Week 1 Assignment

DATA-607, Spring 2019

1. Load Libraries

suppressMessages(library(data.table))
suppressMessages(library(dplyr))
suppressMessages(library(tidyr))
#library(magrittr)

2.Data Import & Column Labeling

2a. Data imports

mushdata <- fread("mush.data", header = FALSE)
keydata <- fread("key.csv", header = TRUE)
mushlabels <- as.character(fread("keycolumns.csv", header = FALSE))

2b. Add Column Names

names(mushdata) <- mushlabels
names(mushdata)

 [1] "edible?"                  "cap-shape"                "cap-surface"             
 [4] "cap-color"                "bruises?"                 "odor"                    
 [7] "gill-attachment"          "gill-spacing"             "gill-size"               
[10] "gill-color"               "stalk-shape"              "stalk-root"              
[13] "stalk-surface-above-ring" "stalk-surface-below-ring" "stalk-color-above-ring"  
[16] "stalk-color-below-ring"   "veil-type"                "veil-color"              
[19] "ring-number"              "ring-type"                "spore-print-color"       
[22] "population"               "habitat"                 

3. Add Data Labels

#warning: Reloading packages may induce an error when running the following code.
#Based on method posted by Jaap Walhout on Stackoverflow (https://stackoverflow.com/questions/49213691/replacing-data-frame-content-with-values-from-another-table-using-matching-colum?rq=1)
mushfinal <- mushdata %>% gather(keycat, letterkey) %>% left_join(., keydata) %>% select(-letterkey) %>% group_by(keycat) %>% mutate(r = row_number()) %>% spread(keycat, keylabel) %>% select(-r)

Joining, by = c("keycat", "letterkey")

head(mushfinal)

Create a Subset

mushsubset1 <- subset(mushfinal, select=c('edible?','gill-attachment','gill-spacing','gill-size','gill-color'))

head(mushsubset1)