andrewbtran

#Simple Pivot table to count number of employees per Department
Department_Workers <- data.frame(table(earnings$DEPARTMENT.NAME))

#Sort it
Department_Workers <- Department_Workers[order(-Department_Workers$Freq),]

#Rename Columns
colnames(Department_Workers) <- c("Department", "Employees")

#Check it

andrewbtran

##DATA TO COLUMNS IN R
#Create new column based on NAME column by deleting after comma
earnings$Last.Name <- sub(",.*","",earnings$NAME)
earnings$First.Name <- sub(".*,","",earnings$NAME)

#Create Middle name column based on First.Name column by deleting before space

#This makes an array out of the total number of observations in earnings
earnings_list <- 1:nrow(earnings)

andrewbtran

#Calculations on columns
earnings_total <- sum(earnings$TOTAL.EARNINGS)
earnings_avg <- mean(earnings$TOTAL.EARNINGS)
earnings_median <- median(earnings$TOTAL.EARNINGS)

andrewbtran

#Filter out a column (in R, it's called "subset")
fire_dept <- subset(earnings, DEPARTMENT.NAME=="Boston Fire Department")

andrewbtran

#Create new column with a formula (Convert OT column into numeric first)
earnings$OVERTIME <- gsub("\\$", "", earnings$OVERTIME)
earnings$OVERTIME <- as.numeric(earnings$OVERTIME)

#FORMULA TIME (If the columns were numbers in the first place, you could skip the steps above)
earnings$Total.minus.OT <- earnings$TOTAL.EARNINGS - earnings$OVERTIME

andrewbtran

#Sort by column TOTAL.EARNINGS descending
earnings <- earnings[order(-earnings$TOTAL.EARNINGS),]

andrewbtran

#Change column to number format (first you have to strip out the $)
#The $ is a special character
earnings$TOTAL.EARNINGS <- gsub("\\$", "", earnings$TOTAL.EARNINGS)

#Function to change the format to numeric
earnings$TOTAL.EARNINGS <- as.numeric(earnings$TOTAL.EARNINGS)

andrewbtran

# Investigate the structure of the dataframe
str(earnings)

andrewbtran

# Look at the first five rows in the Console
head(earnings)

# Alternatively, to look at the last five rows
foot(earnings

andrewbtran

# How many rows? 
nrow(earnings)