library(ggplot2)
library(maptools)
## Loading required package: foreign
## Warning: package 'foreign' was built under R version 2.15.3
## 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
## LOAD DATA
USA <- readShapePoly("/Users/telekineticturtle/Desktop/Colorado 13/Quant Methods/Data/USAcopy.shp")
## Remove count fields and rows with missing data
USA <- USA[, c(1:8, 14:30)]
USA <- na.omit(USA)
# You need two pieces in order to plot anything: a ggplot call and a geom
# call:
plot1 <- ggplot(data = USA@data, aes(x = Obese, y = homevalu))
plot1 + geom_point()
# Manipulating the axes:
plot1 + geom_point() + scale_x_log10() + scale_y_log10()
# Add transparency to the points to make overplotting visible.
plot1 + geom_point(alpha = 1/10) + scale_x_log10() + scale_y_log10()
# Add best fit lines:
plot1 + geom_point(alpha = 1/10) + geom_smooth(method = "lm")
plot1 + geom_point(alpha = 1/10) + geom_smooth(method = "loess")
# Binning points to avoid the overplotting problem:
library(hexbin)
plot1 + stat_binhex()
plot1 + geom_bin2d()
plot1 + geom_density2d()
Seth: “Three ways to incorporate qualitative variables:
1. Facets: Each level of a factor can be plotted in its own panel.
2. Groups: Each level of a factor can be assigned its own group. For example, plotting fitted lines for each group through a scatter plot.
3. Appearance: Color, symbols, line weight, fill, and other variables can be assigned to a factor (qualitative variable).”
# Create a Factor
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 plot1 to include the factor (by color)
plot2 <- ggplot(data = USA@data, aes(x = Obese, y = homevalu, color = good_states))
plot2 + geom_point()
# Include the factor by shape
plot2 <- ggplot(data = USA@data, aes(x = Obese, y = homevalu, color = good_states,
shape = good_states))
plot2 + geom_point()
# Plot as smoothed lines (no shapes yet)
plot2 + stat_smooth() #uses 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.
# Plot as smoothed lines with shapes:
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 to turn off the
# grey standaed error envelopes.
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")
# Adding a third Dimension to data:
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)
plot4 + theme_classic()
library(ggthemes)
## Warning: package 'ggthemes' was built under R version 2.15.3
plot4 + theme_economist()
plot4 + theme_solarized() #OUCH!
plot4 + theme_tufte()
# Seth 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"), title = element_text(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
# ggsave
# Step 1: Fortify Use fortify to extract ploygon boundaries from the
# spatialDataFrame (its slow) -- this literally finds every single vertex
# of every piece of every polygon in the shapefile and stores it as a
# table. Need to include some unique indentifier for each polygon in
# order to group them together later.
library(rgeos)
## Warning: package 'rgeos' was built under R version 2.15.3
## rgeos version: 0.2-16, (SVN revision 389) GEOS runtime version:
## 3.3.3-CAPI-1.7.4 Polygon checking: TRUE
usa_geom <- fortify(USA, region = "FIPS")
# Step 2: Merge Reattach data to ploygon boundaries using
usa_map_df <- merge(usa_geom, USA, by.x = "id", by.y = "FIPS")
# Step3: Map Make a map using ggplot; in order to show a thematic map need
# to add two layers: one for the fill and one for the polygon boundaries
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
# applying themes:
map1 + sethTheme
# Just Do It!
library(classInt)
## Loading required package: class
## Loading required package: e1071
classIntervals(USA$Bush_pct, n = 5, style = "quantile")
## style: quantile
## [0,50.52) [50.52,58.07) [58.07,64.37) [64.37,71.31) [71.31,92.83]
## 622 622 622 622 623
breaks <- c(0, 50, 58, 64, 71, 93) #approximate quantiles
labels = c("[0 - 50%]", "[50% - 58%]", "[58% - 64%]", "[64% - 71%]", "[71% - 93%]")
usa_map_df$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
# Incorporating RColorBrewer:
library(RColorBrewer)
# Use scale_fill_brewer instead of scale_fill_gradient:
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))
