library(readr)
library(dplyr)
library(knitr)
library(kableExtra)
library(ggplot2)
VoterData<-read_csv("/Users/juliushunte/Desktop/fall courses 2018/applied prog research/VOTER_Survey_July17_Release1-csv.csv")
urbanreligon <-VoterData%>%
 mutate(Demographics = ifelse(urbancity_baseline==1,"City",
                        ifelse(urbancity_baseline==2,"Suburb",
                        ifelse(urbancity_baseline==3,"Town",
                        ifelse(urbancity_baseline==4,"Rural Area",
                        ifelse(urbancity_baseline==5,"Other",NA))))),
        ft_muslims = ifelse(ft_muslim_2017==997,NA,ft_muslim_2017),
        ImmiMakeDiff = ifelse(immi_makedifficult_baseline==1,"Much easier",
                        ifelse(immi_makedifficult_baseline==2,"Slightly easier",
                        ifelse(immi_makedifficult_baseline==3,"No change",
                        ifelse(immi_makedifficult_baseline==4,"Slightly harder",
                        ifelse(immi_makedifficult_baseline==5,"Much harder",
                        ifelse(immi_makedifficult_baseline==8,"Not Sure",NA)))))))%>%
 select(Demographics,ft_muslims,ImmiMakeDiff)
gridExtra::grid.arrange(
  urbanreligon%>%
      filter(Demographics=="City")%>%
      ggplot()+
      geom_histogram(aes(ft_muslims),fill="blue")+
      geom_vline(aes(xintercept=mean(urbanreligon$ft_muslims,na.rm=TRUE)))+
      ggtitle("City' Feelings towards Muslims"),
  urbanreligon%>%
      filter(Demographics=="Rural Area")%>%
      ggplot()+
      geom_histogram(aes(ft_muslims),fill="red")+
      geom_vline(aes(xintercept=mean(urbanreligon$ft_muslims,na.rm=TRUE)))+
      ggtitle("Rural Area' Feelings towards Muslims"),
  nrow=1)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 921 rows containing non-finite values (stat_bin).
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Warning: Removed 627 rows containing non-finite values (stat_bin).

urbanreligon%>%
  group_by(Demographics,ImmiMakeDiff)%>%
  summarise(n=n())%>% #n() means "number of observations"
  kable()%>%
  kable_styling(latex_options = c("striped", "scale_down"), font_size = 9)
Demographics ImmiMakeDiff n
City Much easier 249
City Much harder 454
City No change 510
City Not Sure 182
City Slightly easier 439
City Slightly harder 411
City NA 14
Other Much easier 3
Other Much harder 9
Other No change 15
Other Not Sure 2
Other Slightly easier 11
Other Slightly harder 7
Other NA 4
Rural Area Much easier 102
Rural Area Much harder 442
Rural Area No change 366
Rural Area Not Sure 79
Rural Area Slightly easier 217
Rural Area Slightly harder 273
Rural Area NA 4
Suburb Much easier 257
Suburb Much harder 669
Suburb No change 736
Suburb Not Sure 203
Suburb Slightly easier 558
Suburb Slightly harder 557
Suburb NA 22
Town Much easier 105
Town Much harder 272
Town No change 276
Town Not Sure 82
Town Slightly easier 200
Town Slightly harder 200
Town NA 6
NA Much easier 4
NA Much harder 20
NA No change 15
NA Not Sure 6
NA Slightly easier 8
NA Slightly harder 8
NA NA 3 
urbanreligon%>%
      group_by(Demographics,ImmiMakeDiff)%>%
      summarize(n=n())%>%
      mutate(percent = n/sum(n))%>% # # of obs in category divided by total # of obs
      kable()%>%
      kable_styling(latex_options = c("striped", "scale_down"), font_size = 9)
Demographics ImmiMakeDiff n percent
City Much easier 249 0.1102258
City Much harder 454 0.2009739
City No change 510 0.2257636
City Not Sure 182 0.0805666
City Slightly easier 439 0.1943338
City Slightly harder 411 0.1819389
City NA 14 0.0061974
Other Much easier 3 0.0588235
Other Much harder 9 0.1764706
Other No change 15 0.2941176
Other Not Sure 2 0.0392157
Other Slightly easier 11 0.2156863
Other Slightly harder 7 0.1372549
Other NA 4 0.0784314
Rural Area Much easier 102 0.0687795
Rural Area Much harder 442 0.2980445
Rural Area No change 366 0.2467970
Rural Area Not Sure 79 0.0532704
Rural Area Slightly easier 217 0.1463250
Rural Area Slightly harder 273 0.1840863
Rural Area NA 4 0.0026972
Suburb Much easier 257 0.0856096
Suburb Much harder 669 0.2228514
Suburb No change 736 0.2451699
Suburb Not Sure 203 0.0676216
Suburb Slightly easier 558 0.1858761
Suburb Slightly harder 557 0.1855430
Suburb NA 22 0.0073284
Town Much easier 105 0.0920245
Town Much harder 272 0.2383874
Town No change 276 0.2418931
Town Not Sure 82 0.0718668
Town Slightly easier 200 0.1752848
Town Slightly harder 200 0.1752848
Town NA 6 0.0052585
NA Much easier 4 0.0625000
NA Much harder 20 0.3125000
NA No change 15 0.2343750
NA Not Sure 6 0.0937500
NA Slightly easier 8 0.1250000
NA Slightly harder 8 0.1250000
NA NA 3 0.0468750 
urbanreligon%>%
      group_by(Demographics,ImmiMakeDiff)%>%
      summarize(n=n())%>%
      mutate(percent = n/sum(n))%>%
      filter(ImmiMakeDiff=="Much harder")%>%
      kable()%>%
      kable_styling(latex_options = c("striped", "scale_down"), font_size = 9)
Demographics ImmiMakeDiff n percent
City Much harder 454 0.2009739
Other Much harder 9 0.1764706
Rural Area Much harder 442 0.2980445
Suburb Much harder 669 0.2228514
Town Much harder 272 0.2383874
NA Much harder 20 0.3125000 
urbanreligon%>%
      group_by(Demographics,ImmiMakeDiff)%>%
      summarize(n=n())%>%
      mutate(percent = n/sum(n))%>%
      filter(ImmiMakeDiff=="Much harder")%>%
  ggplot()+
  geom_col(aes(x=Demographics, y=percent), fill="darkred")

30% of people in Rural Areas believe that immigration should be harder as opposed to 20% of people in the city.

chartdata<-urbanreligon%>%
  group_by(Demographics)%>%
  summarize(ft_muslims = mean(ft_muslims, na.rm=TRUE))

ggplot(data = chartdata)+
  geom_col(aes(x=Demographics, y=ft_muslims), fill="yellow")