DEM 7093 HW 1
Monica Cruz
June 5, 2018
install.packages(“censusapi”) install.packages(“tidycensus”) install.packages(“sf”)
library(censusapi)##
## Attaching package: 'censusapi'## The following object is masked from 'package:methods':
##
## getFunctionlibrary(tidycensus)
library(sf)## Linking to GEOS 3.6.1, GDAL 2.2.3, proj.4 4.9.3census_api_key(key ="f71931186e975910aa774fdd6aff604b31e9fe71")## To install your API key for use in future sessions, run this function with `install = TRUE`.Look at available ACS variables
v15_Profile <- load_variables(2015 , "acs5/profile", cache = TRUE) #demographic profile tables
v15_tables <- load_variables(2015 , "acs5", cache = TRUE) #all tables
#v10_sf1_tables <- load_variables(2010 , "sf1", cache = TRUE) #all tables for 2010 SF1
#v10_sf1_tables <- load_variables(2000 , "sf3", cache = TRUE) #all tables for 2000 SF#
View(v15_Profile)
#Search for variables by
v15_Profile[grep(x = v15_Profile$label, "Hispanic"), c("name", "label")]## # A tibble: 34 x 2
## name label
## <chr> <chr>
## 1 DP02_0149E Estimate!!ANCESTRY!!Total population!!West Indian (exclu~
## 2 DP02_0149PE Percent!!ANCESTRY!!Total population!!West Indian (exclud~
## 3 DP02PR_0149E Estimate!!ANCESTRY!!Total population!!West Indian (exclu~
## 4 DP02PR_0149PE Percent!!ANCESTRY!!Total population!!West Indian (exclud~
## 5 DP05_0066E Estimate!!HISPANIC OR LATINO AND RACE!!Total population!~
## 6 DP05_0066PE Percent!!HISPANIC OR LATINO AND RACE!!Total population!!~
## 7 DP05_0067E Estimate!!HISPANIC OR LATINO AND RACE!!Total population!~
## 8 DP05_0067PE Percent!!HISPANIC OR LATINO AND RACE!!Total population!!~
## 9 DP05_0068E Estimate!!HISPANIC OR LATINO AND RACE!!Total population!~
## 10 DP05_0068PE Percent!!HISPANIC OR LATINO AND RACE!!Total population!!~
## # ... with 24 more rowsv15_Profile[grep(x = v15_Profile$label, "Built 2000 to 2009"), c("name", "label")]## # A tibble: 2 x 2
## name label
## <chr> <chr>
## 1 DP04_0019E Estimate!!YEAR STRUCTURE BUILT!!Total housing units!!Built ~
## 2 DP04_0019PE Percent!!YEAR STRUCTURE BUILT!!Total housing units!!Built 2~Extract from ACS summary file data profile variables from 2015 for Harris County, TX Census Tracts
The data profile tables are very useful because they contain lots of pre-calculated variables.
library(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, unionha_acs<-get_acs(geography = "tract", state="TX", county = c("Harris County"), year = 2015,
variables=c( "DP05_0001E", "DP03_0009P", "DP03_0062E", "DP03_0119PE",
"DP05_0001E","DP02_0009PE","DP02_0008PE", "DP02_0040E","DP02_0038E",
"DP02_0066PE","DP02_0067PE","DP02_0080PE","DP02_0092PE",
"DP03_0005PE","DP03_0028PE","DP03_0062E","DP03_0099PE","DP03_0101PE",
"DP03_0119PE","DP04_0046PE","DP05_0072PE","DP05_0073PE",
"DP05_0066PE", "DP05_0072PE", "DP02_0113PE") ,
summary_var = "B01001_001",
geometry = T, output = "wide")## Getting data from the 2011-2015 5-year ACS## Downloading feature geometry from the Census website. To cache shapefiles for use in future sessions, set `options(tigris_use_cache = TRUE)`.## Using the ACS Data Profile
## Using the ACS Data Profile#create a county FIPS code - 5 digit
ha_acs$county<-substr(ha_acs$GEOID, 1, 5)
#rename variables and filter missing cases
library(dbplyr)##
## Attaching package: 'dbplyr'## The following objects are masked from 'package:dplyr':
##
## ident, sqlha_acs2<-ha_acs%>%
mutate(phisp=DP05_0066PE) %>%
filter(complete.cases(phisp))
class(ha_acs2)Extract from ACS summary file data profile variables from 2015 for Dallas County, TX Census Tracts
The data profile tables are very useful because they contain lots of pre-calculated variables.
library(dplyr)
dal_acs<-get_acs(geography = "tract", state="TX", county = c("Dallas County"), year = 2015,
variables=c( "DP05_0001E", "DP03_0009P", "DP03_0062E", "DP03_0119PE",
"DP05_0001E","DP02_0009PE","DP02_0008PE", "DP02_0040E","DP02_0038E",
"DP02_0066PE","DP02_0067PE","DP02_0080PE","DP02_0092PE",
"DP03_0005PE","DP03_0028PE","DP03_0062E","DP03_0099PE","DP03_0101PE",
"DP03_0119PE","DP04_0046PE","DP05_0072PE","DP05_0073PE",
"DP05_0066PE", "DP05_0072PE", "DP02_0113PE") ,
summary_var = "B01001_001",
geometry = T, output = "wide")## Getting data from the 2011-2015 5-year ACS## Downloading feature geometry from the Census website. To cache shapefiles for use in future sessions, set `options(tigris_use_cache = TRUE)`.## Using the ACS Data Profile
## Using the ACS Data Profile#create a county FIPS code - 5 digit
dal_acs$county<-substr(dal_acs$GEOID, 1, 5)
#rename variables and filter missing cases
library(dbplyr)
dal_acs2<-dal_acs%>%
mutate(phisp=DP05_0066PE) %>%
filter(complete.cases(phisp))
class(dal_acs2)Harris County Housing
library(dplyr)
ha_housing<-get_acs(geography = "tract", state="TX", county = c("Harris County"), year = 2015,
variables=c( "DP04_0019PE") ,
summary_var = "B01001_001",
geometry = T, output = "wide")## Getting data from the 2011-2015 5-year ACS## Downloading feature geometry from the Census website. To cache shapefiles for use in future sessions, set `options(tigris_use_cache = TRUE)`.## Using the ACS Data Profile#create a county FIPS code - 5 digit
ha_housing$county<-substr(ha_housing$GEOID, 1, 5)
#rename variables and filter missing cases
library(dbplyr)
ha_housing2<-ha_housing%>%
mutate(prophousing= DP04_0019PE) %>%
filter(complete.cases(prophousing))
class(ha_housing2)## [1] "sf" "data.frame"Dallas County Housing
library(dplyr)
dal_housing<-get_acs(geography = "tract", state="TX", county = c("Dallas County"), year = 2015,
variables=c( "DP04_0019PE") ,
summary_var = "B01001_001",
geometry = T, output = "wide")## Getting data from the 2011-2015 5-year ACS## Downloading feature geometry from the Census website. To cache shapefiles for use in future sessions, set `options(tigris_use_cache = TRUE)`.## Using the ACS Data Profile#create a county FIPS code - 5 digit
dal_housing$county<-substr(dal_housing$GEOID, 1, 5)
#rename variables and filter missing cases
library(dbplyr)
dal_housing2<-dal_housing%>%
mutate(prophousing= DP04_0019PE) %>%
filter(complete.cases(prophousing))
class(dal_housing2)## [1] "sf" "data.frame"Write data out to shapefile for Hispanic Population
#change the directory
sf::st_write(ha_acs2,dsn="C:/Users/Monica/Documents/GIS Class/sa_tract_dp.shp",layer="sa_tract_dp", driver="ESRI Shapefile", delete_layer=T, update=T)#change the directory
sf::st_write(dal_acs2,dsn="C:/Users/Monica/Documents/GIS Class/sa_tract_dp.shp",layer="sa_tract_dp", driver="ESRI Shapefile", delete_layer=T, update=T)Some basic mapping of variables
Here I generate a quantile break for % Hispanic in census tracts and compare it to a Jenks break
install.packages(“classInt”) install.packages(“devtools”) devtools::install_github(“thomasp85/patchwork”) install.packages(“ggsn”)
library(classInt)## 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'))`library(patchwork)
#install.packages("dplyr")
library(dplyr)
phisp_map<-ha_acs2 %>%
mutate(chisp=cut(phisp,breaks = quantile(phisp, na.rm=T, p=seq(0,1,length.out = 6)),include.lowest = T),
jhisp = cut(phisp,breaks=data.frame(classIntervals(var=ha_acs2$phisp, n=5, style="jenks")[2])[,1], include.lowest = T))
library(ggsn)## Loading required package: ggplot2p1<-ggplot(phisp_map, aes(fill = jhisp, color = jhisp)) +
geom_sf() +
ggtitle("Proportion Hispanic",
subtitle = "Harris County Texas, 2015 - Jenks Breaks")+
scale_fill_brewer(palette = "Blues") +
scale_color_brewer(palette = "Blues")+
theme(axis.text.x = element_blank(), axis.text.y = element_blank())
p1
phisp_map<-dal_acs2 %>%
mutate(chisp=cut(phisp,breaks = quantile(phisp, na.rm=T, p=seq(0,1,length.out = 6)),include.lowest = T),
jhisp = cut(phisp,breaks=data.frame(classIntervals(var=dal_acs2$phisp, n=5, style="jenks")[2])[,1], include.lowest = T))
library(ggsn)
p2<-ggplot(phisp_map, aes(fill = jhisp, color = jhisp)) +
geom_sf() +
ggtitle("Proportion Hispanic",
subtitle = "Dallas County Texas, 2015 - Jenks Breaks")+
scale_fill_brewer(palette = "Blues") +
scale_color_brewer(palette = "Blues")+
theme(axis.text.x = element_blank(), axis.text.y = element_blank())
p2 
Write data out to shapefile for Housing
#change the directory
sf::st_write(ha_housing2,dsn="C:/Users/Monica/Documents/GIS Class/sa_tract_dp.shp",layer="sa_tract_dp", driver="ESRI Shapefile", delete_layer=T, update=T)#change the directory
sf::st_write(dal_housing2,dsn="C:/Users/Monica/Documents/GIS Class/sa_tract_dp.shp",layer="sa_tract_dp", driver="ESRI Shapefile", delete_layer=T, update=T)Some basic mapping of variables
Here I generate a quantile break for % Hispanic in census tracts and compare it to a Jenks break
install.packages(“classInt”) install.packages(“devtools”) devtools::install_github(“thomasp85/patchwork”) install.packages(“ggsn”)
library(classInt)
library(patchwork)
#install.packages("dplyr")
library(dplyr)
housing_map<-ha_housing2 %>%
mutate(chousing=cut(prophousing,breaks = quantile(prophousing, na.rm=T, p=seq(0,1,length.out = 6)),include.lowest = T),
jhousing = cut(prophousing,breaks=data.frame(classIntervals(var=ha_housing2$prophousing, n=5, style="jenks")[2])[,1], include.lowest = T))
library(ggsn)
p3<-ggplot(housing_map, aes(fill = jhousing, color = jhousing)) +
geom_sf() +
ggtitle("Proportion Housing Built 2000-2009",
subtitle = "Harris County Texas, 2015 - Jenks Breaks")+
scale_fill_brewer(palette = "Blues") +
scale_color_brewer(palette = "Blues")+
theme(axis.text.x = element_blank(), axis.text.y = element_blank())
p3
housing_map<-dal_housing2 %>%
mutate(chousing=cut(prophousing,breaks = quantile(prophousing, na.rm=T, p=seq(0,1,length.out = 6)),include.lowest = T),
jhousing = cut(prophousing,breaks=data.frame(classIntervals(var=dal_housing2$prophousing, n=5, style="jenks")[2])[,1], include.lowest = T))
library(ggsn)
p4<-ggplot(housing_map, aes(fill = jhousing, color = jhousing)) +
geom_sf() +
ggtitle("Proportion Housing Built 2000-2009",
subtitle = "Dallas County Texas, 2015 - Jenks Breaks")+
scale_fill_brewer(palette = "Blues") +
scale_color_brewer(palette = "Blues")+
theme(axis.text.x = element_blank(), axis.text.y = element_blank())
p4
Summarize Hispanic population in both counties
summary(ha_acs2$phisp)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 20.45 35.65 41.44 60.38 97.40summary(dal_acs2$phisp)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 16.20 33.50 37.65 57.00 96.20The percent of the population that is Hispanic in Harris County is 41.44%, slightly higher than the percent Hispanic in Dallas County at 37.65%
Summarize proportion of housing built between 2000-2009
summary(ha_housing2$prophousing)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 3.50 11.65 17.65 26.12 90.60summary(dal_housing2$prophousing)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 2.15 6.80 12.75 18.50 83.50