Part 1: ggplot2 Intro

part1-ggplot2intro.r

## Title: ggplot2 Introduction
## Description: This line by line analysis, provides an introduction to ggplot2
## Created by: Brandon Bertelsen: Research Manager, Credo Consulting Inc.

# install.packages("ggplot2")

## Load Library
library(ggplot2)

# load sample data
d <- diamonds

# let's look at what we have
str(diamonds)

# 'data.frame':  53940 obs. of  10 variables:
#  $ carat  : num  0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
#  $ cut    : Factor w/ 5 levels "Fair","Good",..: 5 4 2 4 2 3 3 3 1 3 ...
#  $ color  : Factor w/ 7 levels "D","E","F","G",..: 2 2 2 6 7 7 6 5 2 5 ...
#  $ clarity: Factor w/ 8 levels "I1","SI2","SI1",..: 2 3 5 4 2 6 7 3 4 5 ...
#  $ depth  : num  61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
#  $ table  : num  55 61 65 58 58 57 57 55 61 61 ...
#  $ price  : int  326 326 327 334 335 336 336 337 337 338 ...
#  $ x      : num  3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
#  $ y      : num  3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
#  $ z      : num  2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...

# Start simple, build up. A histogram of diamond prices
ggplot(d, aes(price)) + geom_histogram()

# Lets try to see a bit more granularity
ggplot(d, aes(price)) + geom_histogram(binwidth=100)

# Look at density instead
ggplot(d, aes(price)) + geom_density() 

# See the relationship between carat and price
ggplot(d, aes(price, carat)) + geom_point() 

# Label our prices by clarity and look for relationships
ggplot(d, aes(price, carat, label=clarity)) + geom_text()

# Sample our data to get a better understanding of relationship
ggplot(d[sample(rownames(d),1000),], aes(price, carat, label=clarity)) + geom_text()

# Still not really providing a good view, perhaps we should color our data
ggplot(d, aes(price, carat, color=clarity)) + geom_point()