AS7-0C 世界地圖

rm(list=ls(all=T))
options(digits=4, scipen=12)
library(dplyr)
library(ggplot2)
library(maps)
library(ggmap)
library(reshape2)

---

7.3 加強基本圖表

library(ggplot2)
# Load our data, which lives in intl.csv
intl = read.csv("data/intl.csv")
str(intl)

'data.frame':   8 obs. of  2 variables:
 $ Region       : Factor w/ 8 levels "Africa","Asia",..: 2 3 6 4 5 1 7 8
 $ PercentOfIntl: num  0.531 0.201 0.098 0.09 0.054 0.02 0.015 0.002

7.3.1 Bar Plot with Quantities

rr # We want to make a bar plot with region on the X axis # and Percentage on the y-axis. ggplot(intl, aes(x=Region, y=PercentOfIntl)) + geom_bar(stat=) + geom_text(aes(label=PercentOfIntl))

• geom_text to put the values of variables on the plot

7.3.2 Reorder by Column

# Make Region an ordered factor
# We can do this with the re-order command and transform command. 
intl = transform(intl, Region = reorder(Region, -PercentOfIntl))
# Make the percentages out of 100 instead of fractions
intl$PercentOfIntl = intl$PercentOfIntl * 100
# Make the plot
ggplot(intl, aes(x=Region, y=PercentOfIntl)) +
  geom_bar(stat="identity", fill="dark blue") +
  geom_text(aes(label=PercentOfIntl), vjust=-0.4) +
  ylab("Percent of International Students") +
  theme(axis.title.x = element_blank(), 
        axis.text.x = element_text(angle = 45, hjust = 1))

• change the order of factor with transform reorder function.

---

7.3 全球國際學生數量

7.3.3 Data for Intl’ Students

library(ggmap)
# Load in the international student data
intlall = read.csv("data/intlall.csv",stringsAsFactors=FALSE)
# Lets look at the first few rows
# head(intlall)
# Those NAs are really 0s, and we can replace them easily
intlall[is.na(intlall)] = 0
# Now lets look again
head(intlall) 

• replace the NAs with 0 by is.na

7.3.4 World Map

# Load the world map
world_map = map_data("world")
str(world_map)

'data.frame':   99338 obs. of  6 variables:
 $ long     : num  -69.9 -69.9 -69.9 -70 -70.1 ...
 $ lat      : num  12.5 12.4 12.4 12.5 12.5 ...
 $ group    : num  1 1 1 1 1 1 1 1 1 1 ...
 $ order    : int  1 2 3 4 5 6 7 8 9 10 ...
 $ region   : chr  "Aruba" "Aruba" "Aruba" "Aruba" ...
 $ subregion: chr  NA NA NA NA ...

7.3.5 Merge Map with Data

# Lets merge intlall into world_map using the merge command
world_map = merge(world_map, intlall, by.x ="region", by.y = "Citizenship")
str(world_map)

'data.frame':   63634 obs. of  12 variables:
 $ region         : chr  "Albania" "Albania" "Albania" "Albania" ...
 $ long           : num  20.5 20.4 19.5 20.5 20.4 ...
 $ lat            : num  41.3 39.8 42.5 40.1 41.5 ...
 $ group          : num  6 6 6 6 6 6 6 6 6 6 ...
 $ order          : int  789 822 870 815 786 821 818 779 879 795 ...
 $ subregion      : chr  NA NA NA NA ...
 $ UG             : num  3 3 3 3 3 3 3 3 3 3 ...
 $ G              : num  1 1 1 1 1 1 1 1 1 1 ...
 $ SpecialUG      : num  0 0 0 0 0 0 0 0 0 0 ...
 $ SpecialG       : num  0 0 0 0 0 0 0 0 0 0 ...
 $ ExhangeVisiting: num  0 0 0 0 0 0 0 0 0 0 ...
 $ Total          : int  4 4 4 4 4 4 4 4 4 4 ...

• the merge function: to keep the observations that appears in both data frames.

7.3.6 Plot the Map

rr ggplot(world_map, aes(x=long, y=lat, group=group)) + geom_polygon(fill=, color=) + coord_map()

7.3.7 Polygon points need to be ordered by Group

rr # Reorder the data world_map = world_map[order(world_map\(group, world_map\)order),] # Redo the plot ggplot(world_map, aes(x=long, y=lat, group=group)) + geom_polygon(fill=, color=)

rr # + coord_map()

• some countries missing
• because of the difference of names(eg: PRC vs china)

7.3.8 Identify and Fix Mismatchs between Map and Data

# Lets look for China
grep("China", intlall$Citizenship, ignore.case=T, value=T) 

[1] "China (People's Republic Of)"

grep("China", unique(map_data("world")$region), ignore.case=T, value=T) 

[1] "China"

• set all the names of china into “China”

# Lets "fix" that in the intlall dataset
intlall$Citizenship[intlall$Citizenship=="China (People's Republic Of)"] = 
  "China"
# We'll repeat our merge and order from before
world_map = merge(map_data("world"), intlall, 
                  by.x ="region",
                  by.y = "Citizenship")
world_map = world_map[order(world_map$group, world_map$order),]
ggplot(world_map, aes(x=long, y=lat, group=group)) +
  geom_polygon(aes(fill=Total), color="black") #+

  #coord_map("mercator")

7.3.9 Different Orientations

rr # We can try other projections - this one is visually interesting ggplot(world_map, aes(x=long, y=lat, group=group)) + geom_polygon(aes(fill=Total), color=) + coord_map(, orientation=c(20, 30, 0))

• is the orientation function to choose which side of the globe to be shown?

rr ggplot(world_map, aes(x=long, y=lat, group=group)) + geom_polygon(aes(fill=Total), color=) + coord_map(, orientation=c(-37, 175, 0))

---

7.3 資料結構轉換

7.3.10 Reshaping before Ploting

library(ggplot2)
library(reshape2)
# Now lets load our dataframe
households = read.csv("data/households.csv")
str(households)

'data.frame':   8 obs. of  7 variables:
 $ Year          : int  1970 1980 1990 1995 2000 2005 2010 2012
 $ MarriedWChild : num  40.3 30.9 26.3 25.5 24.1 22.9 20.9 19.6
 $ MarriedWOChild: num  30.3 29.9 29.8 28.9 28.7 28.3 28.8 29.1
 $ OtherFamily   : num  10.6 12.9 14.8 15.6 16 16.7 17.4 17.8
 $ MenAlone      : num  5.6 8.6 9.7 10.2 10.7 11.3 11.9 12.3
 $ WomenAlone    : num  11.5 14 14.9 14.7 14.8 15.3 14.8 15.2
 $ OtherNonfamily: num  1.7 3.6 4.6 5 5.7 5.6 6.2 6.1

# Plot it
melt(households, id="Year") %>% 
  ggplot(aes(x=Year, y=value, color=variable)) +
  geom_line(size=2) + geom_point(size=5) +  
  ylab("Percentage of Households")

---