Bay Area Real Estate (cont.)
[This article was first published on Analyst At Large » R, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.
Previously, I posted a short post about recent detached single house prices in San Leandro and Hayward areas. I received a little more data (sales data from the past month), so I thought it would be a good time for an update. I’d like to investigate which way the housing market in these areas is moving.
First, I started by looking at prices across the past 6 months.
The plots above show that housing prices rose substantially in San Leandro from January through May before cooling down slightly. House prices in Hayward seem to have been steady or even slightly declining over the past 6 months.
This is the highest level look, but it neglects many details (house size, # of sales, quality of home, neighborhood, etc.). I wanted to drill down one more level and look at cost per square foot (which should help us look across house sizes).
San Leandro cost per square foot has risen significantly since January, but has been flat since April. The cost of Hayward houses per square foot has been more or less stable with median prices in the $325-$350 / sq. ft. range most months.
There is a lot more analysis to do, but I have wedding planning to do. Here is the code…
###### Settings
options(scipen=10)
setwd("C:/Blog/SFHousing")
library(RColorBrewer)
col.9<-brewer.pal(9,"Oranges")
###### Loading data
sl1<-read.csv("SanLeandro.csv")
sl2<-read.csv("SanLeandro2.csv")
hay1<-read.csv("Hayward.csv")
hay2<-read.csv("Hayward2.csv")
sl<-rbind(sl1,sl2)
hay<-rbind(hay1,hay2)
###### Formatting data
sl$Sold.Price<-as.numeric(gsub('[[:punct:]]','',sl$Sold.Price))
sl$List.Price<-as.numeric(gsub('[[:punct:]]','',sl$List.Price))
hay$Sold.Price<-as.numeric(gsub('[[:punct:]]','',hay$Sold.Price))
hay$List.Price<-as.numeric(gsub('[[:punct:]]','',hay$List.Price))
sl$Baths.Partial[is.na(sl$Baths.Partial)]<-0
sl$Baths2<-sl$Baths+sl$Baths.Partial*.5
sl<-sl[order(sl$Bedrooms,sl$Baths2),]
sl$Title<-paste0(sl$Bedrooms,"BD,",sl$Baths2,"BA")
# Remove house types only listed once
sl<-sl[sl$Title %in% names(table(sl$Title))[as.numeric(which(table(sl$Title)>1))],]
sllev<-unique(sl$Title)
sl$Title<-factor(sl$Title,levels=sllev)
hay$Baths.Partial[is.na(hay$Baths.Partial)]<-0
hay$Baths2<-hay$Baths+hay$Baths.Partial*.5
hay<-hay[order(hay$Bedrooms,hay$Baths2),]
hay$Title<-paste0(hay$Bedrooms,"BD,",hay$Baths2,"BA")
# Remove house types only listed once
hay<-hay[hay$Title %in% names(table(hay$Title))[as.numeric(which(table(hay$Title)>1))],]
haylev<-unique(hay$Title)
hay$Title<-factor(hay$Title,levels=haylev)
minmin<-floor(min(sl$Sold.Price)/50000)*50000
maxmax<-ceiling(max(sl$Sold.Price)/50000)*50000
par(mar=c(6,5,5,5))
boxplot(sl$Sold.Price~sl$Title,main="San Leandro - Sold Price",col="skyblue",ylim=c(minmin,maxmax),
yaxt="n")
axis(2,at=seq(minmin,maxmax,by=50000),labels=paste0("$",prettyNum(seq(minmin,maxmax,by=50000),big.mark=",")),las=2)
axis(4,at=seq(minmin,maxmax,by=50000),labels=paste0("$",prettyNum(seq(minmin,maxmax,by=50000),big.mark=",")),las=2)
for (i in seq(minmin,maxmax,by=25000))
{abline(h=i,lty=3,col="lightgray")}
minmin2<-floor(min(hay$Sold.Price)/50000)*50000
maxmax2<-ceiling(max(hay$Sold.Price)/50000)*50000
par(mar=c(6,5,5,5))
boxplot(hay$Sold.Price~hay$Title,main="Hayward - Sold Price",col="lightgreen",ylim=c(minmin,maxmax),
yaxt="n")
axis(2,at=seq(minmin,maxmax2,by=50000),labels=paste0("$",prettyNum(seq(minmin2,maxmax2,by=50000),big.mark=",")),las=2)
axis(4,at=seq(minmin,maxmax2,by=50000),labels=paste0("$",prettyNum(seq(minmin2,maxmax2,by=50000),big.mark=",")),las=2)
for (i in seq(minmin,maxmax2,by=25000))
{abline(h=i,lty=3,col="lightgray")}
###### Sale Price by Month
sl$Closing.Date<-as.Date(sl$Closing.Date,format="%m/%d/%Y")
hay$Closing.Date<-as.Date(hay$Closing.Date,format="%m/%d/%Y")
sl$MONTH<-substr(sl$Closing.Date,0,7)
hay$MONTH<-substr(hay$Closing.Date,0,7)
par(mar=c(6,5,5,5))
boxplot(sl$Sold.Price~sl$MONTH,col=col.9[4],main="San Leandro Sale Prices by Month",yaxt="n")
axis(2,at=seq(300000,450000,by=25000),labels=paste0("$",gsub(" ","",prettyNum(seq(300000,450000,by=25000),big.mark=","))),las=2)
axis(4,at=seq(300000,450000,by=25000),labels=paste0("$",gsub(" ","",prettyNum(seq(300000,450000,by=25000),big.mark=","))),las=2)
for (i in seq(300000,450000,by=25000))
{abline(h=i,lty=3,col="lightgray")}
par(mar=c(6,5,5,5))
boxplot(hay$Sold.Price~hay$MONTH,col=col.9[7],main="Hayward Sale Prices by Month",yaxt="n")
axis(2,at=seq(300000,450000,by=25000),labels=paste0("$",gsub(" ","",prettyNum(seq(300000,450000,by=25000),big.mark=","))),las=2)
axis(4,at=seq(300000,450000,by=25000),labels=paste0("$",gsub(" ","",prettyNum(seq(300000,450000,by=25000),big.mark=","))),las=2)
for (i in seq(300000,450000,by=25000))
{abline(h=i,lty=3,col="lightgray")}
###### Sale/sqft price by month
sl$PriceSQFT<-sl$List.Price/sl$Sq.Ft.Apx
hay$PriceSQFT<-hay$List.Price/hay$Sq.Ft.Apx
par(mar=c(6,5,5,5))
boxplot(sl$PriceSQFT~sl$MONTH,col=col.9[4],main="San Leandro Sale Prices by Month",yaxt="n")
axis(2,at=seq(150,500,by=25),labels=paste0("$",gsub(" ","",prettyNum(seq(150,500,by=25),big.mark=","))),las=2)
axis(4,at=seq(150,500,by=25),labels=paste0("$",gsub(" ","",prettyNum(seq(150,500,by=25),big.mark=","))),las=2)
for (i in seq(150,500,by=25))
{abline(h=i,lty=3,col="lightgray")}
par(mar=c(6,5,5,5))
boxplot(hay$PriceSQFT~hay$MONTH,col=col.9[7],main="Hayward Sale Prices by Month",yaxt="n")
axis(2,at=seq(150,500,by=25),labels=paste0("$",gsub(" ","",prettyNum(seq(150,500,by=25),big.mark=","))),las=2)
axis(4,at=seq(150,500,by=25),labels=paste0("$",gsub(" ","",prettyNum(seq(150,500,by=25),big.mark=","))),las=2)
for (i in seq(150,500,by=25))
{abline(h=i,lty=3,col="lightgray")}
###### Sale-List Price by Month
sl$CHANGE<-sl$Sold.Price-sl$List.Price
hay$CHANGE<-hay$Sold.Price-hay$List.Price
par(mar=c(6,5,5,5))
boxplot(sl$CHANGE~sl$MONTH,col=col.9[4],ylim=c(-50000,50000),
main="San Leandro Sale Price - List Price by Month",yaxt="n")
axis(2,at=seq(-50000,50000,by=10000),labels=paste0("$",gsub(" ","",prettyNum(seq(-50000,50000,by=10000),big.mark=","))),las=2)
axis(4,at=seq(-50000,50000,by=10000),labels=paste0("$",gsub(" ","",prettyNum(seq(-50000,50000,by=10000),big.mark=","))),las=2)
for (i in seq(-50000,50000,by=10000))
{abline(h=i,lty=3,col="lightgray")}
par(mar=c(6,5,5,5))
boxplot(hay$CHANGE~hay$MONTH,col=col.9[7],ylim=c(-50000,50000),
main="Hayward Sale Price - List Price by Month",yaxt="n")
axis(2,at=seq(-50000,50000,by=10000),labels=paste0("$",gsub(" ","",prettyNum(seq(-50000,50000,by=10000),big.mark=","))),las=2)
axis(4,at=seq(-50000,50000,by=10000),labels=paste0("$",gsub(" ","",prettyNum(seq(-50000,50000,by=10000),big.mark=","))),las=2)
for (i in seq(-50000,50000,by=10000))
{abline(h=i,lty=3,col="lightgray")}
###### Days on Market by Month
par(mar=c(6,5,5,5))
boxplot(sl$Days.On.Market~sl$MONTH,col=col.9[4],main="San Leandro DOM by Month",ylim=c(0,70),yaxt="n")
axis(2,at=seq(0,70,by=10),labels=seq(0,70,by=10),las=2)
axis(4,at=seq(0,70,by=10),labels=seq(0,70,by=10),las=2)
for (i in seq(0,70,by=10))
{abline(h=i,lty=3,col="lightgray")}
par(mar=c(6,5,5,5))
boxplot(hay$Days.On.Market~hay$MONTH,col=col.9[7],main="Hayward DOM by Month",ylim=c(0,70),yaxt="n")
axis(2,at=seq(0,70,by=10),labels=seq(0,70,by=10),las=2)
axis(4,at=seq(0,70,by=10),labels=seq(0,70,by=10),las=2)
for (i in seq(0,70,by=10))
{abline(h=i,lty=3,col="lightgray")}
To leave a comment for the author, please follow the link and comment on their blog: Analyst At Large » R.
R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.