History 90.01 Final Project

#FIGURE 1
#running packages
library(dplyr)
library(readr)
library(ggplot2)
library(RColorBrewer)

printplot <- function(plot) {
  png('Figure1.png',height=500,width=1000)
  print(plot)
  dev.off()
}

#reading data downloaded from IPUMS
data1 <- read_csv('Data.csv')

#filtering Alaska and Hawaii
FirstGenData <- data1 %>% filter(YEAR>=1960 | !(STATEFIP %in% c(2,15)))

#filtering out year = 1870
FirstGenData <- FirstGenData %>% filter(YEAR!=1870)

#filtering out children
FirstGenData <- FirstGenData %>% filter(AGE>18)

#Creating Data Frame of First Generation
FirstGenData1 <- FirstGenData %>% mutate(Gen1=ifelse(420<BPL & BPL<429,'First Generation, Northern & Western European',
                                                     ifelse(430<BPL & BPL<499,'First Generation, Southern & Eastern European',
                                                            ifelse(500<BPL & BPL<524,'First Generation, Asian',
                                                                   'Neither'))))

rename(Gen1='First Generation Immigrants')

#filtering out immigrants who are "Neither"
FirstGenData2 <- FirstGenData1 %>% filter(Gen1 != 'Neither')

#Accounting for Sample Line Weight in 1940
FirstGenData3 <- FirstGenData2 %>% mutate(Weight=ifelse(YEAR==1940,SLWT,PERWT))

#Group by Year, Gen1, and Literacy. Summarise by Weight.
FirstGenData4 <- FirstGenData3 %>% group_by(Gen1,YEAR) %>% summarise(Total=sum(Weight))

#Creating Data Frame For Literate
FirstGenDataLit <- FirstGenData3 %>% mutate(LIT=ifelse(LIT==4,'Literate','Illiterate'))

FirstGenDataLit <- FirstGenDataLit %>% mutate(Weight=ifelse(YEAR==1940,SLWT,PERWT))

FirstGenDataLit2 <- FirstGenDataLit%>% group_by (Gen1,YEAR,LIT) %>% summarise(NumberLiterate=sum(Weight))

#filtering out immigrants who are illiterate
FirstGenDataLit3 <- FirstGenDataLit2 %>% filter(LIT != 'Illiterate')

#Joining Data Frames
FirstGenDataFinal <- left_join(FirstGenData4,FirstGenDataLit3,by=c('YEAR','Gen1')) 

#Selecting variables
FirstGenDataFinal2 <- FirstGenDataFinal %>% 
  select(YEAR,Gen1,NumberLiterate,Total)

#determining percent literate
datapercent <- FirstGenDataFinal2 %>% mutate(percent=NumberLiterate/Total*100) %>% 
  select(YEAR,Gen1,percent) %>% 
  rename(Group=Gen1)

#graphing
png('Figure1.3.png',height=1000,width=2000)
graph1 <- ggplot(data=datapercent, aes(x=YEAR, y=percent, group=Group,colour=Group)) +
  geom_line()+
  geom_point()+
  expand_limits(y=0)+
  theme_set(theme_gray(base_size = 30))+
  labs(title='Literacy of First Generation Immigrants, 1880-1930',x='Year',y='Percent Literate') +
  theme_classic()
printplot(graph1)

#FIGURE 2

#running packages
library(dplyr)
library(readr)
library(ggplot2)
library(RColorBrewer)

#reading data downloaded from IPUMS
data1 <- read_csv('Data.csv')

printplot <- function(plot) {
  png('Figure2.png',height=500,width=1000)
  print(plot)
  dev.off()
}

#filtering Alaska and Hawaii
SecondGenData <- data1 %>% filter(YEAR>=1960 | !(STATEFIP %in% c(2,15)))

#filtering out year = 1870
SecondGenData <- SecondGenData %>% filter(YEAR!=1870)

#filtering out children
SecondGenData <- SecondGenData %>% filter(AGE>18)

#Creating Data Frame of Second Generation 
SecondGenData2 <- SecondGenData %>% mutate(Gen2=ifelse((420<MBPL & MBPL<429 | 420<FBPL & FBPL<429) & (001<BPL & BPL<099), 'Second Generation Northern & Western European',
                                                       ifelse((430<MBPL & MBPL<499 | 430<FBPL & FBPL<499) & (001<BPL & BPL<099), 'Second Generation Southern & Eastern European',              
                                                              ifelse((500<MBPL & MBPL<524 | 500<FBPL & FBPL<524) & (001<BPL & BPL<099), 'Second Generation Asian','Neither'))))                 

#filtering out immigrants who are "Neither"
SecondGenData3 <- SecondGenData2 %>% filter(Gen2 != 'Neither')

#Accounting for Sample Line Weight in 1940
SecondGenData4 <- SecondGenData3 %>% mutate(Weight=ifelse(YEAR==1940,SLWT,PERWT))

#Group by Year and Gen2. Summarise by Weight.
SecondGenData5 <- SecondGenData4 %>% group_by(Gen2,YEAR) %>% summarise(Total=sum(Weight))

#Creating Data Frame For Literate
SecondGenDataLit <- SecondGenData3 %>% mutate(LIT=ifelse(LIT==4,'Literate','Illiterate'))

SecondGenDataLit2 <- SecondGenDataLit %>% mutate(Weight=ifelse(YEAR==1940,SLWT,PERWT))

SecondGenDataLit3 <- SecondGenDataLit2 %>% group_by (Gen2,YEAR,LIT) %>% summarise(NumberLiterate=sum(Weight))

#filtering out immigrants who are illiterate
SecondGenDataLit4 <- SecondGenDataLit3 %>% filter(LIT != 'Illiterate')

#Joining Data Frames
SecondGenDataLitFinal <- left_join(SecondGenData5,SecondGenDataLit4,by=c('YEAR','Gen2')) 

#Selecting variables
SecondGenFinal2 <- SecondGenDataLitFinal %>% 
  select(YEAR,Gen2,NumberLiterate,Total)

#determining percent literate
datapercent2 <- SecondGenFinal2 %>% mutate(percent=NumberLiterate/Total*100) %>% 
  select(YEAR,Gen2,percent)%>% 
  rename(Group=Gen2)

#graphing
png('Figure1.4.png',height=1000,width=2000)
graph1 <- ggplot(data=datapercent2, aes(x=YEAR, y=percent, group=Group,colour=Group)) +
  geom_line()+
  geom_point()+
  expand_limits(y=0)+
  theme_set(theme_gray(base_size = 30))+
  labs(title='Literacy of Second Generation Immigrants, 1880-1930',x='Year',y='Percent Literate') +
  theme_classic()
printplot(graph1)

#FIGURE 3

#running packages
library(dplyr)
library(readr)
library(ggplot2)
library(RColorBrewer)

printplot <- function(plot) {
  png('Figure3.2.png',height=500,width=1000)
  print(plot)
  dev.off()
}

#reading data downloaded from IPUMS
data2 <- read_csv(Data.csv)

#filtering Alaska and Hawaii
data2 <- data2 %>% filter(YEAR>=1960 | !(STATEFIP %in% c(2,15)))

#filtering out children
data2.1<-data2 %>% filter(AGE>18)

#filtering out year = 1870
data2.2 <- data2.1 %>% filter(YEAR!=1870)

#Creating Data Frame of First Generation
data3 <- data2.2 %>% mutate(ImStatRace=factor(ifelse((420<BPL & BPL<429) | (430<BPL & BPL<499) | (500<BPL & BPL<524),1,
                                                   ifelse(RACE==1 & BPL<120,2,
                                                   ifelse(RACE==2 & BPL<120,3,
                                                   ifelse(RACE==3 & BPL<120,4,5)))),
                                            labels=c('Immigrant','Native-Born White','Native-Born Black','Native American','Neither')))   
#BPL %in% 421:428 | BPL %in% 431:498

#filtering out people who are "Neither"
data4 <- data3 %>% filter(ImStatRace != 'Neither')

#Accounting for Sample Line Weight in 1940
data5 <- data4 %>% mutate(Weight=ifelse(YEAR==1940,SLWT,PERWT))

#group by ImStatRace and Year.
data6 <- data5 %>% group_by(ImStatRace,YEAR) %>% summarise(Total=sum(Weight))

#creating data frame for literacy
datalit <- data5 %>% mutate(LIT=ifelse(LIT==4,'Literate','Illiterate'))

datalit <- datalit %>% filter(LIT=='Literate')

datalit2 <- datalit %>% mutate(Weight=ifelse(YEAR==1940,SLWT,PERWT))

datalit3 <- datalit2 %>% group_by (YEAR,ImStatRace,LIT) %>% summarise(NumberLiterate=sum(Weight))

#Joining Data Frames
DataFinal <- left_join(data6,datalit3,by=c('YEAR','ImStatRace')) 

#Selecting variables
DataFinal2 <- DataFinal %>% 
  select(YEAR,ImStatRace,NumberLiterate,Total)

#determining percent literate
datapercent3 <- DataFinal2 %>% mutate(percent=NumberLiterate/Total*100) %>% 
  select(YEAR,ImStatRace,percent)%>% 
  rename(Group=ImStatRace) 

#graphing
png('Figure3.png',height=1000,width=2000)
graph3 <-ggplot(data=datapercent3, aes(x=YEAR, y=percent, group=Group, colour=Group)) +
  geom_line()+
  geom_point()+
  expand_limits(y=0)+
  theme_set(theme_gray(base_size = 30))+
  labs(title='Literacy of Immigrants versus Native-Born Americans, 1880-1930',x='Year',y='Percent Literate', colour= 'Immigrant Group') +
  theme_classic()
  printplot(graph3)

#FIGURE 4
#running packages
library(dplyr)
library(readr)
library(ggplot2)
library(RColorBrewer)

#reading data downloaded from IPUMS
a <- read_csv('Figures462.csv')

#Create vector of age category labels
agecats <- '0-9'
for (i in 1:7) {
  agecats <- c(agecats,paste(i,'0-',i,9,sep=''))
}
agecats <- c(agecats,'80+')

#assigning variables to sex
b <- a %>% mutate(Sex=factor(SEX,labels=c('Male','Female')))

#separate ages by 0-9, 10-19, etc.
c <- b %>% mutate(Age=ifelse(AGE>=80,8,floor(AGE/10)))

#label with agecats labels to age
d <- c %>% mutate(Age=factor(Age,labels=agecats))

#separating out first and second generation immigrants (need to look at code book to determine)
e <- d %>% mutate(Gen=ifelse((420<BPL & BPL<429),'First Generation',
                             ifelse((420<MBPL & MBPL<429) | (420<FBPL & FBPL<429) & (001<BPL & BPL<099), 'Second Generation',
                                    'Neither')))

#exclude data from Hawaii and Alaska
f <- e %>% filter(YEAR>=1960 | !(STATEFIP %in% c(2,15)))

f <- f %>% filter(YEAR!=1980)

f <- f %>% filter(Gen != 'Neither')

f1 <- f %>% mutate(Weight=ifelse((YEAR==1940 | YEAR ==1950)&Gen=='Second Generation',SLWT,PERWT))

#Group by Age, Sex, Generation, and Year
g <- f1 %>% group_by(Gen,YEAR,Age,Sex) %>% summarise(Number=sum(Weight))

#flip male to other side of the graph
h <- g %>% mutate(Number=ifelse(Sex=='Male',-1 *Number,Number))

#make population period graph. 
#set correct number of pixels
png('population_pyramid_4.png',height=500,width=2000)
#set x and y axis
ggplot(data=h,aes(x=Age,y=Number,fill=Sex)) +
  #setting the values of the bar in the graph
  geom_bar(data=h[h$Sex=='Male',], stat='identity') +
  geom_bar(data=h[h$Sex=='Female',],stat='identity') +
  #flipping the graph around so the y axis is horizontal
  coord_flip() +
  #separating out/faceting the graphs by generation and year
  facet_grid(Gen~.~YEAR) +
  #View h to determine range, set range based on number of immigrants per year
  scale_y_continuous(breaks=c(-100000,-50000,0,50000,100000),
                     labels=c('100','50','0','50','100')) +
  #labeling the graph
  labs(y='Population in Thousands',title='Population Pyramids for Northern and Western European Immigrants and their Children') +
  labs()
  #setting the color palette of the graph
  scale_fill_brewer(palette='Set1',guide=guide_legend(reverse=TRUE))+
  #setting "Sex" label above the legend
  guides(fill=guide_legend(title='Sex',title.position='top')) +
  #setting background colors to black and white
  theme_bw() + theme(legend.position='bottom') 
dev.off()

#FIGURE 5
#running packages
library(dplyr)
library(readr)
library(ggplot2)
library(RColorBrewer)

#reading data downloaded from IPUMS
a2 <- read_csv('Figures462.csv')

#Create vector of age category labels
agecats <- '0-9'
for (i in 1:7) {
  agecats <- c(agecats,paste(i,'0-',i,9,sep=''))
}
agecats <- c(agecats,'80+')

#assigning variables to sex
b2 <- a2 %>% mutate(Sex=factor(SEX,labels=c('Male','Female')))

#separate ages by 0-9, 10-19, etc.
c2 <- b2 %>% mutate(Age=ifelse(AGE>=80,8,floor(AGE/10)))

#label with agecats labels to age
d2 <- c2 %>% mutate(Age=factor(Age,labels=agecats))

#separating out first and second generation immigrants (need to look at code book to determine)
e2 <- d2 %>% mutate(Gen=ifelse((430<BPL & BPL<499),'First Generation',
                       ifelse((430<MBPL & MBPL<499) | (430<FBPL & FBPL<499) & (001<BPL & BPL<099), 'Second Generation',
                       'Neither')))

#exclude data from Hawaii and Alaska
f2 <- e2 %>% filter(YEAR>=1960 | !(STATEFIP %in% c(2,15)))


f2 <- f2 %>% filter(YEAR!=1980)

#filter out 'neither'
f2 <- f2 %>% filter(Gen != 'Neither')

f2 <- f2 %>% mutate(Weight=ifelse(YEAR==1940 | YEAR==1950 & Gen=='Second Generation',
                                 SLWT,PERWT))

#Group by Age, Sex, Generation, and Year
g2 <- f2 %>% group_by(Gen,YEAR,Age,Sex) %>% summarise(Number=sum(Weight))

#flip male to other side of the graph
h2 <- g2 %>% mutate(Number=ifelse(Sex=='Male',-1 *Number,Number))

#make population period graph. 
#set correct number of pixels
png('population_pyramid_final2.png',height=500,width=2000)
#set x and y axis
ggplot(data=h2,aes(x=Age,y=Number,fill=Sex)) +
  #setting the values of the bar in the graph
  geom_bar(data=h2[h2$Sex=='Male',], stat='identity') +
  geom_bar(data=h2[h2$Sex=='Female',],stat='identity') +
  #flipping the graph around so the y axis is horizontal
  coord_flip() +
  #separating out/faceting the graphs by generation and year
  facet_grid(Gen~.~YEAR) +
  #View h to determine range, set range based on number of immigrants per year
  scale_y_continuous(breaks=c(-2000000,-1000000,0,1000000,2000000),
                     labels=c('2','1','0','1','2')) +
  #labeling the graph
  labs(y='Population in Millions',title='Population Pyramids for Southern and Eastern European Immigrants and their Children') +
  #setting the color palette of the graph
  scale_fill_brewer(palette='Set1',guide=guide_legend(reverse=TRUE))+
  #setting "Sex" label above the legend
  guides(fill=guide_legend(title='Sex',title.position='top')) +
  #setting background colors to black and white
  theme_bw() + theme(legend.position='bottom') 
dev.off()

#FIGURE 6
#running packages
library(dplyr)
library(readr)
library(ggplot2)
library(RColorBrewer)

#reading data downloaded from IPUMS
a3 <- read_csv('Figures462.csv')

#Create vector of age category labels
agecats <- '0-9'
for (i in 1:7) {
  agecats <- c(agecats,paste(i,'0-',i,9,sep=''))
}
agecats <- c(agecats,'80+')

#assigning variables to sex
b3 <- a3 %>% mutate(Sex=factor(SEX,labels=c('Male','Female')))

#separate ages by 0-9, 10-19, etc.
c3 <- b3 %>% mutate(Age=ifelse(AGE>=80,8,floor(AGE/10)))

#label with agecats labels to age
d3 <- c3 %>% mutate(Age=factor(Age,labels=agecats))

#separating out first and second generation immigrants (need to look at code book to determine)
e3 <- d3 %>% mutate(Gen=(ifelse((500<BPL & BPL<524),'First Generation Asian',
                         ifelse((500<MBPL & MBPL<524) | (500<FBPL & FBPL<524) & (001<BPL & BPL<099), 'Second Generation Asian',                 
                                        'Neither'))))

#exclude data from Hawaii and Alaska
f3 <- e3 %>% filter(YEAR>=1960 | !(STATEFIP %in% c(2,15)))

f3 <- f3 %>% filter(YEAR!=1980)

g3 <- f3 %>% filter(Gen!= 'Neither')

f4 <- g3 %>% mutate(Weight=ifelse((YEAR==1940 | YEAR ==1950)&Gen=='Second Generation Asian',SLWT,PERWT))

#Group by Age, Sex, Generation, and Year
h3 <- f4 %>% group_by(Gen,YEAR,Age,Sex) %>% summarise(Number=sum(Weight))


#flip male to other side of the graph
h5 <- h3 %>% mutate(Number=ifelse(Sex=='Male',-1 *Number,Number))

#make population period graph. 
#set correct number of pixels
png('population_pyramid_final4.png',height=500,width=2000)
#set x and y axis
ggplot(data=h5,aes(x=Age,y=Number,fill=Sex)) +
  #setting the values of the bar in the graph
  geom_bar(data=h5[h5$Sex=='Male',], stat='identity') +
  geom_bar(data=h5[h5$Sex=='Female',],stat='identity') +
  #flipping the graph around so the y axis is horizontal
  coord_flip() +
  #separating out/faceting the graphs by generation and year
  facet_grid(Gen~.~YEAR) +
  #View h5 to determine range, set range based on number of immigrants per year
  scale_y_continuous(breaks=c(-30000,-20000,-10000,0,10000,20000,30000),
                     labels=c('30','20','10','0','10','20','30')) +
  #labeling the graph
  labs(y='Population in Thousands',title='Population Pyramids for Asian Immigrants and their Children') +
  #setting the color palette of the graph
  scale_fill_brewer(palette='Set1',guide=guide_legend(reverse=TRUE))+
  #setting "Sex" label above the legend
  guides(fill=guide_legend(title='Sex',title.position='top')) +
  #setting background colors to black and white
  theme_bw() + theme(legend.position='bottom') 
dev.off()