Key Concepts covered in the lecture include (Same as before):
1. Learn concepts of visualizing statistics
The in-class exercise focuses on GGPlot2. GG stands for Grammer of Graphics (by Leland Wilkinson)
Part 1: Creating scatterplots in GGPlot
library(ggplot2)
library(maptools)
## Loading required package: foreign
## Loading required package: sp
## Loading required package: grid
## Loading required package: lattice
## Checking rgeos availability: TRUE
USA <- readShapePoly("H:/Quant/inClassExercises/InClassExerciseData/2004_Election_Counties.shp")
names(USA)
## [1] "NAME" "STATE_NAME" "STATE_FIPS" "CNTY_FIPS" "FIPS"
## [6] "AREA" "FIPS_num" "Bush" "Kerry" "County_F"
## [11] "Nader" "Total" "Bush_pct" "Kerry_pct" "Nader_pct"
## [16] "MDratio" "hosp" "pcthisp" "pcturban" "urbrural"
## [21] "pctfemhh" "pcincome" "pctpoor" "pctlt9ed" "pcthsed"
## [26] "pctcoled" "unemploy" "pctwhtcl" "homevalu" "rent"
## [31] "popdens" "crowded" "ginirev" "SmokecurM" "SmokevrM"
## [36] "SmokecurF" "SmokevrF" "Obese" "Noins" "XYLENES__M"
## [41] "TOLUENE" "TETRACHLOR" "STYRENE" "NICKEL_COM" "METHYLENE_"
## [46] "MERCURY_CO" "LEAD_COMPO" "BENZENE__I" "ARSENIC_CO" "POP2000"
## [51] "POP00SQMIL" "MALE2000" "FEMALE2000" "MAL2FEM" "UNDER18"
## [56] "AIAN" "ASIA" "BLACK" "NHPI" "WHITE"
## [61] "AIAN_MORE" "ASIA_MORE" "BLK_MORE" "NHPI_MORE" "WHT_MORE"
## [66] "HISP_LAT" "CH19902000" "MEDAGE2000" "PEROVER65"
plot1 <- ggplot(data = USA@data, aes(x = Obese, y = homevalu)) #Create a GGPlot. R does nothing,
plot1 + geom_point() #we need to plot it using a point geometry. Now we get the scatterplot!
plot1 + geom_point() + scale_x_log10() + scale_y_log10() #Change the scale of the plot.
plot1 + geom_point(alpha = 1/10) + scale_x_log10() + scale_y_log10() #Edit the transparency for each dot based on attribute value
plot1 + geom_point(alpha = 1/10) + geom_smooth(method = "lm") #Fit a line through the data. It also creates a standard error envelope for this fitted line. Can we access informaiton about this line?
# Do some additional overlays:
library(hexbin) #bring in a new library
plot1 + stat_binhex() #similar to a density plot. Each point has a hexagon; then each hexagon shows overplotting. It highlights where the there is more data in terms of the scatterplot space.
plot1 + geom_bin2d() #This is the same plot but uses a different binning shape.
plot1 + geom_density2d() #This is a weird contour plot of there there is data. I don't much use in this.
# Create a goofy factor for the data. We can plot data in terms of its
# factors:
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) #Define the factor
plot2 <- ggplot(data = USA@data, aes(x = Obese, y = homevalu, color = good_states))
plot2 + geom_point() #colors a point based on its attribute (the factor)
plot2 <- ggplot(data = USA@data, aes(x = Obese, y = homevalu, color = good_states,
shape = good_states))
plot2 + stat_smooth() #uses a local fit. Note: this takes a few moments to draw.
## 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) #Overlay the points and line plots. Not sure how to interpret this... I think it draws trend lines for the factors.
Part 2: Modify ggplot appearance
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")
# We can get very detailed in how we modify the data to be displayed:
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
plot4 + facet_grid(. ~ good_states) #We can also split the plots based on a factor variable
plot4 + theme_classic() #A theme to be applied to a plot. This is just a regular white-backgrounded scatterplot. This is useful to standardize plot appearances. More on these themes in the next section...
Part 3: Using and Creating Themes
install.packages("ggthemes")#This is a library full of pre-created themes.
## Installing package(s) into 'Q:/RStu97.64b/RStudio/R/library' (as 'lib' is
## unspecified)
## Warning: 'lib = "Q:/RStu97.64b/RStudio/R/library"' is not writable
## Error: unable to install packages
library(ggthemes)#This gives you access other created themes
## Warning: package 'ggthemes' was built under R version 2.15.3
plot4 + theme_economist()#This is an example of a default theme
plot4 + theme_solarized() #here is another
plot4 + theme_tufte()#and another
#Some of the defualt themes aren't very good. It is possible to create your own theme. Here is Seth's creation:
sethTheme <- theme(
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 = "black"),
legend.background = element_rect(fill = "black"),
axis.ticks = element_blank())
plot4 + sethTheme#Uh-oh. No titles present. We must fix the text color and edit the theme...
sethTheme <- theme(
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"),
title = element_text(colour = "white"),#this was added
legend.key = element_rect(fill = "black"),
legend.text = element_text(colour = "white"),
legend.title = element_text(colour = "white"),#This was edited
legend.background = element_rect(fill = "black"),
axis.ticks = element_blank())
plot4 + sethTheme#Ah, much better!
Part 4: Making Maps with GGPlot2
# note... we use the 'RGEOS' library for this? or something like this.
usa_geom <- fortify(USA, region = "FIPS") #Fortify extracts the coords of each polygon. Sounds like the same way google maps plots polygons in a mashup. Holy crap this takes forever!
## Loading required package: rgeos
## rgeos version: 0.2-12, (SVN revision 372) GEOS runtime version:
## 3.3.6-CAPI-1.7.6 Polygon checking: TRUE
usa_map_df <- merge(usa_geom, USA, by.x = "id", by.y = "FIPS") #Creates the dataframe of polygons.
# Create a map:
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 #We can also apply themes to the maps
Part 5: Creating proper thematic maps
library(classInt)
## Loading required package: class
## Loading required package: e1071
classIntervals(USA$Bush_pct, n = 5, style = "quantile")
## style: quantile
## [0,50.52) [50.52,58.07) [58.07,64.37) [64.37,71.31) [71.31,92.83]
## 622 622 622 622 623
# The ggplot isn't compatable with this stuff, so we need to manually
# define these breaks:
breaks <- c(0, 50, 58, 64, 71, 93) #approximate quantiles
labels = c("[0 - 50%]", "[50% - 58%]", "[58% - 64%]", "[64% - 71%]", "[71% - 93%]")
usa_map_df$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 #How are the colors being applied?
# Here, ggplot is looking at the class breaks as factors, so we must
# specify a proper color ramp:
library(RColorBrewer)
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))
