Assignment 1 - Loading Data into a Data Frame

fileUrl <- "https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data"

# To download the datset: 
#download.file(fileUrl, destfile = "Mushrooms.csv")
#list.files("Mushrooms.csv")

head(read.csv(fileUrl, sep = ",", header=FALSE))

##   V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13 V14 V15 V16 V17 V18 V19 V20
## 1  p  x  s  n  t  p  f  c  n   k   e   e   s   s   w   w   p   w   o   p
## 2  e  x  s  y  t  a  f  c  b   k   e   c   s   s   w   w   p   w   o   p
## 3  e  b  s  w  t  l  f  c  b   n   e   c   s   s   w   w   p   w   o   p
## 4  p  x  y  w  t  p  f  c  n   n   e   e   s   s   w   w   p   w   o   p
## 5  e  x  s  g  f  n  f  w  b   k   t   e   s   s   w   w   p   w   o   e
## 6  e  x  y  y  t  a  f  c  b   n   e   c   s   s   w   w   p   w   o   p
##   V21 V22 V23
## 1   k   s   u
## 2   n   n   g
## 3   n   n   m
## 4   k   s   u
## 5   n   a   g
## 6   k   n   g

library(dplyr)

# Rename columns and recode entries for the selected five columns

shrooms <- 
  read.csv(fileUrl, sep = ",", header=FALSE) %>%
  rename(
     Edible = V1,
     CapShape = V2, 
     CapSurface = V3, 
     CapColor = V4, 
     Bruises = V5, 
     Odor = V6, 
     GillAtt = V7, 
     GillSpacing = V8,
     GillSize = V9, 
     GillColor = V10, 
     StalkShape = V11, 
     StalkRoot = V12, 
     StalkSurfaceAboveRing = V13,
     StalkSurfaceBelowRing = V14, 
     StalkColorAboveRing = V15, 
     StalkColorBelowRing = V16, 
     VeilType = V17,
     VeilColor = V18, 
     RingNumber = V19, 
     RingType = V20, 
     SporePrintColor = V21, 
     Population = V22, 
     Habitat = V23) %>%
  mutate(
    Edible     = recode(Edible, 
                        e = "edible", 
                        p = "poinsonous"),
    CapShape   = recode(CapShape, 
                        b="bell", 
                        c="conical",
                        x="convex", 
                        f="flat",
                        k="knobbed",
                        s="sunken"),
    CapSurface = recode(CapSurface, 
                        f='fibrous', 
                        g='grooves', 
                        y='scaly', 
                        s='smooth'),
    Odor       = recode(Odor, 
                        a='almond', 
                        l='anise', 
                        c='creosote', 
                        y='fishy',
                        f='foul',
                        m='musty',
                        n='none',
                        p='pungent',
                        s='spicy'),
    Population = recode(Population, 
                        a='abundant',
                        c='clustered',
                        n='numerous',
                        s='scattered',
                        v='several',
                        y='solitary')) %>% 
  select(Edible, CapShape, CapSurface, Odor, Population)

head(shrooms)

##       Edible CapShape CapSurface    Odor Population
## 1 poinsonous   convex     smooth pungent  scattered
## 2     edible   convex     smooth  almond   numerous
## 3     edible     bell     smooth   anise   numerous
## 4 poinsonous   convex      scaly pungent  scattered
## 5     edible   convex     smooth    none   abundant
## 6     edible   convex      scaly  almond   numerous