Assignment1

DATA 607: Assignment1 – Loading Data into a Data Frame - Mushroom Data

See raw date under “https://github.com/igukusamuel/DATA-607-Assignment-1/blob/master/Mushroom%20Data.csv”

Load data into a data frame named MD directly from the original url.

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

Review the column titles.

names(mushroom[c(1:5),c(1:5)])

## [1] "V1" "V2" "V3" "V4" "V5"

Review the data frame structure as well as a summary of the data items.

summary(mushroom[c(1:5),c(1:5)])

##  V1    V2    V3          V4    V5   
##  e:3   b:1   f:0   w      :2   f:1  
##  p:2   c:0   g:0   g      :1   t:4  
##        f:0   s:4   n      :1        
##        k:0   y:1   y      :1        
##        s:0         b      :0        
##        x:4         c      :0        
##                    (Other):0

Review first 5 rows of the data frame

head(mushroom[c(1:5),c(1:5)])

##   V1 V2 V3 V4 V5
## 1  p  x  s  n  t
## 2  e  x  s  y  t
## 3  e  b  s  w  t
## 4  p  x  y  w  t
## 5  e  x  s  g  f

Review last 5 rows in the data frame to confirm that the data has loaded correctly.

tail(mushroom, 5)

##      V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 V13 V14 V15 V16 V17 V18 V19
## 8120  e  k  s  n  f  n  a  c  b   y   e   ?   s   s   o   o   p   o   o
## 8121  e  x  s  n  f  n  a  c  b   y   e   ?   s   s   o   o   p   n   o
## 8122  e  f  s  n  f  n  a  c  b   n   e   ?   s   s   o   o   p   o   o
## 8123  p  k  y  n  f  y  f  c  n   b   t   ?   s   k   w   w   p   w   o
## 8124  e  x  s  n  f  n  a  c  b   y   e   ?   s   s   o   o   p   o   o
##      V20 V21 V22 V23
## 8120   p   b   c   l
## 8121   p   b   v   l
## 8122   p   b   c   l
## 8123   e   w   v   l
## 8124   p   o   c   l

Rename the columns (note the default naming of columns is V1, V2,….., V23)

names(mushroom) <- c("classes", "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")

Confirm name change

names(mushroom[c(1:5),c(1:5)])

## [1] "classes"     "cap-shape"   "cap-surface" "cap-color"   "bruises?"

Replace abbreviations used in column named classes

levels(mushroom$classes) [levels(mushroom$classes)=="p"] <- "poisonous"
levels(mushroom$classes) [levels(mushroom$classes)=="e"] <- "edible"

Confirm abbreviations change in column named classes

mushroom[c(1:5),c(1:5)]

##     classes cap-shape cap-surface cap-color bruises?
## 1 poisonous         x           s         n        t
## 2    edible         x           s         y        t
## 3    edible         b           s         w        t
## 4 poisonous         x           y         w        t
## 5    edible         x           s         g        f