HW3_mushrooms.Rmd

---
title: "HW3 - Mushrooms"
output: html_document
---
#### Walt Wells - 07.23-07.30.2016

### Prepare Environment and Load Data
```{r warning=FALSE, message=FALSE}
# Set Environment
if (!require("RCurl")) install.packages('RCurl')
if (!require("data.table")) install.packages('data.table')
if (!require("DT")) install.packages('DT')
if (!require("plyr")) install.packages('plyr')

# Import Data
if(!exists("dat")) {
    URL <- "https://raw.githubusercontent.com/wwells/CUNYBridge_R/master/agaricus-lepiota.data"
    x <- getURL(URL)
    dat <- fread(x, header=FALSE)
}

# Change to DF instead of DT
dat <- data.frame(dat)

# Preview
head(dat)
```

### Subset
```{r}
# choose class, cap-shape, cap-surface, cap-color, population, and habitat
##  these decisions are arbitratry for the purposes of this project.   we'd otherwise 
##  want to do some additional data exploration before finalizing our subset
mdat <- dat[,c(1:4, 22, 23)]

# Preview Data
head(mdat)
```

### Rename Columns and Data
``` {r}
# Update vars and colnames by creating new cols
mdat$class <- revalue(mdat$V1, c("e"="edible", "p"="poisonous"))
mdat$class <- factor(mdat$class)
mdat$cshape <- revalue(mdat$V2, c("b"="bell", "c"="conical", "x"="convex",
                                  "f"="flat", "k"="knobbed", "s"="sunken"))
mdat$csurface <- revalue(mdat$V3, c("f"="fibrous", "g"="grooves", "y"="scaly",
                                    "s"="smooth"))
mdat$ccolor <- revalue(mdat$V4, c("n"="brown", "b"="buff", "c"="cinnamon",
                                  "g"="gray", "r"="green", "p"= "pink",
                                  "u"="purple", "e"="red", "w"="white",
                                  "y"="yellow"))
mdat$population <- revalue(mdat$V22, c("a"="abundant", "c"="clustered",
                                       "n"="numerous", "s"="scattered",
                                       "v"="several", "y"="solitary"))
mdat$habitat <- revalue(mdat$V23, c("g"="grasses", "l"="leaves", "m"="meadows",
                                    "p"="paths", "u"="urban", "w"="waste",
                                    "d"="woods"))

# Remove raw columns, once accuracy of renaming assured
mdat <- mdat[, c(7:12)]

# Use datatable to review curated data
datatable(mdat, options = list(pageLength = 5))

```