Creating Maps in R - week 9 HW - 20191030

#install packages and libraries
#install.packages("rio")
#install.packages("tmap")
#install.packages("tmaptools")
#install.packages("sf")
#install.packages("leaflet")
#install.packages("leaflet.extras")
#install.packages("shiny")
#install.packages("urltools")
#install.packages("scales")
#install.packages("htmlwidgets")
#install.packages("sf")
#install.packages("dplyr")
library(dplyr)
## Warning: package 'dplyr' was built under R version 3.5.3
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(tmap)
## Warning: package 'tmap' was built under R version 3.5.3
library(tmaptools)
## Warning: package 'tmaptools' was built under R version 3.5.3
library(sf)
## Warning: package 'sf' was built under R version 3.5.3
## Linking to GEOS 3.6.1, GDAL 2.2.3, PROJ 4.9.3
library(leaflet)
## Warning: package 'leaflet' was built under R version 3.5.3
library(leaflet.extras)
## Warning: package 'leaflet.extras' was built under R version 3.5.3
library(rio)
## Warning: package 'rio' was built under R version 3.5.3
library(shiny)
## Warning: package 'shiny' was built under R version 3.5.3
library(urltools)
## Warning: package 'urltools' was built under R version 3.5.3
library(scales)
## Warning: package 'scales' was built under R version 3.5.3
library(htmlwidgets)
## Warning: package 'htmlwidgets' was built under R version 3.5.3
getwd()
## [1] "C:/Users/Jennifer/Documents/MC Data Science/Data Science 110 Writing and Comm/R Data Files and Markdown files"

Step 1: Get election results data

nhdatafile <- "NHD2016.xlsx"
nhdatafilecsv <- "NHD2016.csv"

nhfipscode <- "33"
scdatafile <- "SCGOP2016.csv"
SCfipscode <- "45"
#now read in the NH election results file
nhdata <- rio::import(nhdatafilecsv)
#select only columns for county, Clinton, and Sanders
nhdata <- nhdata[,c("County", "Clinton", "Sanders")]

Step 2: Decide what data to map

Add columns to pull the candidates’ margins of victory(or loss) and percent of the vote.

nhdata$SandersMarginVotes <- nhdata$Sanders - nhdata$Clinton
nhdata$SandersPct <- (nhdata$Sanders)/(nhdata$Sanders + nhdata$Clinton)
nhdata$ClintonPct <- (nhdata$Clinton)/(nhdata$Sanders + nhdata$Clinton)
nhdata$SandersMarginPctgPoints <- nhdata$SandersPct - nhdata$ClintonPct

Step 3: Get your geographic data

Store the name of the file in a variable called usshapefile

library(tmaptools)
usshapefile <- "cb_2014_us_county_5m.shp"
usgeo <- read_shape(file = usshapefile, as.sf = TRUE)
## Warning: This function is deprecated and has been migrated to github.com/
## mtennekes/oldtmaptools
## Warning in readOGR(dir, base, verbose = FALSE, ...): Z-dimension discarded

Step 3.5: Plot the shapefile.

library(tmap)
qtm(usgeo)

Step 3.6: Look at the structure.

str(usgeo)
## Classes 'sf' and 'data.frame':   3233 obs. of  10 variables:
##  $ STATEFP : Factor w/ 56 levels "01","02","04",..: 1 11 16 37 39 37 28 26 29 10 ...
##  $ COUNTYFP: Factor w/ 328 levels "001","003","005",..: 42 76 74 78 78 38 22 137 291 35 ...
##  $ COUNTYNS: Factor w/ 3233 levels "00023901","00025441",..: 120 430 738 1911 2024 1880 1399 1373 1490 298 ...
##  $ AFFGEOID: Factor w/ 3233 levels "0500000US01001",..: 30 442 844 2189 2302 2158 1669 1589 1764 344 ...
##  $ GEOID   : Factor w/ 3233 levels "01001","01003",..: 30 442 844 2189 2302 2158 1669 1589 1764 344 ...
##  $ NAME    : Factor w/ 1921 levels "Abbeville","Acadia",..: 620 592 945 1291 1665 692 320 1683 284 747 ...
##  $ LSAD    : Factor w/ 11 levels "00","03","04",..: 5 5 5 5 5 5 5 5 1 5 ...
##  $ ALAND   : Factor w/ 3233 levels "1000508842","1001064387",..: 1199 5 2047 452 1721 2091 1880 1194 2397 1215 ...
##  $ AWATER  : Factor w/ 3233 levels "0","10017640",..: 1626 414 1940 1718 1118 2724 2916 2228 1613 497 ...
##  $ geometry:sfc_MULTIPOLYGON of length 3233; first list element: List of 1
##   ..$ :List of 1
##   .. ..$ : num [1:9, 1:2] -88.2 -88.2 -88.2 -88.1 -87.5 ...
##   ..- attr(*, "class")= chr  "XY" "MULTIPOLYGON" "sfg"
##  - attr(*, "sf_column")= chr "geometry"
##  - attr(*, "agr")= Factor w/ 3 levels "constant","aggregate",..: NA NA NA NA NA NA NA NA NA
##   ..- attr(*, "names")= chr  "STATEFP" "COUNTYFP" "COUNTYNS" "AFFGEOID" ...

Step 3.7: Filter to pull NH. Then do the quick thematic map again to check we have the right one.

nhgeo <- filter(usgeo, STATEFP=="33")
qtm(nhgeo)

Step 4: Merge spatial and results data. Check the vectors to see if they will match.

Step 4.1: check the NAME in nhgeo dataframe.

str(nhgeo$NAME)
##  Factor w/ 1921 levels "Abbeville","Acadia",..: 684 791 416 138 1470 334 1653 1131 282 1657

Step 4.2: Check the County in the nhdata dataframe.

str(nhdata$County)
##  chr [1:10] "Belknap" "Carroll" "Cheshire" "Coos" "Grafton" "Hillsborough" ...

Step 4.3: change the geospatial factors to character strings.

nhgeo$NAME <- as.character(nhgeo$NAME)

Step 4.4: Sort both datasets by county name and the compare them.

nhgeo <- nhgeo[order(nhgeo$NAME),]
nhdata <- nhdata[order(nhdata$County),]
identical(nhgeo$NAME,nhdata$County)
## [1] TRUE

Step 4.5: Join the two files using tmaptool’s append_data() function. Then view the structure.

nhmap <- append_data(nhgeo, nhdata, key.shp = "NAME", key.data = "County")
## Warning: This function is deprecated and has been migrated to github.com/
## mtennekes/oldtmaptools
## Keys match perfectly.
str(nhmap)
## Classes 'sf' and 'data.frame':   10 obs. of  16 variables:
##  $ STATEFP                : Factor w/ 56 levels "01","02","04",..: 30 30 30 30 30 30 30 30 30 30
##  $ COUNTYFP               : Factor w/ 328 levels "001","003","005",..: 1 2 3 5 6 8 10 12 14 15
##  $ COUNTYNS               : Factor w/ 3233 levels "00023901","00025441",..: 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505
##  $ AFFGEOID               : Factor w/ 3233 levels "0500000US01001",..: 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774
##  $ GEOID                  : Factor w/ 3233 levels "01001","01003",..: 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774
##  $ NAME                   : chr  "Belknap" "Carroll" "Cheshire" "Coos" ...
##  $ LSAD                   : Factor w/ 11 levels "00","03","04",..: 5 5 5 5 5 5 5 5 5 5
##  $ ALAND                  : Factor w/ 3233 levels "1000508842","1001064387",..: 67 1991 1424 2526 2494 1831 1997 1382 3172 730
##  $ AWATER                 : Factor w/ 3233 levels "0","10017640",..: 778 638 2460 3097 55 1942 2454 1327 1852 1817
##  $ Clinton                : int  3495 3230 5132 2013 6918 28147 12250 22829 8813 2497
##  $ Sanders                : int  6005 5638 12441 3639 14245 39245 18107 31065 15881 5915
##  $ SandersMarginVotes     : int  2510 2408 7309 1626 7327 11098 5857 8236 7068 3418
##  $ SandersPct             : num  0.632 0.636 0.708 0.644 0.673 ...
##  $ ClintonPct             : num  0.368 0.364 0.292 0.356 0.327 ...
##  $ SandersMarginPctgPoints: num  0.264 0.272 0.416 0.288 0.346 ...
##  $ geometry               :sfc_POLYGON of length 10; first list element: List of 1
##   ..$ : num [1:33, 1:2] -71.7 -71.7 -71.7 -71.7 -71.7 ...
##   ..- attr(*, "class")= chr  "XY" "POLYGON" "sfg"
##  - attr(*, "sf_column")= chr "geometry"
##  - attr(*, "agr")= Factor w/ 3 levels "constant","aggregate",..: NA NA NA NA NA NA NA NA NA NA ...
##   ..- attr(*, "names")= chr  "STATEFP" "COUNTYFP" "COUNTYNS" "AFFGEOID" ...

Step 5: Create a static map. Use Sanders’ margins by county in number of votes.

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.

Step 5.1: Mapping margins by percentage.

qtm(nhmap, "SandersMarginPctgPoints")

Step 5.2: Change the colors, borders, and other aesthetics.

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.

Step 5.3: Change the map theme.

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.

tm_style_classic()
## Warning in tm_style_classic(): tm_style_classic is deprecated as of tmap version
## 2.0. Please use tm_style("classic", ...) instead
## $tm_layout
## $tm_layout$style
## [1] "classic"
## 
## 
## attr(,"class")
## [1] "tm"

Step 5.4: Save the static map.

nhstaticmap <- tm_shape(nhmap) +
  tm_fill("SandersMarginVotes", title="Sanders Margin, Total Votes", palette = "PRGn") +
  tm_borders(alpha=.5) +
  tm_text("NAME", size=0.8)
save_tmap(nhstaticmap, filename="nhdemprimary.jpg")
## Warning in save_tmap(nhstaticmap, filename = "nhdemprimary.jpg"): save_tmap is
## deprecated as of tmap version 2.0. Please use tmap_save instead
## Warning in png(tmp, width = width, height = height, res = res): 'width=7,
## height=7' are unlikely values in pixels
## Map saved to C:\Users\Jennifer\Documents\MC Data Science\Data Science 110 Writing and Comm\R Data Files and Markdown files\nhdemprimary.jpg
## Resolution: 1501.336 by 2937.385 pixels
## Size: 5.004452 by 9.791282 inches (300 dpi)

Stop here for HW assignment (covers steps 1-5)

Step 6: Create palette and pop-ups for interactive map.

Use Clinton’s vote percentage data. Use scales package for the percent function.

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