Project 2 - Data Set 2

// Reading in Data
library(tidyr)
library(dplyr)
library(stringr)
library(knitr)
library(htmltab)

URL <- "https://www.bls.gov/news.release/empsit.t19.htm"

Project6DS3 <- htmltab(doc = URL, which = "//th[text() = 'Industry']/ancestor::table")
head(Project6DS3)

kable(head(Project6DS3), caption = "Table 1. Unitdy Data")

// Cleaning Data
Project6DS2<-tbl_df(Project6DS2)
Project6DS2a <- Project6DS2  %>% gather("RegionMetrics","Values",3:5)
Project6DS2a <- Project6DS2a[2:4]

Project6DS2a <- Project6DS2a %>% group_by(CensusRegion, RegionMetrics) %>% spread(CensusRegion, Values)
colnames(Project6DS2a) <- str_to_title(colnames(Project6DS2a))


kable(head(Project6DS2a), caption="Table 2. Data Cleaned Up and Inverted for Analysis")

#normalizing function built for each column
normalit<-function(m){
   (m - min(m))/(max(m)-min(m))
}

Project6DS3b <- Project6DS3a %>% group_by(Metric) %>% mutate(`Feb.2017(P)` = normalit(`Feb.2017(P)`), `Jan.2017(P)` = normalit(`Jan.2017(P)`), `Dec.2016` = normalit(`Dec.2016`), `Feb.2016` = normalit(`Feb.2016`))

#Method 1
kable(Project6DS3b, caption="Table 3. Normalized Average Earnings by Industry")

#subset each metric, average hourly and average weekly.
AvgHourly <- subset(Project6DS3b, Metric=="Average hourly earnings")
AvgWeekly <- subset(Project6DS3b, Metric=="Average weekly earnings")

par(mfrow=c(1,2))
boxplot(AvgHourly[,c(3:6)],main="Boxplot of Average Hourly", ylab="Normalized Earnings for All Industries", xlab="Periods")
boxplot(AvgWeekly[,c(3:6)],main="Boxplot of Average Weekly", ylab="Normalized Earnings for All Industries", xlab="Periods")