R Notebook
Applied Spatial Data
*Import necessary packages
library(ggplot2)
library(tidyr)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(raster)## Loading required package: sp##
## Attaching package: 'raster'## The following object is masked from 'package:dplyr':
##
## select## The following object is masked from 'package:tidyr':
##
## extractlibrary(rgdal)## rgdal: version: 1.2-8, (SVN revision 663)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 2.0.1, released 2015/09/15
## Path to GDAL shared files: C:/Program Files/R/R-3.4.1/library/rgdal/gdal
## Loaded PROJ.4 runtime: Rel. 4.9.2, 08 September 2015, [PJ_VERSION: 492]
## Path to PROJ.4 shared files: C:/Program Files/R/R-3.4.1/library/rgdal/proj
## Linking to sp version: 1.2-5library(sp)*Obtain Vietnam map (vector data) from GADM website
Vietnam<-getData("GADM", country="Vietnam",level=1)
head(Vietnam@data)## OBJECTID ID_0 ISO NAME_0 ID_1 NAME_1 HASC_1 CCN_1 CCA_1
## 1 1 250 VNM Vietnam 1 Ðà N<U+1EB5>ng VN.DA NA 501
## 2 2 250 VNM Vietnam 2 Ð<U+1ED3>ng Nai VN.DN NA 713
## 3 3 250 VNM Vietnam 3 Ð<U+1ED3>ng Tháp VN.DT NA 803
## 4 4 250 VNM Vietnam 4 Ðak Nông VN.DO NA 606
## 5 5 250 VNM Vietnam 5 Ð<U+1EAF>k L<U+1EAF>k VN.DC NA 605
## 6 6 250 VNM Vietnam 6 Ði<U+1EC7>n Biên VN.DB NA 302
## TYPE_1
## 1 Thành ph<U+1ED1> tr<U+1EF1>c thu<U+1ED9>c t<U+1EC9>nh
## 2 T<U+1EC9>nh
## 3 T<U+1EC9>nh
## 4 T<U+1EC9>nh
## 5 T<U+1EC9>nh
## 6 T<U+1EC9>nh
## ENGTYPE_1 NL_NAME_1 VARNAME_1
## 1 City|Municipality|Thanh Pho Da Nang City|Da Nang
## 2 Province Dong Nai
## 3 Province Dong Thap
## 4 Province Dac Nong
## 5 Province Dak Lak|Dac Lac
## 6 Province Dien Bien*A spatial polygon dataframe behaves like a normal dataframe. It is also noted that there are few duplicates in the dataset
# Kin Giang and Ninh Binh provinces are having
Vietnam@data[duplicated(Vietnam@data$VARNAME_1),]## OBJECTID ID_0 ISO NAME_0 ID_1 NAME_1 HASC_1 CCN_1 CCA_1
## 34 34 250 VNM Vietnam 33 Kiên Giang VN.KG NA 813
## 44 44 250 VNM Vietnam 42 Ninh Bình VN.NB NA 117
## TYPE_1 ENGTYPE_1 NL_NAME_1 VARNAME_1
## 34 T<U+1EC9>nh Province Kien Giang
## 44 T<U+1EC9>nh Province Ninh Binh*Extract coordinate points of Vietnam to use in ggplot2
# Using ggplot2 to derive the coordinate
vn<-fortify(Vietnam,regions="VARNAME_1") # You can pass ID_1 or any other unique variables which are dinstint## Regions defined for each Polygonshead(vn)## long lat order hole piece id group
## 1 107.9137 16.21422 1 FALSE 1 1 1.1
## 2 107.9139 16.21408 2 FALSE 1 1 1.1
## 3 107.9140 16.21396 3 FALSE 1 1 1.1
## 4 107.9141 16.21377 4 FALSE 1 1 1.1
## 5 107.9141 16.21355 5 FALSE 1 1 1.1
## 6 107.9142 16.21323 6 FALSE 1 1 1.1*Visualizing the Vietnam map
# A traditional way of visualization of spatial data
plot(Vietnam,main="Vietnam Map", col=4, axes=T)
# Using a btter way of plotting the map, ggplot2
ggplot(data=vn, aes(x=long,y=lat,group=group)) + geom_point(fill="blue")
*Create a random variable called GPA
set.seed(123) # Make sure that it is fixed
vn$GPA<-runif(nrow(vn),1,100) # GPA ranges from 1 to 100
head(vn)## long lat order hole piece id group GPA
## 1 107.9137 16.21422 1 FALSE 1 1 1.1 29.470174
## 2 107.9139 16.21408 2 FALSE 1 1 1.1 79.042208
## 3 107.9140 16.21396 3 FALSE 1 1 1.1 41.488715
## 4 107.9141 16.21377 4 FALSE 1 1 1.1 88.418723
## 5 107.9141 16.21355 5 FALSE 1 1 1.1 94.106261
## 6 107.9142 16.21323 6 FALSE 1 1 1.1 5.510093*Visualizing the GPA distribution across Vietnam provinces
ggplot(data=vn, aes(x=long,y=lat,group=group)) + geom_polygon(aes(fill=id),color="gray40",show.legend = F) + labs(title="Vietnam Map",x="Longitude",y="Latitude") + theme(plot.title = element_text(hjust = 0.5))
ggplot(data=vn, aes(x=long,y=lat,group=group)) + geom_polygon(aes(fill=GPA),color="gray40",show.legend = T) + labs(title="Vietnam Map",x="Longitude",y="Latitude") + theme(plot.title = element_text(hjust = 0.5)) + scale_fill_gradient(name="Vietnam GPA",limits=c(1,100),low="green",high="red")
library(viridis)## Loading required package: viridisLiteggplot(data=vn, aes(x=long,y=lat, group=group,fill=GPA)) + geom_polygon(color="black") + scale_fill_viridis(direction = 1,option = "viridis") + labs(x="Longitude",y="Latitute", title="GPA Distribution by Province",caption="Tuyen Ha Van, Massey University, NZ") + theme(plot.title = element_text(hjust=0.5))