Class Instructions for 3/22/2017 - dplyr practice

03212017.txt

## RUN ALL THIS SYNTAX BEFORE WE START
## This will install and load all the packages you need for class today. 

ipak <- function(pkg){
    new.pkg <- pkg[!(pkg %in% installed.packages()[, "Package"])]
    if (length(new.pkg)) 
        install.packages(new.pkg, dependencies = TRUE)
    sapply(pkg, require, character.only = TRUE)
}

packages <- c("ggplot2", "dplyr", "car", "plotly")
ipak(packages)

## STOP AND WAIT FOR ME

salary <- data.frame("name" =c("Bill Gates", "Warren Buffett", "Donald Trump", "Bob", "Steve", "Lisa", "Karen", "David Glassman", "Ben", "Piper", "Hope"), 
                  money = c(10000000,12000000,2000000, 42000,35000,54000,27500,400000,33000, 75000, 87000))
                  
salary$gender <- c("M", "M", "M", "M", "M", "F", "F", "M", "M", "F", "F")

## Let's do that group_by command exercise again. It should work this time. 

## Now, I've found a basic dataset of baseball players
bball <- read.csv(url("https://raw.githubusercontent.com/ryanburge/pls2003_sp17/master/dplyr.csv"))

## Some sample commands
group_by() - What variable to you want to group your analysis by? 
arrange() - Arrange things in an order if you want to do it reverse it: arrange(dataset, desc(variable))
filter() - You can use == or <= or !=. If it's a word remember to surround it by quotation marks
summarise() - You are creating a new dataset, usually used with group_by(). summarise(avg = mean(variable))

## Create a dataset of just the American League
## Overwrite that dataset: Make it American Leaguers since 2000
## Who is the highest paid ball player in that dataset you just created?
## Now, do it all in one line. 

## What individual had the most ABs in one year? 
## What individual had the most strikeouts in one year? 
## How has home run hitting changed over time in MLB? 
## How has salaries changed over time? 
## Plot it!