# Mindanao State University
# General Santos City
# Submitted by: Roland Fritz C. Adam & Aj Ardaniel
# ggplot2 Tutorial 1 - Intro
# Understanding the Ggplot Syntax
# Setup
options(scipen=999) # turn off scientific notation like 1e+06
library(ggplot2)
data("midwest", package = "ggplot2") # load the data
# midwest <- read.csv("http://goo.gl/G1K41K") # alt source
# Init Ggplot
ggplot(midwest, aes(x=area, y=poptotal)) # area and poptotal are columns in 'midwest'
# How to Make a Simple Scatterplot
library(ggplot2)
ggplot(midwest, aes(x=area, y=poptotal)) + geom_point()
library(ggplot2)
g <- ggplot(midwest, aes(x=area, y=poptotal)) + geom_point() + geom_smooth(method="lm") # set se=FALSE to turnoff confidence bands
plot(g)
## `geom_smooth()` using formula = 'y ~ x'
# Adjusting the X and Y axis limits
# Method 1: By deleting the points outside the range
library(ggplot2)
g <- ggplot(midwest, aes(x=area, y=poptotal)) + geom_point() + geom_smooth(method="lm") # set se=FALSE to turnoff confidence bands
# Delete the points outside the limits
g + xlim(c(0, 0.1)) + ylim(c(0, 1000000)) # deletes points
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 5 rows containing non-finite values (`stat_smooth()`).
## Warning: Removed 5 rows containing missing values (`geom_point()`).
# g + xlim(0, 0.1) + ylim(0, 1000000) # deletes points
# Method 2: Zooming In
library(ggplot2)
g <- ggplot(midwest, aes(x=area, y=poptotal)) + geom_point() + geom_smooth(method="lm") # set se=FALSE to turnoff confidence bands
# Zoom in without deleting the points outside the limits.
# As a result, the line of best fit is the same as the original plot.
g1 <- g + coord_cartesian(xlim=c(0,0.1), ylim=c(0, 1000000)) # zooms in
plot(g1)
## `geom_smooth()` using formula = 'y ~ x'
# How to Change the Title and Axis Labels
library(ggplot2)
g <- ggplot(midwest, aes(x=area, y=poptotal)) + geom_point() + geom_smooth(method="lm") # set se=FALSE to turnoff confidence bands
g1 <- g + coord_cartesian(xlim=c(0,0.1), ylim=c(0, 1000000)) # zooms in
# Add Title and Labels
g1 + labs(title="Area Vs Population", subtitle="From midwest dataset", y="Population", x="Area", caption="Midwest Demographics")
## `geom_smooth()` using formula = 'y ~ x'
# or
g1 + ggtitle("Area Vs Population", subtitle="From midwest dataset") + xlab("Area") + ylab("Population")
## `geom_smooth()` using formula = 'y ~ x'
# Full Plot call
library(ggplot2)
ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point() +
geom_smooth(method="lm") +
coord_cartesian(xlim=c(0,0.1), ylim=c(0, 1000000)) +
labs(title="Area Vs Population", subtitle="From midwest dataset", y="Population", x="Area", caption="Midwest Demographics")
## `geom_smooth()` using formula = 'y ~ x'
# How to Change the Color and Size of Points
library(ggplot2)
ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(col="steelblue", size=3) + # Set static color and size for points
geom_smooth(method="lm", col="firebrick") + # change the color of line
coord_cartesian(xlim=c(0, 0.1), ylim=c(0, 1000000)) +
labs(title="Area Vs Population", subtitle="From midwest dataset", y="Population", x="Area", caption="Midwest Demographics")
## `geom_smooth()` using formula = 'y ~ x'
# How to Change the Color To Reflect Categories in Another Column?
library(ggplot2)
gg <- ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state), size=3) + # Set color to vary based on state categories.
geom_smooth(method="lm", col="firebrick", size=2) +
coord_cartesian(xlim=c(0, 0.1), ylim=c(0, 1000000)) +
labs(title="Area Vs Population", subtitle="From midwest dataset", y="Population", x="Area", caption="Midwest Demographics")
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
plot(gg)
## `geom_smooth()` using formula = 'y ~ x'
gg + theme(legend.position="None") # remove legend
## `geom_smooth()` using formula = 'y ~ x'
gg + scale_colour_brewer(palette = "Set1") # change color palette
## `geom_smooth()` using formula = 'y ~ x'
# How to Change the X Axis Texts and Ticks Location
# Step 1: Set the breaks
library(ggplot2)
# Base plot
gg <- ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state), size=3) + # Set color to vary based on state categories.
geom_smooth(method="lm", col="firebrick", size=2) +
coord_cartesian(xlim=c(0, 0.1), ylim=c(0, 1000000)) +
labs(title="Area Vs Population", subtitle="From midwest dataset", y="Population", x="Area", caption="Midwest Demographics")
# Change breaks
gg + scale_x_continuous(breaks=seq(0, 0.1, 0.01))
## `geom_smooth()` using formula = 'y ~ x'
# Step 2: Change the labels You can optionally change the labels at the axis ticks. labels take a vector of the same length as breaks.
library(ggplot2)
# Base Plot
gg <- ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state), size=3) + # Set color to vary based on state categories.
geom_smooth(method="lm", col="firebrick", size=2) +
coord_cartesian(xlim=c(0, 0.1), ylim=c(0, 1000000)) +
labs(title="Area Vs Population", subtitle="From midwest dataset", y="Population", x="Area", caption="Midwest Demographics")
# Change breaks + label
gg + scale_x_continuous(breaks=seq(0, 0.1, 0.01), labels = letters[1:11])
## `geom_smooth()` using formula = 'y ~ x'
# Reverse
library(ggplot2)
gg <- ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state), size=3) + # Set color to vary based on state categories.
geom_smooth(method="lm", col="firebrick", size=2) +
coord_cartesian(xlim=c(0, 0.1), ylim=c(0, 1000000)) +
labs(title="Area Vs Population", subtitle="From midwest dataset", y="Population", x="Area", caption="Midwest Demographics")
# Reverse X Axis Scale
gg + scale_x_reverse()
## `geom_smooth()` using formula = 'y ~ x'
# How to Write Customized Texts for Axis Labels, by Formatting the Original Values?
library(ggplot2)
# Base Plot
gg <- ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state), size=3) + # Set color to vary based on state categories.
geom_smooth(method="lm", col="firebrick", size=2) +
coord_cartesian(xlim=c(0, 0.1), ylim=c(0, 1000000)) +
labs(title="Area Vs Population", subtitle="From midwest dataset", y="Population", x="Area", caption="Midwest Demographics")
# Change Axis Texts
gg + scale_x_continuous(breaks=seq(0, 0.1, 0.01), labels = sprintf("%1.2f%%", seq(0, 0.1, 0.01))) +
scale_y_continuous(breaks=seq(0, 1000000, 200000), labels = function(x){paste0(x/1000, 'K')})
## `geom_smooth()` using formula = 'y ~ x'
# How to Customize the Entire Theme in One Shot using Pre-Built Themes?
library(ggplot2)
# Base plot
gg <- ggplot(midwest, aes(x=area, y=poptotal)) +
geom_point(aes(col=state), size=3) + # Set color to vary based on state categories.
geom_smooth(method="lm", col="firebrick", size=2) +
coord_cartesian(xlim=c(0, 0.1), ylim=c(0, 1000000)) +
labs(title="Area Vs Population", subtitle="From midwest dataset", y="Population", x="Area", caption="Midwest Demographics")
gg <- gg + scale_x_continuous(breaks=seq(0, 0.1, 0.01))
# method 1: Using theme_set()
theme_set(theme_classic()) # not run
gg
## `geom_smooth()` using formula = 'y ~ x'
# method 2: Adding theme Layer itself.
gg + theme_bw() + labs(subtitle="BW Theme")
## `geom_smooth()` using formula = 'y ~ x'
gg + theme_classic() + labs(subtitle="Classic Theme")
## `geom_smooth()` using formula = 'y ~ x'
