Assignment3_Restaurants_Part2
Dishaddra Poddar
10/27/2021
library(tigris)## To enable
## caching of data, set `options(tigris_use_cache = TRUE)` in your R script or .Rprofile.library(GWmodel)## Loading required package: maptools## Loading required package: sp## Checking rgeos availability: FALSE
## Please note that 'maptools' will be retired by the end of 2023,
## plan transition at your earliest convenience;
## some functionality will be moved to 'sp'.
## Note: when rgeos is not available, polygon geometry computations in maptools depend on gpclib,
## which has a restricted licence. It is disabled by default;
## to enable gpclib, type gpclibPermit()## Loading required package: robustbase## Loading required package: Rcpp## Loading required package: spatialreg## Loading required package: spData## To access larger datasets in this package, install the spDataLarge
## package with: `install.packages('spDataLarge',
## repos='https://nowosad.github.io/drat/', type='source')`## Loading required package: Matrix## Welcome to GWmodel version 2.2-8.library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.4 v dplyr 1.0.7
## v tidyr 1.1.3 v stringr 1.4.0
## v readr 2.0.1 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x tidyr::expand() masks Matrix::expand()
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## x tidyr::pack() masks Matrix::pack()
## x tidyr::unpack() masks Matrix::unpack()library(sf)## Linking to GEOS 3.9.0, GDAL 3.2.1, PROJ 7.2.1library(tmap)
library(rgdal)## Please note that rgdal will be retired by the end of 2023,
## plan transition to sf/stars/terra functions using GDAL and PROJ
## at your earliest convenience.
##
## rgdal: version: 1.5-27, (SVN revision 1148)
## Geospatial Data Abstraction Library extensions to R successfully loaded
## Loaded GDAL runtime: GDAL 3.2.1, released 2020/12/29
## Path to GDAL shared files: D:/Documents/R/win-library/4.1/sf/gdal
## GDAL binary built with GEOS: TRUE
## Loaded PROJ runtime: Rel. 7.2.1, January 1st, 2021, [PJ_VERSION: 721]
## Path to PROJ shared files: D:/Documents/R/win-library/4.1/rgdal/proj
## PROJ CDN enabled: FALSE
## Linking to sp version:1.4-5
## To mute warnings of possible GDAL/OSR exportToProj4() degradation,
## use options("rgdal_show_exportToProj4_warnings"="none") before loading sp or rgdal.
## Overwritten PROJ_LIB was D:/Documents/R/win-library/4.1/rgdal/projlibrary(dplyr)
library(shinyjs)##
## Attaching package: 'shinyjs'## The following object is masked from 'package:Matrix':
##
## show## The following object is masked from 'package:Rcpp':
##
## show## The following object is masked from 'package:sp':
##
## show## The following objects are masked from 'package:methods':
##
## removeClass, showlibrary(RColorBrewer)options(tigris_use_cache=TRUE)
cnty <- counties(cb=TRUE, resolution="20m", year=2019) %>% mutate(GEOID = as.integer(GEOID))
UA <- urban_areas(cb=TRUE, year=2019) %>% mutate(UACE10 = as.integer(UACE10))
#Create Base Data
restaurantPts= read.csv('restaurantPts.csv')colnames(restaurantPts)## [1] "fn" "gn" "old_pct" "bachelor_pct"
## [5] "clinton_pct" "median_income" "pop_density" "lon"
## [9] "lat" "TRACT_GEOID" "County" "MSA_NAME"
## [13] "UA_NAME"print(length(unique(restaurantPts$UA_NAME)))## [1] 3486print(length(unique(restaurantPts$MSA_NAME)))## [1] 919print(length(unique(restaurantPts$County)))## [1] 3091#Summary Statistics for Counties
GWR_county = restaurantPts %>%
select(c(County, fn, gn, old_pct, bachelor_pct, clinton_pct, median_income, pop_density)) %>%
mutate(median_income = median_income/10000, pop_density = pop_density/1000, gn = gn * 100) %>%
group_by(County) %>%
summarise_all(list(mean = ~mean(.), n=~n()))
#Organize County data and remove counties with fewer than 10 restaurants.
GWR_county <- GWR_county[,-c(10:15)]
GWR_county <- filter(GWR_county, fn_n > 10)
#Join County data to shapefile
GWR_countyGeo = GWR_county %>%
left_join(cnty %>% filter(GEOID %in% GWR_county$County) %>%
select(c(GEOID, geometry)), by=c("County" = "GEOID"), copy=FALSE) %>% st_as_sf() %>% as_Spatial()
#Summary Statistics for UAs
GWR_UA = restaurantPts %>%
select(c(UA_NAME, fn, gn, old_pct, bachelor_pct, clinton_pct, median_income, pop_density)) %>%
mutate(median_income = median_income/10000, pop_density = pop_density/1000, gn = gn * 100) %>%
group_by(UA_NAME) %>%
summarise_all(list(mean = ~mean(.), n=~n()))
#Organize UA data and remove UA with fewer than 10 restaurants.
GWR_UA <- GWR_UA[,-c(10:15)]
GWR_UA <- filter(GWR_UA, fn_n > 10)
#Create table of Chainniest small town.
GWR_UA_st <- GWR_UA
colnames(GWR_UA_st)## [1] "UA_NAME" "fn_mean" "gn_mean"
## [4] "old_pct_mean" "bachelor_pct_mean" "clinton_pct_mean"
## [7] "median_income_mean" "pop_density_mean" "fn_n"GWR_UA_st %>%
arrange(desc(fn_mean),pop_density_mean) %>%
select(c(UA_NAME, fn_mean, gn_mean, pop_density_mean)) %>%
slice(1:5)## # A tibble: 5 x 4
## UA_NAME fn_mean gn_mean pop_density_mean
## <chr> <dbl> <dbl> <dbl>
## 1 Thomasville, AL 5040. 68.4 0.069
## 2 Scott City, MO 4830. 72.7 0.284
## 3 Bells, TN 4647. 64.7 0.0865
## 4 Denton, MD 4640. 46.2 0.606
## 5 Beebe, AR 4599. 76.5 0.208OLSModel <- lm(formula = fn ~ old_pct + bachelor_pct + clinton_pct, data = restaurantPts)
OLSModel##
## Call:
## lm(formula = fn ~ old_pct + bachelor_pct + clinton_pct, data = restaurantPts)
##
## Coefficients:
## (Intercept) old_pct bachelor_pct clinton_pct
## 2276.367 -3.093 -9.771 -15.901summary(OLSModel)##
## Call:
## lm(formula = fn ~ old_pct + bachelor_pct + clinton_pct, data = restaurantPts)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2105.9 -1404.0 -1095.4 -671.8 21338.7
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2276.3671 16.8504 135.093 < 2e-16 ***
## old_pct -3.0934 0.5784 -5.348 8.91e-08 ***
## bachelor_pct -9.7705 0.3155 -30.971 < 2e-16 ***
## clinton_pct -15.9013 0.2789 -57.013 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3831 on 793318 degrees of freedom
## Multiple R-squared: 0.009048, Adjusted R-squared: 0.009045
## F-statistic: 2415 on 3 and 793318 DF, p-value: < 2.2e-16print("Returned coefficients.")## [1] "Returned coefficients."#Change shapefile to a meter based projection
GWR_countyGeo <- spTransform(GWR_countyGeo, CRS("+proj=lcc +lon_0=-90 +lat_1=33 +lat_2=45"))
#Bandwidth for adaptive kernel (nearest neighbors)
myBandwidthNeighbors_county <- bw.gwr(fn_mean ~ old_pct_mean + bachelor_pct_mean + clinton_pct_mean,
adaptive = T,
data = GWR_countyGeo)## Take a cup of tea and have a break, it will take a few minutes.
## -----A kind suggestion from GWmodel development group
## Adaptive bandwidth: 1778 CV score: 937594260
## Adaptive bandwidth: 1107 CV score: 916219188
## Adaptive bandwidth: 691 CV score: 892861737
## Adaptive bandwidth: 435 CV score: 873899444
## Adaptive bandwidth: 275 CV score: 862814121
## Adaptive bandwidth: 178 CV score: 863593215
## Adaptive bandwidth: 337 CV score: 866148677
## Adaptive bandwidth: 239 CV score: 861989901
## Adaptive bandwidth: 214 CV score: 862115357
## Adaptive bandwidth: 251 CV score: 862185663
## Adaptive bandwidth: 227 CV score: 862003375
## Adaptive bandwidth: 241 CV score: 862041658
## Adaptive bandwidth: 232 CV score: 861967351
## Adaptive bandwidth: 233 CV score: 862042394
## Adaptive bandwidth: 236 CV score: 861992148
## Adaptive bandwidth: 233 CV score: 862042394
## Adaptive bandwidth: 234 CV score: 861991447
## Adaptive bandwidth: 233 CV score: 862042394
## Adaptive bandwidth: 233 CV score: 862042394
## Adaptive bandwidth: 232 CV score: 861967351#Bandwidth for fixed kernel (distance)
myBandwidthDistance_county <- bw.gwr(fn_mean ~ old_pct_mean + bachelor_pct_mean + clinton_pct_mean,
adaptive = F,
data = GWR_countyGeo)## Take a cup of tea and have a break, it will take a few minutes.
## -----A kind suggestion from GWmodel development group
## Fixed bandwidth: 2822927 CV score: 989790993
## Fixed bandwidth: 1745014 CV score: 943220953
## Fixed bandwidth: 1078827 CV score: 909492711
## Fixed bandwidth: 667100.5 CV score: 882730896
## Fixed bandwidth: 412639.7 CV score: 871354444
## Fixed bandwidth: 255374.3 CV score: 937868165
## Fixed bandwidth: 509835.1 CV score: 874570875
## Fixed bandwidth: 352569.6 CV score: 876062519
## Fixed bandwidth: 449765 CV score: 872209641
## Fixed bandwidth: 389695 CV score: 871788558
## Fixed bandwidth: 426820.3 CV score: 871533169
## Fixed bandwidth: 403875.6 CV score: 871405725
## Fixed bandwidth: 418056.2 CV score: 871389409
## Fixed bandwidth: 409292.1 CV score: 871357822
## Fixed bandwidth: 414708.6 CV score: 871361994
## Fixed bandwidth: 411361 CV score: 871353364
## Fixed bandwidth: 410570.8 CV score: 871354132
## Fixed bandwidth: 411849.4 CV score: 871353447
## Fixed bandwidth: 411059.2 CV score: 871353525
## Fixed bandwidth: 411547.6 CV score: 871353346
## Fixed bandwidth: 411662.9 CV score: 871353365
## Fixed bandwidth: 411476.3 CV score: 871353346
## Fixed bandwidth: 411432.3 CV score: 871353350
## Fixed bandwidth: 411503.6 CV score: 871353345
## Fixed bandwidth: 411520.4 CV score: 871353345
## Fixed bandwidth: 411493.2 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411513.9 CV score: 871353345
## Fixed bandwidth: 411507.5 CV score: 871353345
## Fixed bandwidth: 411511.5 CV score: 871353345
## Fixed bandwidth: 411509 CV score: 871353345
## Fixed bandwidth: 411510.6 CV score: 871353345
## Fixed bandwidth: 411509.6 CV score: 871353345
## Fixed bandwidth: 411510.2 CV score: 871353345
## Fixed bandwidth: 411509.8 CV score: 871353345
## Fixed bandwidth: 411510.1 CV score: 871353345
## Fixed bandwidth: 411509.9 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345
## Fixed bandwidth: 411510 CV score: 871353345#---- Prepare data for on the County level ----#
## Retrieve a county level shapefile from the census. the resolution is 20 m, which means that it is not a big dataset, it is generalized. Make GEOID an integer, because we will be joining it to an integer field below.
options(tigris_use_cache=TRUE)
cnty <- counties(cb=TRUE, resolution="20m", year=2019) %>% mutate(GEOID = as.integer(GEOID))
## Produce summary statistics on our data on the field "COUNTY"
GWR_input = restaurantPts %>%
select(c(County, fn, gn, old_pct, bachelor_pct, clinton_pct, median_income, pop_density)) %>%
mutate(median_income = median_income/10000, pop_density = pop_density/1000, gn = gn * 100) %>%
group_by(County) %>%
summarise_all(list(mean = ~mean(.), n=~n()))
## Delete those extra hanging columns---they all say the same thing and delete counties w/ fewer than 10 restaurants.
GWR_input <- GWR_input[,-c(10:15)]
GWR_input <- filter(GWR_input, fn_n > 10)
## Join the data to the county shapefile!
GWR_inputGeo = GWR_input %>%
left_join(cnty %>% filter(GEOID %in% GWR_input$County) %>%
select(c(GEOID, geometry)), by=c('County' = 'GEOID'), copy=FALSE) %>% st_as_sf() %>% as_Spatial()
##Let's take a look at colors (uncomment me!)
install.packages("shinyjs")## Warning: package 'shinyjs' is in use and will not be installedlibrary(shinyjs)
tmaptools::palette_explorer() ## Loading required namespace: shinyShiny applications not supported in static R Markdown documents
library(RColorBrewer)
## Make your map: You can ignore the warnings.
#------END CNTY -----------------######### Modified For Assignment Q 8 ##########
##Prints in the console!
########### We need to change the projection to a meter based projection. W are using lambert conformal conic
GWR_inputGeo <- spTransform(GWR_inputGeo, CRS("+proj=lcc +lon_0=-90 +lat_1=33 +lat_2=45"))
########## Let's figure out our bandwidth: first let's use number of neighbors
myBandwidthKNeighbors <- bw.gwr(fn_mean ~ old_pct_mean + bachelor_pct_mean + clinton_pct_mean + pop_density_mean,
adaptive = T,
data=GWR_inputGeo) ## Take a cup of tea and have a break, it will take a few minutes.
## -----A kind suggestion from GWmodel development group
## Adaptive bandwidth: 1778 CV score: 927535707
## Adaptive bandwidth: 1107 CV score: 901988561
## Adaptive bandwidth: 691 CV score: 875659434
## Adaptive bandwidth: 435 CV score: 857611318
## Adaptive bandwidth: 275 CV score: 847961793
## Adaptive bandwidth: 178 CV score: 851746244
## Adaptive bandwidth: 337 CV score: 850008595
## Adaptive bandwidth: 239 CV score: 848248465
## Adaptive bandwidth: 300 CV score: 848306252
## Adaptive bandwidth: 262 CV score: 848110863
## Adaptive bandwidth: 285 CV score: 848124577
## Adaptive bandwidth: 270 CV score: 848053080
## Adaptive bandwidth: 279 CV score: 848021268
## Adaptive bandwidth: 273 CV score: 848008471
## Adaptive bandwidth: 276 CV score: 847973182
## Adaptive bandwidth: 273 CV score: 848008471
## Adaptive bandwidth: 274 CV score: 847965834
## Adaptive bandwidth: 273 CV score: 848008471
## Adaptive bandwidth: 273 CV score: 848008471
## Adaptive bandwidth: 272 CV score: 848036537
## Adaptive bandwidth: 272 CV score: 848036537
## Adaptive bandwidth: 271 CV score: 848053189
## Adaptive bandwidth: 271 CV score: 848053189
## Adaptive bandwidth: 270 CV score: 848053080
## Adaptive bandwidth: 270 CV score: 848053080
## Adaptive bandwidth: 269 CV score: 848076693
## Adaptive bandwidth: 269 CV score: 848076693
## Adaptive bandwidth: 268 CV score: 848085575
## Adaptive bandwidth: 268 CV score: 848085575
## Adaptive bandwidth: 267 CV score: 848054197
## Adaptive bandwidth: 267 CV score: 848054197
## Adaptive bandwidth: 266 CV score: 848037813
## Adaptive bandwidth: 266 CV score: 848037813
## Adaptive bandwidth: 265 CV score: 848079069
## Adaptive bandwidth: 265 CV score: 848079069
## Adaptive bandwidth: 264 CV score: 848108494
## Adaptive bandwidth: 264 CV score: 848108494######### Let's figure out our bandwidth: second, let's use distance!
myBandwidthDistance <- bw.gwr(fn_mean ~ old_pct_mean + bachelor_pct_mean + clinton_pct_mean + pop_density_mean,
adaptive = F,
data=GWR_inputGeo) ## Take a cup of tea and have a break, it will take a few minutes.
## -----A kind suggestion from GWmodel development group
## Fixed bandwidth: 2822927 CV score: 986105758
## Fixed bandwidth: 1745014 CV score: 936047750
## Fixed bandwidth: 1078827 CV score: 897789065
## Fixed bandwidth: 667100.5 CV score: 866110509
## Fixed bandwidth: 412639.7 CV score: 860061367
## Fixed bandwidth: 255374.3 CV score: 970183994
## Fixed bandwidth: 509835.1 CV score: 859122810
## Fixed bandwidth: 569905.2 CV score: 861077382
## Fixed bandwidth: 472709.8 CV score: 858604841
## Fixed bandwidth: 449765 CV score: 858911948
## Fixed bandwidth: 486890.4 CV score: 858697141
## Fixed bandwidth: 463945.7 CV score: 858668506
## Fixed bandwidth: 478126.3 CV score: 858612660
## Fixed bandwidth: 469362.2 CV score: 858618929
## Fixed bandwidth: 474778.7 CV score: 858603472
## Fixed bandwidth: 476057.3 CV score: 858605384
## Fixed bandwidth: 473988.4 CV score: 858603347
## Fixed bandwidth: 473500 CV score: 858603671
## Fixed bandwidth: 474290.3 CV score: 858603298
## Fixed bandwidth: 474476.8 CV score: 858603327
## Fixed bandwidth: 474175 CV score: 858603303
## Fixed bandwidth: 474361.5 CV score: 858603304
## Fixed bandwidth: 474246.2 CV score: 858603298
## Fixed bandwidth: 474219 CV score: 858603299
## Fixed bandwidth: 474263.1 CV score: 858603298
## Fixed bandwidth: 474273.5 CV score: 858603298
## Fixed bandwidth: 474256.6 CV score: 858603298
## Fixed bandwidth: 474267 CV score: 858603298
## Fixed bandwidth: 474260.6 CV score: 858603298
## Fixed bandwidth: 474264.6 CV score: 858603298
## Fixed bandwidth: 474265.5 CV score: 858603298
## Fixed bandwidth: 474264 CV score: 858603298
## Fixed bandwidth: 474264.9 CV score: 858603298#Creating the model
myGWR_model <- gwr.basic(fn_mean ~ old_pct_mean + bachelor_pct_mean + clinton_pct_mean + pop_density_mean,
adaptive = T,
data = GWR_inputGeo,
bw = myBandwidthKNeighbors) ## Warning in proj4string(data): CRS object has comment, which is lost in output#7) A map of coefficients for County Clinton Votes on g(n). Remember your descriptive caption.
tm_shape(myGWR_model$SDF) +
tm_polygons("clinton_pct_mean", size = 0.1, midpoint=NA,
border.alpha = 0, palette = "BrBG", n = 5,
palette="Spectral",
title='G(n) Coeff: Clinton voters') +
tm_shape(cnty) +
tm_polygons(alpha=0) +
tm_layout(legend.text.size = 0.6, title.size = 0.5, legend.position = c(0.01, 0.01))## Warning in sp::proj4string(obj): CRS object has comment, which is lost in output
#8) A map of coefficients for Mean County Population Density on g(n) Remember your descriptive caption.
tm_shape(myGWR_model$SDF) +
tm_polygons("pop_density_mean", size = 0.1, midpoint=NA,
border.alpha = 0, palette = "BrBG", n = 5,
palette="Spectral",
title='G(n) Coeff: Mean Population Density') +
tm_shape(cnty) +
tm_polygons(alpha=0) +
tm_layout(legend.text.size = 0.6, title.size = 0.5, legend.position = c(0.01, 0.01))## Warning in sp::proj4string(obj): CRS object has comment, which is lost in output
#9) An r squared map of your choice (you must say what the model was, e.g. “I am looking at mean(f(n) as a function of Clinton votes and Percent Elderly”)
myBandwidthKNeighbors2 <- bw.gwr(fn_mean ~ clinton_pct_mean + pop_density_mean,
adaptive = T,
data=GWR_inputGeo) ## Take a cup of tea and have a break, it will take a few minutes.
## -----A kind suggestion from GWmodel development group
## Adaptive bandwidth: 1778 CV score: 1035068060
## Adaptive bandwidth: 1107 CV score: 999055115
## Adaptive bandwidth: 691 CV score: 966755999
## Adaptive bandwidth: 435 CV score: 942313493
## Adaptive bandwidth: 275 CV score: 924108985
## Adaptive bandwidth: 178 CV score: 917795508
## Adaptive bandwidth: 116 CV score: 915430592
## Adaptive bandwidth: 80 CV score: 915636934
## Adaptive bandwidth: 141 CV score: 915422813
## Adaptive bandwidth: 153 CV score: 915980825
## Adaptive bandwidth: 129 CV score: 915435159
## Adaptive bandwidth: 143 CV score: 915557213
## Adaptive bandwidth: 134 CV score: 915464970
## Adaptive bandwidth: 139 CV score: 915465434
## Adaptive bandwidth: 135 CV score: 915519648
## Adaptive bandwidth: 137 CV score: 915566074
## Adaptive bandwidth: 135 CV score: 915519648
## Adaptive bandwidth: 136 CV score: 915512220
## Adaptive bandwidth: 135 CV score: 915519648
## Adaptive bandwidth: 135 CV score: 915519648
## Adaptive bandwidth: 134 CV score: 915464970
## Adaptive bandwidth: 134 CV score: 915464970
## Adaptive bandwidth: 133 CV score: 915408963
## Adaptive bandwidth: 140 CV score: 915502201
## Adaptive bandwidth: 140 CV score: 915502201
## Adaptive bandwidth: 139 CV score: 915465434
## Adaptive bandwidth: 139 CV score: 915465434
## Adaptive bandwidth: 138 CV score: 915475899
## Adaptive bandwidth: 138 CV score: 915475899
## Adaptive bandwidth: 137 CV score: 915566074
## Adaptive bandwidth: 137 CV score: 915566074
## Adaptive bandwidth: 136 CV score: 915512220
## Adaptive bandwidth: 136 CV score: 915512220
## Adaptive bandwidth: 135 CV score: 915519648
## Adaptive bandwidth: 135 CV score: 915519648
## Adaptive bandwidth: 134 CV score: 915464970
## Adaptive bandwidth: 134 CV score: 915464970myBandwidthDistance2 <- bw.gwr(fn_mean ~ clinton_pct_mean + pop_density_mean,
adaptive = F,
data=GWR_inputGeo) ## Take a cup of tea and have a break, it will take a few minutes.
## -----A kind suggestion from GWmodel development group
## Fixed bandwidth: 2822927 CV score: 1129946314
## Fixed bandwidth: 1745014 CV score: 1049415271
## Fixed bandwidth: 1078827 CV score: 987605543
## Fixed bandwidth: 667100.5 CV score: 946979963
## Fixed bandwidth: 412639.7 CV score: 918246622
## Fixed bandwidth: 255374.3 CV score: 924793178
## Fixed bandwidth: 509835.1 CV score: 930078609
## Fixed bandwidth: 352569.6 CV score: 910952095
## Fixed bandwidth: 315444.3 CV score: 909995673
## Fixed bandwidth: 292499.6 CV score: 912495512
## Fixed bandwidth: 329624.9 CV score: 909984907
## Fixed bandwidth: 338389 CV score: 910242324
## Fixed bandwidth: 324208.4 CV score: 909904553
## Fixed bandwidth: 320860.8 CV score: 909896642
## Fixed bandwidth: 318791.9 CV score: 909916439
## Fixed bandwidth: 322139.5 CV score: 909894118
## Fixed bandwidth: 322929.7 CV score: 909896050
## Fixed bandwidth: 321651.1 CV score: 909894235
## Fixed bandwidth: 322441.3 CV score: 909894549
## Fixed bandwidth: 321952.9 CV score: 909894041
## Fixed bandwidth: 321837.6 CV score: 909894069
## Fixed bandwidth: 322024.2 CV score: 909894053
## Fixed bandwidth: 321908.9 CV score: 909894045
## Fixed bandwidth: 321980.1 CV score: 909894043
## Fixed bandwidth: 321936.1 CV score: 909894042
## Fixed bandwidth: 321963.3 CV score: 909894042
## Fixed bandwidth: 321946.5 CV score: 909894041
## Fixed bandwidth: 321956.9 CV score: 909894041
## Fixed bandwidth: 321950.5 CV score: 909894041
## Fixed bandwidth: 321949 CV score: 909894041
## Fixed bandwidth: 321951.4 CV score: 909894041
## Fixed bandwidth: 321949.9 CV score: 909894041
## Fixed bandwidth: 321950.8 CV score: 909894041
## Fixed bandwidth: 321951.1 CV score: 909894041myGWR_model2 <- gwr.basic(fn_mean ~ clinton_pct_mean + pop_density_mean,
adaptive = T,
data = GWR_inputGeo,
bw = myBandwidthKNeighbors2)## Warning in proj4string(data): CRS object has comment, which is lost in outputtm_shape(myGWR_model2$SDF) +
tm_polygons(c("Local_R2"),
title='Mean(f(n) as a function of Clinton votes and Population density') +
tm_shape(cnty) +
tm_polygons(alpha=0)## Warning in sp::proj4string(obj): CRS object has comment, which is lost in output