Alan Zarychta's R-Journal

GEOG 5023: Quantitative Methods In Geography

Making Graphs with GGPLOT2

Options and packages:

options(scipen = 999)

library(ggplot2)
library(maptools)

## Warning: package 'maptools' was built under R version 2.15.3

## Loading required package: foreign

## Loading required package: sp

## Warning: package 'sp' was built under R version 2.15.3

## Loading required package: grid

## Loading required package: lattice

## Checking rgeos availability: TRUE

library(hexbin)

## Warning: package 'hexbin' was built under R version 2.15.3

library(ggthemes)

## Warning: package 'ggthemes' was built under R version 2.15.3

library(rgeos)

## Warning: package 'rgeos' was built under R version 2.15.3

## rgeos version: 0.2-16, (SVN revision 389) GEOS runtime version:
## 3.3.6-CAPI-1.7.6 Polygon checking: TRUE

library(classInt)

## Warning: package 'classInt' was built under R version 2.15.3

## Loading required package: class

## Loading required package: e1071

library(RColorBrewer)

Loading and preparing the data:

Read in the shapefile

USA <- readShapePoly("C:/CU BOULDER/Coursework/Y2S2/GEOG 5023 - Quant Methods Geo/Week 15 - ggplot2/USA copy.shp")

Clean and Summarize the data

USA <- USA[, c(1:8, 14:30)]  #remove count fields
USA <- na.omit(USA)  #remove missing data

Making Graphs with ggplot2:

Visualize the data

plot1 <- ggplot(data = USA@data, aes(x = Obese, y = homevalu))
plot1 + geom_point()

plot1 + geom_point() + scale_x_log10() + scale_y_log10()

Add trasparency to address overplotting of points

plot1 + geom_point(alpha = 1/10) + scale_x_log10() + scale_y_log10()

plot1 + geom_point(alpha = 1/10) + geom_smooth(method = "lm")  #add a fitted line

plot1 + geom_point(alpha = 1/10) + geom_smooth(method = "loess")  #add a lowess curve

plot1 + stat_binhex()  #deal with overplotting using hexogonal bins

plot1 + geom_bin2d()  #deal with overplotting with regular bins

plot1 + geom_density2d()  #try a density plot

Create a qualitative variable

USA$good_states <- ifelse(USA$STATE_NAME %in% c("New York", "Massachusetts", 
    "Rhode Island", "Wyoming"), yes = "its good", no = "its ok")
USA$good_states <- as.factor(USA$good_states)

Modify prior plots

plot2 <- ggplot(data = USA@data, aes(x = Obese, y = homevalu, color = good_states))
plot2 + geom_point()

plot2 <- ggplot(data = USA@data, aes(x = Obese, y = homevalu, color = good_states, 
    shape = good_states))
plot2 + stat_smooth()  #use a local fit

## geom_smooth: method="auto" and size of largest group is >=1000, so using
## gam with formula: y ~ s(x, bs = "cs"). Use 'method = x' to change the
## smoothing method.

plot2 + geom_point() + stat_smooth(method = "lm", se = TRUE, lwd = 0.5, lty = 1)

# lwd controls line thickenss lty controls line type 1= solid line, higher
# numbers various forms of dashed lines. se can be used ti turn off the
# grey standaed error envelopes.

Add marginalia and change the appearance of the plots

# Look at the percent college educated (pctcoled) and the per capita
# income (pcincome), these two variables have a correlation of r=.7 so our
# plots should show some sort of relationship.

plot3 <- ggplot(data = USA@data, aes(x = pctcoled, y = pcincome))
plot3 + geom_point() + ylab("Per Capita Income") + xlab("Percent College Educated") + 
    ggtitle("US Counties (2000)\nPercent College Educated by Per Capita Income")

Make a multidimensional plot

# Add the unemployment variable to the plot by changing the color of the
# dots based on the unemployment rate.

plot4 <- ggplot(data = USA@data, aes(x = pctcoled, y = pcincome, color = unemploy)) + 
    geom_point() + ylab("Per Capita Income") + xlab("Percent College Educated") + 
    ggtitle("US Counties (2000)\nPercent College Educated by Per Capita Income") + 
    scale_color_gradient2("Unemployment", breaks = c(min(USA$unemploy), mean(USA$unemploy), 
        max(USA$unemploy)), labels = c("Below Average", "Average", "Above Average"), 
        low = "green", mid = "yellow", high = "red", midpoint = mean(USA$unemploy))
plot4

Split the plot into panels based upon the “good states” variable

# Create 'facets' or subplots that display only the data for each level of
# the factor.

plot4 + facet_grid(. ~ good_states)

# A more involved option:

plot4 + facet_grid(. ~ STATE_NAME)

Working with themes

plot4 + theme_classic()

# There is a library of themes:

plot4 + theme_economist()

plot4 + theme_solarized()  #OUCH!

plot4 + theme_tufte()

# Seth's custom theme for presentations (with corrections in code to
# include plot title and legend title):

sethTheme <- theme(title = element_text(colour = "white"), panel.background = element_rect(fill = "black"), 
    plot.background = element_rect(fill = "black"), panel.grid.minor = element_blank(), 
    panel.grid.major = element_line(linetype = 3, colour = "white"), axis.text.x = element_text(colour = "grey80"), 
    axis.text.y = element_text(colour = "grey80"), axis.title.x = element_text(colour = "grey80"), 
    axis.title.y = element_text(colour = "grey80"), legend.key = element_rect(fill = "black"), 
    legend.text = element_text(colour = "white"), legend.title = element_text(colour = "white"), 
    legend.background = element_rect(fill = "black"), axis.ticks = element_blank())
plot4 + sethTheme

Making maps

# Use fortify to extract ploygon boundaries from the spatial Data Frame
# (its slow)
usa_geom <- fortify(USA, region = "FIPS")
dim(usa_geom)

## [1] 80926     7

# reattach data to ploygon boundaries
usa_map_df <- merge(usa_geom, USA, by.x = "id", by.y = "FIPS")

# make a map of bush_pct
map1 <- ggplot(usa_map_df, aes(long, lat, group = group)) + geom_polygon(data = usa_map_df, 
    aes(fill = Bush_pct)) + coord_equal() + scale_fill_gradient(low = "yellow", 
    high = "red") + geom_path(data = usa_geom, aes(long, lat, group = group), 
    lty = 3, lwd = 0.1, color = "white")

map1

map1 + sethTheme

Make thematic maps with legend classes using ColorBrewer

classIntervals(USA$Bush_pct, n = 5, style = "quantile")

## style: quantile
##     [0,50.52) [50.52,58.07) [58.07,64.37) [64.37,71.31) [71.31,92.83] 
##           622           622           622           622           623

breaks <- c(0, 50, 58, 64, 71, 93)  #approximate quantiles
labels = c("[0 - 50%]", "[50% - 58%]", "[58% - 64%]", "[64% - 71%]", "[71% - 93%]")
usa_map_df$bushBreaks <- cut(usa_map_df$Bush_pct, breaks = breaks, labels = labels)
map2 <- ggplot(aes(long, lat, group = group), data = usa_map_df) + geom_polygon(data = usa_map_df, 
    aes(fill = bushBreaks)) + coord_equal()
map2

map2 + scale_fill_brewer("Votes for Bush in 2004 (%)", palette = "YlGnBu") + 
    sethTheme + ggtitle("Votes for Bush in 2004 (%)") + theme(plot.title = element_text(size = 24, 
    face = "bold", color = "white", hjust = 2))