushrooms)<-col_names
levels(mushrooms$`cap-color`)<-cap_colors
levels(mushrooms$habitat)<-habitats
levels(mushrooms$odor)<-odors
levels(mushrooms$class)<-class

Data Summary

dim(mushrooms)

## [1] 8124   23

##Coulmn Names
names(mushrooms)

##  [1] "class"                    "cap-shape"               
##  [3] "cap-surface"              "cap-color"               
##  [5] "bruises"                  "odor"                    
##  [7] "gill-attachment"          "gill-spacing"            
##  [9] "gill-size"                "gill-color"              
## [11] "stalk-shape"              "stalk-root"              
## [13] "stalk-surface-above-ring" "stalk-surface-below-ring"
## [15] "stalk-color-above-ring"   "stalk-color-below-ring"  
## [17] "veil-type"                "veil-color"              
## [19] "ring-number"              "ring-type"               
## [21] "spore-print-color"        "population"              
## [23] "habitat"

## Summary for cap Color, Odor, Class and Habitat
mushroom_summary <- data.frame(mushrooms$class, mushrooms$`cap-color`, mushrooms$odor, mushrooms$habitat)
summary.data.frame(mushroom_summary)

##   mushrooms.class mushrooms..cap.color.  mushrooms.odor mushrooms.habitat
##  Edible   :4208   green   :2284         musty   :3528   grasses:3148     
##  Poisonous:3916   gray    :1840         creosote:2160   leaves :2148     
##                   cinnamon:1500         pungent : 576   meadows: 832     
##                   yellow  :1072         spicy   : 576   paths  : 292     
##                   white   :1040         almond  : 400   urban  :1144     
##                   brown   : 168         fishy   : 400   waste  : 368     
##                   (Other) : 220         (Other) : 484   woods  : 192

Color Distribution

## 
##    brown     buff cinnamon     gray    green     pink   purple      red 
##      168       44     1500     1840     2284      144       16       16 
##    white   yellow 
##     1040     1072

Odor Distribution

## 
##   almond    anise creosote    fishy     foul    musty     none  pungent 
##      400      192     2160      400       36     3528      256      576 
##    spicy 
##      576

Class Distribution

## 
##    Edible Poisonous 
##      4208      3916

Class and Odor

##            
##             almond anise creosote fishy foul musty none pungent spicy
##   Edible       400     0        0   400    0  3408    0       0     0
##   Poisonous      0   192     2160     0   36   120  256     576   576

Class and Habitat

##            
##             grasses leaves meadows paths urban waste woods
##   Edible       1880   1408     240   256   136    96   192
##   Poisonous    1268    740     592    36  1008   272     0

Class and Cap Color

##            
##             brown buff cinnamon gray green pink purple  red white yellow
##   Edible       48   32      624 1032  1264   56     16   16   720    400
##   Poisonous   120   12      876  808  1020   88      0    0   320    672