Analyzing GDP by Industry with R

 

library(quantmod)

library(Quandl)

library(xts)

library(zoo)

Industry_Data <- read.csv("Industry Data.csv")

View(Industry_Data)

GDP<-ts(Industry_Data, start=c(2005,1), end=c(2020,2), frequency=4)

data<-GDP

data

# Percent changes from previous

percent_GDP<-diff(data, lag=4)/lag(data, k=-4)*100

Hw# Percentage of each industry in total industry

pct_GDP<-(data/data[,1])*100

summary(percent_GDP)

plot(pct_GDP)

par(mfrow=c(2,1))

plot(percent_GDP[,2], main="Private Industry")

plot(pct_GDP[,2])

par(mfrow=c(2,1))

plot(percent_GDP[,3], main="  Agriculture, forestry, fishing, and hunting")

plot(pct_GDP[,3])

par(mfrow=c(2,1))

plot(percent_GDP[,4], main="      Farms")

plot(pct_GDP[,4])

par(mfrow=c(2,1))

plot(percent_GDP[,6], main="       Mining")

plot(pct_GDP[,6])

par(mfrow=c(2,1))

plot(percent_GDP[,7], main="        Oil and gas extraction")

plot(pct_GDP[,7])

par(mfrow=c(2,1))

plot(percent_GDP[,11], main=" Construction")

plot(pct_GDP[,11])

par(mfrow=c(2,1))

plot(percent_GDP[,12], main="   Manufacturing")

plot(pct_GDP[,12])

par(mfrow=c(2,1))

plot(percent_GDP[,13], main="     Durable goods")

plot(pct_GDP[,13])

par(mfrow=c(2,1))

plot(percent_GDP[,19], main="Computer and electronic products")

plot(pct_GDP[,19])

par(mfrow=c(2,1))

plot(percent_GDP[,20], main="Electrical equipment, appliances, and components")

plot(pct_GDP[,20])

par(mfrow=c(2,1))

plot(percent_GDP[,21], main="Motor vehicles, bodies and trailers, and parts")

plot(pct_GDP[,21])

par(mfrow=c(2,1))

plot(percent_GDP[,27], main="    Textile mills and textile product mills")

plot(pct_GDP[,27])

par(mfrow=c(2,1))

plot(percent_GDP[,28], main="         Apparel and leather and allied products")

plot(pct_GDP[,28])

par(mfrow=c(2,1))

plot(percent_GDP[,34], main="    Wholesale trade")

plot(pct_GDP[,34])

par(mfrow=c(2,1))

plot(percent_GDP[,35], main="     Retail trade")

plot(pct_GDP[,35])

par(mfrow=c(2,1))

plot(percent_GDP[,40], main="   Transportation and warehousing")

plot(pct_GDP[,40])

par(mfrow=c(2,1))

plot(percent_GDP[,41], main="      Air transportation")

plot(pct_GDP[,41])

par(mfrow=c(2,1))

plot(percent_GDP[,42], main=" Rail transportation")

plot(pct_GDP[,42])

par(mfrow=c(2,1))

plot(percent_GDP[,49], main="Information")

plot(pct_GDP[,49])

par(mfrow=c(2,1))

plot(percent_GDP[,55], main="    Finance and insurance")

plot(pct_GDP[,55])

par(mfrow=c(2,1))

plot(percent_GDP[,60], main=" Real estate")

plot(pct_GDP[,60])

par(mfrow=c(2,1))

plot(percent_GDP[,62], main=" Housing")

plot(pct_GDP[,62])

Analyzing Gross Domestic Product (GDP) as of 2020-07-01

 

library(Quandl)

library(ggplot2)

library(tseries);library(timeseries);library(xts);library(forecast)

library (quantmod)

library(psych)

library(plotly) #install.package(plotly)

getSymbols(c('GDPDEF','GDP','PCEC','GPDI','NETEXP','GCE'), src='FRED')

ratio_PCEC=PCEC/GDP*100

ratio_GPDI=GPDI/GDP*100

ratio_NETEXP=NETEXP/GDP*100

ratio_GCE=GCE/GDP*100

basket<-cbind(ratio_PCEC, ratio_GPDI, ratio_NETEXP, ratio_GCE)

summary(basket)

tail(basket)

myColors <- c("red", "darkgreen", "goldenrod", "darkblue")

plot(x = basket, xlab = "Year", ylab = "Percent",

       main = "Percent in GDP", col = myColors, screens = 1, subset = "1980-01-04/")

legend(x = "topleft", legend = c("PCEC", "GDPI", "NETEXP", "GCE"),

       lty = 1, col = myColors)

describe(ratio_GPDI)

plot(ratio_PCEC, main="% of Personal Consumption Expenditure in GDP", ylab="Percent")

lines(mean_PCEC, col='red')

plot(ratio_GPDI, main="% of Gross Private Domestic Investment in GDP")

plot(ratio_NETEXP, main="% of Net Export in GDP")

plot(ratio_GCE, main="% of Government Consumption Expenditure in GDP")

Diff_GDP=Delt(GDP, k=4)*100

Diff_PCEC=Delt(PCEC, k=4)*100

Diff_GPDI=Delt(GPDI, k=4)*100

Diff_NETEXP=Delt(NETEXP, k=4)*100

Diff_GCE=Delt(GCE, k=4)*100

Diff_basket<-cbind(Diff_GDP, Diff_PCEC, Diff_GPDI, Diff_GCE)

myColors <- c("red", "darkgreen", "goldenrod", "darkblue")

plot(x = Diff_basket, xlab = "Year", ylab = "Percent",

     main = "Percent in GDP", col = myColors, screens = 1, subset = "1980-01-04/")

legend(x = "topleft", legend = c("GDP", "PCEC", "GDPI",  "GCE"),

       lty = 1, col = myColors)

Diff_GDPDEF=Delt(GDPDEF, k=4)*100

Real_GDP=Diff_GDP-Diff_GDPDEF

plot(Real_GDP)

Housing Top 20 cities with R as of 10-2020

 

download.file("https://s3-us-west-2.amazonaws.com/econresearch/Reports/Core/RDC_InventoryCoreMetrics_State.csv",

              destfile = "State.csv")

download.file("https://s3-us-west-2.amazonaws.com/econresearch/Reports/Core/RDC_InventoryCoreMetrics_Metro.csv",

              destfile = "Metro.csv")

library(ggplot2)

State_data<-read.csv("State.csv")

Metro_data<-read.csv("Metro.csv")

taland

Metro_prices<-Metro_data [which(Metro_data$Hhrank<21),]

Metro_top<-subset(Metro_data,Metro_data$Hrank <21)

Metro_top

ratio_yy<-Metro_prices$price_increased_count_yy/Metro_prices$price_reduced_count_yy

ratio_mm<-Metro_prices$price_increased_count_mm/Metro_prices$price_reduced_count_mm

barplot(ratio_yy, main='Ratio of price increase to decrease in Top 20 cities Y to Y', col="blue",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7, cex.names = 0.6, las=2)

barplot(ratio_mm, main='Ratio of price increase to decrease in Top 20 cities M to M', col="red",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7, cex.names = 0.6, las=2)

        

barplot(Metro_prices$Median.Listing.Price, main='Median Prices for Top 20 cities', col="blue",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7,

        

        

        cex.names = 0.5, las=2)

barplot(Metro_prices$Median.Listing.Price.Y.Y, main='Median Prices for Top 20 cities Y to Y', col="red",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7,

        cex.names = 0.6, las=2)

barplot(Metro_prices$Median.Listing.Price.M.M, main='Median Prices for Top 20 cities M to M', col="blue",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7,

        cex.names = 0.6, las=2)

barplot(Metro_prices$Active.Listing.Count.Y.Y, main='Active Listing for Top 20 cities Y to Y', col="blue",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7,

        cex.names = 0.6, las=2)

barplot(Metro_prices$Active.Listing.Count.M.M, main='Active Listing for Top 20 cities M to M', col="blue",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7,

        cex.names = 0.6, las=2)

barplot(Metro_prices$Days.on.Market.Y.Y, main='Days on Market for Top 20 cities Y to Y', col="red",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7,

        cex.names = 0.6, las=2)

barplot(Metro_prices$price_increased_count_yy, main='Price Increased count for Top 20 cities Y to Y', col="green",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7,

        cex.names = 0.6, las=2)

barplot(Metro_prices$pending_ratio_yy, main='Price Pending ratio for Top 20 cities Y to Y', col="green",

        names.arg=Metro_prices$cbsa_title, cex.axis=0.7,

        cex.names = 0.5, las=2)

ggplot(Metro_prices, aes(x=factor(Hhrank), y=Median.Listing.Price.Y.Y)) +

     geom_col(fill="lightblue", colour="red")

     geom_text(aes(label=Median.Listing.Price.Y.Y), vjust=-0.2)

ggplot(Metro_prices, aes(x=Metro_prices$Median.Listing.Price.Y.Y)) +

  geom_histogram()

barplot(Metro_prices[order(Metro_prices$Median.Listing.Price.Y.Y)], horiz=T)

hist(Metro_prices$Median.Listing.Price)

hist(Metro_data$Median.Listing.Price.Y.Y)

summary(Metro_data$Median.Listing.Price.Y.Y)

barplot(Metro_prices$Median.Listing.Price.Y.Y, cex.names = 0.9, las=2)

# Select Housing Prices for top 20 cities

Housing<- subset(Metro_data, Metro_data$Hhrank <'20') 

Housing<-Housing[order(Housing$Month),]

ratio=Housing$Avg.Listing.Price/Housing$Median.Listing.Price

barplot(Housing$Median.Listing.Price)

d <- density(ratio)

plot(d, main="Average Prices / Median Prices")

polygon(d, col="red", border="blue")

var0<-Housing$Median.Listing.Price

var1<-Housing$Avg.Listing.Price

date <- seq(as.Date("2012-05-01"), by="1 month", length.out=84) 

# Creating Charts

ggplot() + geom_line(aes(x=date,y=var0),color='red') +

  

  geom_line(aes(x=date,y=var1),color='blue') + 

  

  ylab('Housing Prices')+xlab('Date')+

  

  labs(title=" Median Listing Prices (in Red) and Average Listing Prices (in Blue)")

# Percent Chagnes

var2<-Housing$Median.Listing.Price.Y.Y

var3<-Housing$Avg.Listing.Price.Y.Y

date <- seq(as.Date("2012-05-01"), by="1 month", length.out=84) 

ggplot() + geom_line(aes(x=date,y=var2),color='red') +

  

  geom_line(aes(x=date,y=var3),color='blue') + 

  

  ylab('Housing Prices')+xlab('Date')+

  

  labs(title=" Median Listing Prices (in Red) and Average Listing Prices Y to Y (in Blue)")

barplot(Housing$Days.on.Market, main="Days on Market"

        ,

        names.arg = Housing$Month, cex.names = 0.3 )

barplot(Housing$Days.on.Market.Y.Y, main="Days on Market Y to Y"

        ,

        names.arg = Housing$Month, cex.names = 0.3 )

barplot(Housing$Total.Listing.Count.Y.Y, main="Total Listing Y to Y"

        ,

        names.arg = Housing$Month, cex.names = 0.5 )

barplot(Housing$Pending.Listing.Count.Y.Y, main="Pending Listing Y to Y"

        ,

        names.arg = Housing$Month, cex.names = 0.5 )

# Basic line plot with points

ggplot(data=Housing, aes(x=Housing$Month, y=ratio, group=1)) +

  geom_line()+

  geom_point()+

  labs(title=" Ratio ( Average Price / Median Price) ")

# Basic line plot with points

ggplot(data=Housing, aes(x=Housing$Month, y=Housing$Active.Listing.Count.Y.Y, group=1)) +

  geom_line(linetype="dashed")+

  geom_point()+

  labs(title=" Active Listing Count")

U.S. Employment analysis with R as of 10-2020

 

library(Quandl)

library(ggplot2)

library(tseries);library(timeseries);library(xts);library(forecast)

library (quantmod)

library(psych)

library(plotly) #install.package(plotly)

#Service-Providing Industries (SRVPRD)

#USGOOD -  All Employees: Goods-Producing Industries

#Private Service-Providing (CES0800000001)

#Mining and Logging: Oil and Gas Extraction (CES1021100001)

#Construction (USCONS)

#Manufacturing (MANEMP)

#Durable Goods (DMANEMP)

#Nondurable goods (NDMANEMP)

#Trade, Transportation and Utilities (USTPU)

#Wholesale Trade (USWTRADE)

#Transportation and Warehousing (CES4300000001)

#Retail Trade (USTRADE)

#Utilities (CES4422000001)

#Information Services (USINFO)

#Financial Activities (USFIRE)

#Professional and Business Services (USPBS)

#Education and Health Services (USEHS)

#Leisure and Hospitality (USLAH)

#Other Services (USSERV)

#Government (USGOVT)

getSymbols(c('PAYEMS','USGOOD','SRVPRD','CES0800000001','CES1021100001','USCONS','MANEMP',

             'DMANEMP','NDMANEMP','USTPU','USWTRADE','USTRADE','CES4300000001','CES4422000001',

            'USINFO','USFIRE','USPBS','USEHS','USLAH','USSERV','USGOVT'), from="1990-01-01",src='FRED')

EMP<-merge (PAYEMS,USGOOD,SRVPRD,CES0800000001,CES1021100001,USCONS,MANEMP,

            DMANEMP,NDMANEMP,USTPU,USWTRADE,USTRADE,CES4300000001,CES4422000001,

            USINFO,USFIRE,USPBS,USEHS,USLAH,USSERV,USGOVT)

names(EMP)<-c('PAYEMS','USGOOD','SRVPRD','CES0800000001','CES1021100001',

              'USCONS','MANEMP','DMANEMP','NDMANEMP','USTPU',

              'USWTRADE','USTRADE','CES4300000001','CES4422000001',

              'USINFO','USFIRE','USPBS','USEHS','USLAH',

              'USSERV','USGOVT')

# % in Total Nonfarm

PER_Good=USGOOD/PAYEMS*100

PER_Service=SRVPRD/PAYEMS*100

PER_CES0800000001=CES0800000001/PAYEMS*100

PER_CES1021100001=CES1021100001/PAYEMS*100

PER_USCONS=USCONS/PAYEMS*100

PER_MANEMP=MANEMP/PAYEMS*100

PER_DMANEMP=DMANEMP/MANEMP*100

PER_NDMANEMP=NDMANEMP/MANEMP*100

PER_USTPU=USTPU/PAYEMS*100

PER_USTRADE=USTRADE/PAYEMS*100

PER_USINFO=USINFO/PAYEMS*100

PER_USPBS=USPBS/PAYEMS*100

PER_USEHS=USEHS/PAYEMS*100

PER_USWTRADE=USWTRADE/PAYEMS*100

PER_USFIRE=USFIRE/PAYEMS*100

PER_USLAH=USLAH/PAYEMS*100

PER_USSERV=USSERV/PAYEMS*100

PER_USGOVT=USGOVT/PAYEMS*100

plot(PER_CES1021100001)

PER_USPBS

summary(PER_USCONS)

hist(PER_USCONS)

# Chart for Total Nonfarm

myColors <- c("red", "darkblue")

plot(x = EMP_PER, xlab = "Year", ylab = "% in Total Nonfarm",

     main = "% in Total Nonfarm Employment",col=myColors,   screens = 1)

legend(x = "bottom", legend = c('USGOOD','SRVPRD'),

       lty = 1, col=myColors)

plot(x = EMP_MAN, xlab = "Year", ylab = "% in Manufacturing",

     main = "% in Total Manufacturing Employment",col=myColors,   screens = 1)

legend(x = "bottom", legend = c('Durable','NonDurable'),

       lty = 1, col=myColors)

write.table(EMP, file='EMP.xls')

myColors <- c("red", "darkblue","brown","yellow","darkred","blue","pink","green","violet","black")

plot(x = last(EMP, "30 years"), xlab = "Year", ylab = "Index",

     main = "CPI", col=myColors,  screens = 1)

legend(x = "topleft", legend = c('PAYEMS','USGOOD','SRVPRD','CES0800000001','CES1021100001',

                                 'USCONS','MANEMP','DMANEMP','NDMANEMP','USTPU',

                                 'USWTRADE','USTRADE','CES4300000001','CES4422000001',

                                 'USINFO','USFIRE','USPBS','USEHS','USLAH',

                                 'USSERV','USGOVT'),

       lty = 1, col=myColors)

Diff_EMP <- (EMP/lag(EMP)-1)  

Diff_EMP[1,] <- 0

Diff_EMP12<-diff(EMP,lag =12)

write.table(Diff_EMP, file='Diff_EMP.xls')

tail(Diff_EMP12)

# Retail Trade

par(mfrow=c(3,1))

plot(USTRADE, main="Retail Trade", col="black")

barplot(Diff_EMP12$USTRADE, main="Changes from previous year ", col="red")

barplot(annualReturn(USTRADE), main=" Annual Changes ", col="blue")

# Financial Activities

par(mfrow=c(3,1))

plot(USFIRE, main="Financial Activities", col="black")

barplot(Diff_EMP12$USFIRE, main="Changes from previous year ", col="red")

barplot(annualReturn(USFIRE), main=" Annual Changes ", col="blue")

# Professional and Business Services

par(mfrow=c(3,1))

plot(USPBS, main="Professional and Business Services", col="black")

barplot(Diff_EMP12$USPBS, main="Changes from previous year ", col="red")

barplot(annualReturn(USPBS), main=" Annual Changes ", col="blue")

# Education and Health Services

par(mfrow=c(3,1))

plot(USEHS, main="Education and Health Services", col="black")

barplot(Diff_EMP12$USEHS, main="Changes from previous year ", col="red")

barplot(annualReturn(USEHS), main=" Annual Changes ", col="blue")

# Leisure and Hospitality

par(mfrow=c(3,1))

plot(USLAH, main="Leisure and Hospitality", col="black")

barplot(Diff_EMP12$USLAH, main="Changes from previous year ", col="red")

barplot(annualReturn(USLAH), main=" Annual Changes ", col="blue")

# Other Services

par(mfrow=c(3,1))

plot(USSERV, main="Other Services", col="black")

barplot(Diff_EMP12$USSERV, main="Changes from previous year ", col="red")

barplot(annualReturn(USSERV), main=" Annual Changes ", col="blue")

# US Government

par(mfrow=c(3,1))

plot(USGOVT, main="Government", col="black")

barplot(Diff_EMP12$USGOVT, main="Changes from previous year ", col="red")

barplot(annualReturn(USGOVT), main=" Annual Changes ", col="blue")

# Wholesale Trade

par(mfrow=c(3,1))

plot(USWTRADE, main="Wholesale Trade", col="black")

barplot(Diff_EMP12$USWTRADE, main="Changes from previous year ", col="red")

barplot(annualReturn(USWTRADE), main=" Annual Changes ", col="blue")

# Mining and Logging: Oil and Gas Extraction

par(mfrow=c(3,1))

plot(CES1021100001, main="Mining and Logging: Oil and Gas Extraction", col="black")

barplot(Diff_EMP12$CES1021100001, main="Changes from previous year ", col="red")

barplot(annualReturn(CES1021100001), main=" Annual Changes ", col="blue")

summary(Diff_EMP$PAYEMS)

hist(Diff_EMP$PAYEMS)

plot(Diff_EMP$PAYEMS)

tail(Diff_EMP)

Diff_EMP12<-(EMP/lag(EMP,k=12)-1)*100

  

write.table(Diff_EMP12, file='Diff_EMP12.xls')

  

plot(Diff_EMP12[,2])

summary(Diff_EMP12)

Diff_12=window(Diff_EMP12,start=as.Date("2001-01-01"), end=as.Date("2020-12-31"))

cor.distance <- cor(Diff_12)

corrplot::corrplot(cor.distance)

cor.distance

plot(Diff_12)

Diff_12

write.table(Diff_12, file='Diff_12.xls')