Module 6: Apply 5

Import data

# csv file
data <- read.csv("../00_data/Salaries.csv")
data

# excel file
data <- read_excel("../00_data/Salaries.xlsx")
data

Apply the following dplyr verbs to your data

Filter rows

filter(data, rank == "Prof")

Arrange rows

arrange(data, yrs.since.phd)

Select columns

# Select columns by name
select(data, salary, yrs.service, yrs.since.phd)

Add columns

mutate(data, salary.per.year = salary / yrs.service)

Summarize by groups

data %>%
    
    # Group by Rank
    group_by(rank) %>%
    
    # Calculate Years between Phd and Start of Service
    summarise(yrs.between.phd.and.service = mean(yrs.since.phd - yrs.service, na.rm = TRUE)) %>%
    
    # Sort it
    arrange(yrs.between.phd.and.service)