Thematic Mapping in R without the Tears, Highlighting
Richard Careaga 
July 28, 2015
To show differences between broad groups, consider highlighting with breakouts
- Load script (see the gist to review)
setwd("~/Desktop/gitmo/playpen/r") # your directory here
download.file("https://gist.githubusercontent.com/technocrat/7719f51d0ae0e42edeb2/raw/f4c3157f17b3822416637a987d57bba678cb7839/popBase.R", "popBase.R", method = "libcurl")
source("R/popBase.R")##
## 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
##
## Loading required package: sp
## rgdal: version: 1.0-4, (SVN revision 548)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 1.11.2, released 2015/02/10
## Path to GDAL shared files: /Users/rc/Library/R/3.2/library/rgdal/gdal
## Loaded PROJ.4 runtime: Rel. 4.9.1, 04 March 2015, [PJ_VERSION: 491]
## Path to PROJ.4 shared files: /Users/rc/Library/R/3.2/library/rgdal/proj
## Linking to sp version: 1.1-1
## Checking rgeos availability: TRUE
## Loading required package: maps
## rgeos version: 0.3-11, (SVN revision 479)
## GEOS runtime version: 3.4.2-CAPI-1.8.2 r3921
## Linking to sp version: 1.1-0
## Polygon checking: TRUE
##
## Loading required package: bitopssources <- "Sources: Police caused deaths Data as reported by http://bit.ly/1LJwlF3 from another\n source, accessed 2015-07-26. Disease death rates: Centers for Disease Control \nand Protection: Detailed Tables for the National Vital Statistics Report\n(NVSR) “Deaths: Final Data for 2013. (national rates) http://1.usa.gov/1gjDcbd\naccessed 2015-07-26. 2012 election results: http://1.usa.gov/1go1Jfj\naccessed 2015-07-29. Prepared by @technocrat 2015-07-29"
deaths <- read.csv('csv/shootings.csv', header = FALSE)
names(deaths) <- c("id", "deaths")
popdeath <- merge(pop, deaths, by = 'id')
popdeath$ratio <- (popdeath$deaths/popdeath$pop)*100000
popdeath$ratio <- factor(popdeath$ratio)
head(popdeath)## id fips pop state pop.equal pop.quantile
## 1 AK 2 736732 Alaska [5.84e+05,6.95e+06] [5.84e+05,1.15e+06]
## 2 AL 1 4849377 Alabama [5.84e+05,6.95e+06] (4.41e+06,6.23e+06]
## 3 AR 5 2966369 Arkansas [5.84e+05,6.95e+06] (2.88e+06,4.41e+06]
## 4 AZ 4 6731484 Arizona [5.84e+05,6.95e+06] (6.23e+06,9.93e+06]
## 5 CA 6 38802500 California (3.24e+07,3.88e+07] (9.93e+06,3.88e+07]
## 6 CO 8 5355866 Colorado [5.84e+05,6.95e+06] (4.41e+06,6.23e+06]
## pop.std pop.natural deaths ratio
## 1 [5.84e+05,7.71e+06] [5.84e+05,3.6e+06] 0.1 0.0135734568336926
## 2 [5.84e+05,7.71e+06] (3.6e+06,7.06e+06] 72.0 1.48472680098908
## 3 [5.84e+05,7.71e+06] [5.84e+05,3.6e+06] 41.0 1.38216115392252
## 4 [5.84e+05,7.71e+06] (3.6e+06,7.06e+06] 176.0 2.61457948945582
## 5 (3.62e+07,3.88e+07] (2.7e+07,3.88e+07] 1233.0 3.17763030732556
## 6 [5.84e+05,7.71e+06] (3.6e+06,7.06e+06] 104.0 1.94179615397398load('helpers/redblue')
redblue## id president
## 1 AL R
## 2 AK R
## 3 AZ R
## 4 AR R
## 5 CA D
## 6 CO D
## 7 CT D
## 8 DE E
## 9 DC D
## 10 FL D
## 11 GA R
## 12 HI D
## 13 ID R
## 14 IL D
## 15 IN R
## 16 IA D
## 17 KS R
## 18 KY R
## 19 LA R
## 20 ME D
## 21 MD D
## 22 MA D
## 23 MI D
## 24 MN D
## 25 MS R
## 26 MO R
## 27 MT R
## 28 NE R
## 29 NV D
## 30 NH D
## 31 NJ D
## 32 NM D
## 33 NY D
## 34 NC R
## 35 ND R
## 36 OH D
## 37 OK R
## 38 OR D
## 39 PA D
## 40 RI D
## 41 SC R
## 42 SD R
## 43 TN R
## 44 TX R
## 45 UT R
## 46 VT D
## 47 VA D
## 48 WA D
## 49 WV R
## 50 WI D
## 51 WY Rpopdeath <- merge(popdeath, redblue, by = 'id')
#not run in RStudio
#popdeath <- intervals(popdeath,ratio)
head(popdeath)## id fips pop state pop.equal pop.quantile
## 1 AK 2 736732 Alaska [5.84e+05,6.95e+06] [5.84e+05,1.15e+06]
## 2 AL 1 4849377 Alabama [5.84e+05,6.95e+06] (4.41e+06,6.23e+06]
## 3 AR 5 2966369 Arkansas [5.84e+05,6.95e+06] (2.88e+06,4.41e+06]
## 4 AZ 4 6731484 Arizona [5.84e+05,6.95e+06] (6.23e+06,9.93e+06]
## 5 CA 6 38802500 California (3.24e+07,3.88e+07] (9.93e+06,3.88e+07]
## 6 CO 8 5355866 Colorado [5.84e+05,6.95e+06] (4.41e+06,6.23e+06]
## pop.std pop.natural deaths ratio
## 1 [5.84e+05,7.71e+06] [5.84e+05,3.6e+06] 0.1 0.0135734568336926
## 2 [5.84e+05,7.71e+06] (3.6e+06,7.06e+06] 72.0 1.48472680098908
## 3 [5.84e+05,7.71e+06] [5.84e+05,3.6e+06] 41.0 1.38216115392252
## 4 [5.84e+05,7.71e+06] (3.6e+06,7.06e+06] 176.0 2.61457948945582
## 5 (3.62e+07,3.88e+07] (2.7e+07,3.88e+07] 1233.0 3.17763030732556
## 6 [5.84e+05,7.71e+06] (3.6e+06,7.06e+06] 104.0 1.94179615397398
## president
## 1 R
## 2 R
## 3 R
## 4 R
## 5 D
## 6 Dredbluemap <- merge(us50, popdeath, by = 'id')
redstates <- filter(redbluemap, president == 'R')
bluestates <- filter(redbluemap, president == 'D')
p = ggplot(data= redbluemap) +
geom_map(map=redbluemap, aes(x=long, y=lat, map_id=id, group=group), fill = "light grey", color="dark grey", size=0.3) +
no_ylab +
no_xlab +
plain_theme
makewhite = centroids[c('MT', 'NV', 'FL', 'ME', 'OR', 'NM'),]
l = geom_text(data=centroids, aes(clong, clat, label = id), color = "black", size=2)
w = geom_text(data=makewhite, aes(clong, clat, label = id), color = "white", size=2)
combined_title <- "Estimated Police Caused Deaths (unstated period)\nin States and District of Columbia"
combined <- p + geom_polygon(data = redbluemap, aes(x=long, y=lat, group=group, fill = ratio), color = "dark grey", size = 0.3)
combined <- combined + scale_fill_brewer(palette = "Reds", name = "Police Caused Deaths\nper 100,000 population\n(comparable to)", labels=c("Under 1.5(influenza)", "1.5(atherosclerosis)", "1.5-2.2(atherosclerosis)","2.2-3.5(aortic aneurysm)","3.5-4.8(asthma and emphysema)","4.8-8.3(liver disease)")) + ggtitle(combined_title) + l + w + annotate("text", x = -120000, y = -2350000, label = sources, size = 3, hjust = 0, family = "Times", colour = "black")
# not run in RStudio
#combined + l + w
r_title <- "Estimated Police Caused Deaths (unstated period)\nin States voting for Romney in 2012"
r <- p + geom_polygon(data = redstates, aes(x=long, y=lat, group=group, fill =
ratio), color = "dark grey", size = 0.3)
r <- r + scale_fill_brewer(palette = "Reds", name = "Police Caused Deaths\nper 100,000 population\n(comparable to)", labels=c("Under 1.5(influenza)","1.5-2.2(atherosclerosis)","2.2-3.5(aortic aneurysm)","3.5-4.8(asthma and emphysema)","4.8-8.3(liver disease)")) + ggtitle(r_title) + l + w + annotate("text", x = -120000, y = -2350000, label = sources, size = 3, hjust = 0, family = "Times", colour = "black")
makewhite = centroids[c('MT'),]
w = geom_text(data=makewhite, aes(clong, clat, label = id), color = "white", size=2)
# Not run in RStudio
# r + l + w
d_title <- "Estimated Police Caused Deaths (unstated period)\nin States and District of Columbia voting for Obama"
d <- p + geom_polygon(data = bluestates, aes(x=long, y=lat, group=group, fill = ratio), color = "dark grey", size = 0.3)
d <- d + scale_fill_brewer(palette = "Reds", name = "Police Caused Deaths\nper 100,000 population\n(comparable to)", labels=c("Under 1.5(influenza)", "1.5(atherosclerosis)", "1.5-2.2(atherosclerosis)","2.2-3.5(aortic aneurysm)","3.5-4.8(asthma and emphysema)","4.8-8.3(liver disease)")) + ggtitle(d_title) + annotate("text", x = -120000, y = -2350000, label = sources, size = 3, hjust = 0, family = "Times", colour = "black")
makewhite = centroids[c('NV', 'FL', 'ME', 'OR', 'NM'),]
w = geom_text(data=makewhite, aes(clong, clat, label = id), color = "white", size=2)
# Not run in RStudio
# d + l + w- For convenience states with missing data were set to 0.1 deaths
table_of_data <- data.frame(popdeath$id,popdeath$pop,popdeath$deaths, popdeath$ratio)
names(table_of_data) <- c("State", "Population", "Deaths", "Per 100,000")
table_of_data## State Population Deaths Per 100,000
## 1 AK 736732 0.1 0.0135734568336926
## 2 AL 4849377 72.0 1.48472680098908
## 3 AR 2966369 41.0 1.38216115392252
## 4 AZ 6731484 176.0 2.61457948945582
## 5 CA 38802500 1233.0 3.17763030732556
## 6 CO 5355866 104.0 1.94179615397398
## 7 CT 3596677 0.1 0.00278034418992865
## 8 DC 658893 0.1 0.0151769710711754
## 9 DE 935614 0.1 0.010688168411332
## 10 FL 19893297 958.0 4.81569244152943
## 11 GA 10097343 204.0 2.0203334679232
## 12 HI 1419561 0.1 0.00704443134180215
## 13 IA 3107126 26.0 0.836786149000716
## 14 ID 1634464 46.0 2.81437829159896
## 15 IL 12880580 177.0 1.37416172253113
## 16 IN 6596855 58.0 0.879206834165674
## 17 KS 2904021 47.0 1.61844559663997
## 18 KY 4413457 62.0 1.40479447290412
## 19 LA 4649676 73.0 1.57000186679674
## 20 MA 6745408 101.0 1.49731491408674
## 21 MD 5976407 130.0 2.17521999422061
## 22 ME 1330089 55.0 4.13506163873245
## 23 MI 9909877 87.0 0.877912006375054
## 24 MN 5457173 95.0 1.74082808076636
## 25 MO 6063589 110.0 1.81410712368533
## 26 MS 2994079 44.0 1.46956710227085
## 27 MT 1023579 40.0 3.90785664809458
## 28 NC 9943964 221.0 2.22245374178748
## 29 ND 739482 5.0 0.676148979961649
## 30 NE 1881503 27.0 1.43502295770987
## 31 NH 1326813 23.0 1.7334771365671
## 32 NJ 8938175 83.0 0.928601196552988
## 33 NM 2085572 86.0 4.1235689777193
## 34 NV 2839099 236.0 8.31249632365761
## 35 NY 19746227 383.0 1.93961104569496
## 36 OH 11594163 158.0 1.36275468957958
## 37 OK 3878051 82.0 2.11446419863999
## 38 OR 3970239 189.0 4.7604187052719
## 39 PA 12787209 142.0 1.11048470389434
## 40 RI 1055173 0.1 0.00947711891794047
## 41 SC 4832482 76.0 1.57269080360775
## 42 SD 853175 21.0 2.4613942040027
## 43 TN 6549352 94.0 1.43525649560445
## 44 TX 26956958 361.0 1.33917187540226
## 45 UT 2942902 104.0 3.53392671587433
## 46 VA 8326289 79.0 0.948802041341587
## 47 VT 626562 17.0 2.71321912276838
## 48 WA 7061530 212.0 3.00218224662361
## 49 WI 5757564 56.0 0.972633565167491
## 50 WV 1850326 26.0 1.40515779381579
## 51 WY 584153 12.0 2.05425633352906sessionInfo()## R version 3.2.1 (2015-06-18)
## Platform: x86_64-apple-darwin13.4.0 (64-bit)
## Running under: OS X 10.10.4 (Yosemite)
##
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] RCurl_1.95-4.7 bitops_1.0-6 rgeos_0.3-11 mapproj_1.2-3
## [5] maps_2.3-10 maptools_0.8-36 rgdal_1.0-4 sp_1.1-1
## [9] dplyr_0.4.2 classInt_0.1-22 ggplot2_1.0.1
##
## loaded via a namespace (and not attached):
## [1] Rcpp_0.12.0 knitr_1.10.5 magrittr_1.5 MASS_7.3-42
## [5] munsell_0.4.2 lattice_0.20-33 colorspace_1.2-6 R6_2.1.0
## [9] stringr_1.0.0 plyr_1.8.3 tools_3.2.1 parallel_3.2.1
## [13] grid_3.2.1 gtable_0.1.2 e1071_1.6-4 DBI_0.3.1
## [17] htmltools_0.2.6 class_7.3-13 lazyeval_0.1.10 yaml_2.1.13
## [21] digest_0.6.8 assertthat_0.1 reshape2_1.4.1 evaluate_0.7
## [25] rmarkdown_0.7 stringi_0.5-5 scales_0.2.5 foreign_0.8-65
## [29] proto_0.3-10The combined map makes it difficult to focus on any difference between Red and Blue States
Breaking out groups separately allows easier detection of any pattern
Next up
Taking suggestions @technocrat on twitter.
Disclaimer
I am unable to answer questions relating to the use of this code under Windows.
Credits
Algorithms
Data
See sources in the walkthrough installment.
R Packages
- Roger Bivand and Nicholas Lewin-Koh (2015). maptools: Tools for Reading and Handling Spatial Objects. R package version 0.8-36. http://CRAN.R-project.org/package=maptools
- Roger Bivand and Colin Rundel (2015). rgeos: Interface to Geometry Engine - Open Source (GEOS). R package version 0.3-11. http://CRAN.R-project.org/package=rgeos
- Roger Bivand, Tim Keitt and Barry Rowlingson (2015). rgdal: Bindings for the Geospatial Data Abstraction Library. R package version 1.0-4 rgdal
- Doug McIlroy. Packaged for R by Ray Brownrigg, Thomas P Minka and transition to Plan 9 codebase by Roger Bivand. (2015). mapproj: Map Projections. R package version 1.2-3. http://CRAN.R-project.org/package=mappro
- Erich Neuwirth (2014). RColorBrewer: ColorBrewer Palettes. R package version 1.1-2. RColorBrewer
- R Core Team (2015). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. [grid]
- Karthik Ram, Hadley Wickham, Clark Richards. wesanderson R package
- H. Wickham. ggplot2: elegant graphics for data analysis. Springer New York, 2009. ggplot2
License
Copyright (c) 2015, Richard Careaga
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.