# This tutorial is part of Computerworld's How to Make a Map with R in 10 (fairly) Easy Steps
# https://www.computerworld.com/article/3038270/data-analytics/create-maps-in-r-in-10-fairly-easy-steps.html
# by Sharon Machlis sharon_machlis@idg.com


# Set various values needed, including names of files and FIPS codes for New Hampshire and South Carolina
nhdatafile <- "NHD2016.xlsx"
nhdatafilecsv <- "NHD2016.csv"
usshapefile <- "cb_2014_us_county_5m/cb_2014_us_county_5m.shp"
nhfipscode <- "33"
scdatafile <- "SCGOP2016.csv"
scfipscode <- "45"

# Run any of the install.packages() commands below for packages that are not yet on your system
library(tidyverse)

## Warning: package 'tidyr' was built under R version 4.3.1

library(tmap)

## Warning: package 'tmap' was built under R version 4.3.1

library(tmaptools)

## Warning: package 'tmaptools' was built under R version 4.3.1

library(leaflet)

## Warning: package 'leaflet' was built under R version 4.3.1

library(sf)

## Warning: package 'sf' was built under R version 4.3.1

library(leaflet.extras)

## Warning: package 'leaflet.extras' was built under R version 4.3.1

library(dplyr)
library(rio)

## Warning: package 'rio' was built under R version 4.3.1

library(sp)

## Warning: package 'sp' was built under R version 4.3.1

library(htmlwidgets)

## Warning: package 'htmlwidgets' was built under R version 4.3.1

library(scales)

## Warning: package 'scales' was built under R version 4.3.1

Step 1: Read in the NH election results file:

setwd("C:\\Users\\asing\\Desktop\\data_science\\data_110\\week_5\\GIS\\computerworldrmaptutorial\\data")
nhdata <- import(nhdatafile)
nhdata <- import(nhdatafilecsv)

Eliminate columns for minor candidates and just use County, Clinton and Sanders columns:

nhdata <- nhdata[,c("County", "Clinton", "Sanders")]

Step 2: Decide what data to map

Add columns for percents and margins:

nhdata$SandersMarginVotes <- nhdata$Sanders - nhdata$Clinton
nhdata$SandersPct <- (nhdata$Sanders) / (nhdata$Sanders + nhdata$Clinton) 
# Will use formatting later to multiply by a hundred
nhdata$ClintonPct <- (nhdata$Clinton) / (nhdata$Sanders + nhdata$Clinton)
nhdata$SandersMarginPctgPoints <- nhdata$SandersPct - nhdata$ClintonPct

Step 3: Get geographic data files

Read in the shapefile for US states and counties:

• If libraries with raster and rgdal don’t work (see next chunk), try library(sf) with the command st_read

• All these options are here and should help you get the qtm command in the next chunk

setwd("C:\\Users\\asing\\Desktop\\data_science\\data_110\\week_5\\GIS\\computerworldrmaptutorial\\data\\cb_2014_us_county_5m")
library(raster)

## Warning: package 'raster' was built under R version 4.3.1

## 
## Attaching package: 'raster'

## The following object is masked from 'package:dplyr':
## 
##     select

library(rgdal)

## Warning: package 'rgdal' was built under R version 4.3.1

## Please note that rgdal will be retired during October 2023,
## plan transition to sf/stars/terra functions using GDAL and PROJ
## at your earliest convenience.
## See https://r-spatial.org/r/2023/05/15/evolution4.html and https://github.com/r-spatial/evolution
## rgdal: version: 1.6-7, (SVN revision 1203)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 3.6.2, released 2023/01/02
## Path to GDAL shared files: C:/Users/asing/AppData/Local/R/win-library/4.3/rgdal/gdal
##  GDAL does not use iconv for recoding strings.
## GDAL binary built with GEOS: TRUE 
## Loaded PROJ runtime: Rel. 9.2.0, March 1st, 2023, [PJ_VERSION: 920]
## Path to PROJ shared files: C:/Users/asing/AppData/Local/R/win-library/4.3/rgdal/proj
## PROJ CDN enabled: FALSE
## Linking to sp version:2.0-0
## To mute warnings of possible GDAL/OSR exportToProj4() degradation,
## use options("rgdal_show_exportToProj4_warnings"="none") before loading sp or rgdal.

usgeo <- shapefile("cb_2014_us_county_5m.shp")

## Warning: [vect] Z coordinates ignored

Do a quick plot (qtm stands for quick thematic map) of the shapefile and check its structure:

tmap_options(check.and.fix =  TRUE)
qtm(usgeo)

Subset just the NH data from the US shapefile

nhgeo <- usgeo[usgeo$STATEFP==nhfipscode,]

##tmap test plot of the New Hampshire data

qtm(nhgeo)

Structure of the object

## I EDITED THE STRING OUT BECAUSE IT WAS TO LONG

#str(nhgeo)
#str(nhdata$County)

# They're not. Change the county names to plain characters in nhgeo:
nhgeo$NAME <- as.character(nhgeo$NAME)

Order each data set by county name

nhgeo <- nhgeo[order(nhgeo$NAME),]
nhdata <- nhdata[order(nhdata$County),]
# Are the two county columns identical now? They should be:
identical(nhgeo$NAME,nhdata$County)

## [1] TRUE

Step 4: Merge geo data with results data using the merge function

library(sf)  # sf stands for simple features#

nhmap <- merge(nhgeo, nhdata, by.x = "NAME", by.y = "County")
# See the new data structure with

# I EDITED THE STRING OUT CAUSE IT WAS TO LONG

#str(nhmap)

Step 5: Create a static map with tmap’s qtm() function:

qtm(nhmap, "SandersMarginVotes")

## Some legend labels were too wide. These labels have been resized to 0.62, 0.62, 0.62, 0.57, 0.53. Increase legend.width (argument of tm_layout) to make the legend wider and therefore the labels larger.

qtm(nhmap, "SandersMarginPctgPoints")

For more control over look and feel, use the tm_shape() function:

tm_shape(nhmap) +
  tm_fill("SandersMarginVotes", title="Sanders Margin, Total Votes", palette = "PRGn") +
  tm_borders(alpha=.5) +
  tm_text("NAME", size=0.8)

## Some legend labels were too wide. These labels have been resized to 0.62, 0.62, 0.62, 0.57, 0.53. Increase legend.width (argument of tm_layout) to make the legend wider and therefore the labels larger.

Same code as above, but store the static map in a variable, and change the theme to “classic” style:

nhstaticmap <- tm_shape(nhmap) +
tm_fill("SandersMarginVotes", title="Sanders Margin, Total Votes", palette = "viridis") + #I like viridis
tm_borders(alpha=.5) +
tm_text("NAME", size=0.8) + 
tm_style("classic")

View the map

nhstaticmap

## Some legend labels were too wide. These labels have been resized to 0.62, 0.62, 0.62, 0.57, 0.53. Increase legend.width (argument of tm_layout) to make the legend wider and therefore the labels larger.

Save the map to a jpg file with tmap’s tmap_save():

tmap_save(nhstaticmap, filename="nhdemprimary.jpg")

## Map saved to C:\Users\asing\Desktop\data_science\data_110\week_5\nhdemprimary.jpg

## Resolution: 1501.336 by 2937.385 pixels

## Size: 5.004452 by 9.791282 inches (300 dpi)

Part 6

Next up: Code for a basic interactive map, this time for Clinton percentages in NH

Create a palette

clintonPalette <- colorNumeric(palette = "Blues", domain=nhmap$ClintonPct)

and a pop-up window

library(scales)
#library(raster)
nhpopup <- paste0("County: ", nhmap$NAME, "<br /><br /> Sanders:  ", percent(nhmap$SandersPct), " Clinton: ", percent(nhmap$ClintonPct))

Step 7: Now generate the interactive map:

For more information on CRS (coordinate reference systems) projection, see this document:

https://rspatial.org/raster/spatial/6-crs.html

nhmap_projected <- sp::spTransform(nhmap, "+proj=longlat +datum=WGS84")
leaflet(nhmap_projected) %>%
  addProviderTiles("CartoDB.Positron") %>%
  addPolygons(stroke=FALSE, 
              smoothFactor = 0.2, 
              fillOpacity = .8, 
              popup=nhpopup, 
              color= ~clintonPalette(nhmap$ClintonPct)
  )

South Carolina data

setwd("C:\\Users\\asing\\Desktop\\data_science\\data_110\\week_5\\GIS\\computerworldrmaptutorial\\data")
scdata <- rio::import(scdatafile)

South Carolina shapefile and Quick plot of scgeo SC geospatial object:

scgeo <- usgeo[usgeo@data$STATEFP=="45",]
qtm(scgeo)

Add a column with percent of votes for each candidate. Candidates are in columns 2-7:

candidates <- colnames(scdata[2:7])
for(i in 2:7){
  j = i + 7
  temp <- scdata[[i]] / scdata$Total
  scdata[[j]] <- temp
  colnames(scdata)[j] <- paste0(colnames(scdata)[i], "Pct")
}  
winner <- colnames(scdata[2:7])

Get winner in each precinct

for(i in 1:nrow(scdata)){
  scdata$winner[i] <- names(which.max(scdata[i,2:7]))
}

Import spreadsheet with percent of adult population holding at least a 4-yr college degree

setwd("C:\\Users\\asing\\Desktop\\data_science\\data_110\\week_5\\GIS\\computerworldrmaptutorial\\data")
sced <- rio::import("SCdegree.xlsx")

Check if county names are in the same format in both files

str(scgeo$NAME)

##  chr [1:46] "Edgefield" "Lee" "Horry" "Allendale" "Marion" "Dorchester" ...

##  chr [1:46] "Edgefield" "Lee" "Horry" "Allendale" "Marion" "Dorchester" ...
str(scdata$County)

##  chr [1:46] "Abbeville" "Aiken" "Allendale" "Anderson" "Bamberg" "Barnwell" ...

##  chr [1:46] "Abbeville" "Aiken" "Allendale" "Anderson" "Bamberg" "Barnwell" ...
# Change the county names to plain characters in scgeo:
scgeo$NAME <- as.character(scgeo$NAME)

# Order each data set by county name
scgeo <- scgeo[order(scgeo$NAME),]
scdata <- scdata[order(scdata$County),]

# Are the two county columns identical now? They should be:
identical(scgeo$NAME,scdata$County )

## [1] TRUE

Add the election results and rename county column

scmap <- merge(scgeo, scdata, by.x = "NAME", by.y = "County")

Instead of just coloring the winner, let’s color by strength of win with multiple layers

# Use same intensity for all - get minimum and maximum for the top 3 combined
minpct <- min(c(scdata$`Donald J TrumpPct`, scdata$`Marco RubioPct`, scdata$`Ted CruzPct`))
maxpct <- max(c(scdata$`Donald J TrumpPct`, scdata$`Marco RubioPct`, scdata$`Ted CruzPct`))

Create leaflet palettes for each layer of the map:

trumpPalette <- colorNumeric(palette = "Purples", domain=c(minpct, maxpct))
rubioPalette <- colorNumeric(palette = "Reds", domain = c(minpct, maxpct))
cruzPalette <- colorNumeric(palette = "Oranges", domain = c(minpct, maxpct))

winnerPalette <- colorFactor(palette=c("#984ea3", "#e41a1c"), domain = scmap$winner)
edPalette <- colorNumeric(palette = "Blues", domain=scmap$PctCollegeDegree)

Create a pop-up:

scpopup <- paste0("<b>County: ", scmap$NAME, "<br />Winner: ", scmap$winner, "</b><br /><br />Trump: ", percent(scmap$`Donald J TrumpPct`), "<br />Rubio: ", percent(scmap$`Marco RubioPct`), "<br />Cruz: ", percent(scmap$`Ted CruzPct`), "<br /><br />Pct w college ed: ", sced$PctCollegeDegree, "% vs state-wide avg of 25%")

Add the projection we know from the NH map we’ll need for this data on a Leaflet map:

scmap <- sp::spTransform(scmap, "+proj=longlat +datum=WGS84")

Basic interactive map showing winner in each county:

leaflet(scmap) %>%
  addProviderTiles("CartoDB.Positron") %>%
  addPolygons(stroke=TRUE,
              weight=1,
              smoothFactor = 0.2,
              fillOpacity = .75,
              popup=scpopup, 
              color= ~winnerPalette(scmap$winner),
              group="Winners" ) %>%
    addLegend(position="bottomleft", colors=c("#984ea3", "#e41a1c"), labels=c("Trump", "Rubio"))

Put top 3 candidates in their own layers and add education layer, store in scGOPmap variable

scGOPmap <- leaflet(scmap) %>%
  addProviderTiles("CartoDB.Positron") %>%
  addPolygons(stroke=TRUE,
              weight=1,
              smoothFactor = 0.2,
              fillOpacity = .75,
              popup=scpopup, 
              color= ~winnerPalette(scmap$winner),
              group="Winners"  ) %>% 
    addLegend(position="bottomleft", colors=c("#984ea3", "#e41a1c"), labels=c("Trump", "Rubio"))  %>%

  addPolygons(stroke=TRUE,
     weight=1,
     smoothFactor = 0.2, 
     fillOpacity = .75, 
     popup=scpopup, 
     color= ~trumpPalette(scmap$`Donald J TrumpPct`),
     group="Trump") %>%

  addPolygons(stroke=TRUE,
              weight=1,
              smoothFactor = 0.2, 
              fillOpacity = .75, 
              popup=scpopup, 
              color= ~rubioPalette(scmap$`Marco RubioPct`),
              group="Rubio") %>%

  addPolygons(stroke=TRUE,
              weight=1,
              smoothFactor = 0.2, 
              fillOpacity = .75, 
              popup=scpopup, 
              color= ~cruzPalette(scmap$`Ted CruzPct`),
              group="Cruz") %>%

  addPolygons(stroke=TRUE,
              weight=1,
              smoothFactor = 0.2, 
              fillOpacity = .75, 
              popup=scpopup, 
              color= ~edPalette(sced$PctCollegeDegree), #this data is in the sced table, not scmaps
              group="College degs") %>%

  addLayersControl(
      baseGroups=c("Winners", "Trump", "Rubio", "Cruz", "College degs"),
      position = "bottomleft",
      options = layersControlOptions(collapsed = FALSE))

# Now display the map
scGOPmap

Save as self-contained HTML file

library(htmlwidgets)
htmlwidgets::saveWidget(scGOPmap, file="scGOPwidget2.html")

# save as an HTML file with dependencies in another directory:
#htmlwidgets::saveWidget(widget=scGOPmap2, file="scGOPprimary_withdependencies.html", selfcontained=FALSE, libdir = "js")

GIS Tutorial

A Singh

2023-07-03

Step 1: Read in the NH election results file:

Eliminate columns for minor candidates and just use County, Clinton and Sanders columns:

Step 2: Decide what data to map

Add columns for percents and margins:

Step 3: Get geographic data files

Read in the shapefile for US states and counties:

• If libraries with raster and rgdal don’t work (see next chunk), try library(sf) with the command st_read

• All these options are here and should help you get the qtm command in the next chunk

Do a quick plot (qtm stands for quick thematic map) of the shapefile and check its structure:

Subset just the NH data from the US shapefile

Structure of the object

Order each data set by county name

Step 4: Merge geo data with results data using the merge function

Step 5: Create a static map with tmap’s qtm() function:

For more control over look and feel, use the tm_shape() function:

Same code as above, but store the static map in a variable, and change the theme to “classic” style:

View the map

Save the map to a jpg file with tmap’s tmap_save():

Part 6

Create a palette

and a pop-up window

Step 7: Now generate the interactive map:

For more information on CRS (coordinate reference systems) projection, see this document:

https://rspatial.org/raster/spatial/6-crs.html

South Carolina data

South Carolina shapefile and Quick plot of scgeo SC geospatial object:

Add a column with percent of votes for each candidate. Candidates are in columns 2-7:

Get winner in each precinct

Import spreadsheet with percent of adult population holding at least a 4-yr college degree

Check if county names are in the same format in both files

Add the election results and rename county column

Instead of just coloring the winner, let’s color by strength of win with multiple layers

Create leaflet palettes for each layer of the map:

Create a pop-up:

Add the projection we know from the NH map we’ll need for this data on a Leaflet map:

Basic interactive map showing winner in each county:

Put top 3 candidates in their own layers and add education layer, store in scGOPmap variable

Save as self-contained HTML file