Homework IPUMS
Asiya
4/19/2021
Load
setwd("/Users/asiyavalidova/Dropbox/Demography/GIS/w10/IPUMS")
library(ipumsr)
ddi <- read_ipums_ddi("usa_00004.xml")
data <- read_ipums_micro(ddi)## Use of data from IPUMS USA is subject to conditions including that users should
## cite the data appropriately. Use command `ipums_conditions()` for more details.data<-haven::zap_labels(data)
names(data)<-tolower(names(data))
library(survey)## Loading required package: grid## Loading required package: Matrix## Loading required package: survival##
## Attaching package: 'survey'## The following object is masked from 'package:graphics':
##
## dotchartlibrary(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(car)## Loading required package: carData##
## Attaching package: 'car'## The following object is masked from 'package:dplyr':
##
## recodelibrary(ggplot2)
library(tigris)## To enable
## caching of data, set `options(tigris_use_cache = TRUE)` in your R script or .Rprofile.library(classInt)
library(tmap)### Download geographic data for Public Use Microdata Areas
options(tigris_class = "sf")
pumas<-pumas(state = "TX", year = 2019, cb = T)##
|
| | 0%
|
|== | 2%
|
|=== | 5%
|
|==== | 5%
|
|===== | 7%
|
|====== | 9%
|
|======== | 12%
|
|========== | 14%
|
|=========== | 15%
|
|============ | 17%
|
|============= | 19%
|
|=============== | 21%
|
|================ | 23%
|
|================= | 25%
|
|=================== | 27%
|
|==================== | 28%
|
|===================== | 31%
|
|======================= | 33%
|
|======================== | 34%
|
|========================= | 36%
|
|========================== | 38%
|
|============================ | 40%
|
|============================== | 42%
|
|============================== | 44%
|
|================================ | 46%
|
|================================= | 47%
|
|=================================== | 49%
|
|==================================== | 52%
|
|===================================== | 53%
|
|======================================= | 55%
|
|======================================== | 57%
|
|========================================= | 59%
|
|=========================================== | 61%
|
|============================================ | 62%
|
|============================================= | 65%
|
|============================================== | 66%
|
|================================================ | 68%
|
|================================================== | 71%
|
|================================================== | 72%
|
|==================================================== | 74%
|
|===================================================== | 75%
|
|====================================================== | 78%
|
|======================================================== | 80%
|
|========================================================= | 81%
|
|=========================================================== | 84%
|
|=========================================================== | 85%
|
|============================================================= | 87%
|
|=============================================================== | 90%
|
|================================================================ | 91%
|
|================================================================= | 93%
|
|================================================================== | 94%
|
|==================================================================== | 97%
|
|===================================================================== | 99%
|
|======================================================================| 100%plot(pumas["GEOID10"], main = "Public Use Microdata Areas in Texas")
names(pumas)<-tolower(names(pumas))
pumas$puma<-as.numeric(pumas$pumace10)
data<-data%>%
mutate(
migrate=Recode(migrate1,recodes="1='not_migrate';2:4='migrate';else=NA")
)
data<-data%>%
filter(!is.na(migrate))
data$pwt <- data$perwt/100 Generate survey design object
des<-svydesign(ids = ~cluster,
strata = ~ strata,
weights = ~pwt,
data = data)perform survey estimation
puma_est_migr<-svyby(formula=~migrate,
by=~puma,
design = des,
FUN=svymean,na.rm=T)join to geography
geo<-geo_join(pumas, puma_est_migr, by_sp="puma",by_df= "puma") ## Warning: `group_by_()` was deprecated in dplyr 0.7.0.
## Please use `group_by()` instead.
## See vignette('programming') for more helpgeo$not_migrate<-geo$migratenot_migrate*100
head(geo)## Simple feature collection with 6 features and 15 fields
## geometry type: MULTIPOLYGON
## dimension: XY
## bbox: xmin: -98.56392 ymin: 27.82079 xmax: -93.83772 ymax: 32.4076
## geographic CRS: NAD83
## statefp10 pumace10 affgeoid10 geoid10
## 1 48 04302 7950000US4804302 4804302
## 2 48 05500 7950000US4805500 4805500
## 3 48 05000 7950000US4805000 4805000
## 4 48 05901 7950000US4805901 4805901
## 5 48 06500 7950000US4806500 4806500
## 6 48 01700 7950000US4801700 4801700
## name10
## 1 Jefferson County (Outside Beaumont City)--Port Arthur City
## 2 Golden Crescent Regional Planning Commission (North) & Wilson & Karnes Counties
## 3 Houston-Galveston Area Council (West)
## 4 San Antonio City (Central)
## 5 Coastal Bend COG (Northeast)
## 6 East Texas COG (Southeast)--Rusk, Cherokee & Panola Counties
## lsad10 aland10 awater10 puma migratemigrate migratenot_migrate
## 1 P0 2072607049 604906509 4302 0.15496671 0.8450333
## 2 P0 16001092181 131878837 5500 0.11821855 0.8817814
## 3 P0 11134586598 1439210499 5000 0.09854454 0.9014555
## 4 P0 49642078 744374 5901 0.14190722 0.8580928
## 5 P0 6724202765 876050758 6500 0.16398316 0.8360168
## 6 P0 7221787148 86900821 1700 0.14791047 0.8520895
## se.migratemigrate se.migratenot_migrate rank geometry
## 1 0.009040789 0.009040789 1 MULTIPOLYGON (((-94.44491 3...
## 2 0.007426341 0.007426341 1 MULTIPOLYGON (((-98.39758 2...
## 3 0.006337391 0.006337391 1 MULTIPOLYGON (((-96.87422 2...
## 4 0.008863613 0.008863613 1 MULTIPOLYGON (((-98.56338 2...
## 5 0.010124744 0.010124744 1 MULTIPOLYGON (((-96.8229 28...
## 6 0.008621732 0.008621732 1 MULTIPOLYGON (((-95.46224 3...
## not_migrate
## 1 84.50333
## 2 88.17814
## 3 90.14555
## 4 85.80928
## 5 83.60168
## 6 85.20895Map estimates
tmap_mode("plot")## tmap mode set to plottingtm_basemap("OpenStreetMap.Mapnik")+
tm_shape(geo)+
tm_polygons("not_migrate",
style="kmeans",
n=8,
legend.hist = TRUE) +
tm_layout(legend.outside = TRUE,
title = "Migration rate in Texas PUMAs 2019") ## Linking to GEOS 3.8.1, GDAL 3.1.4, PROJ 6.3.1