Class 10/30/19

#install.packages("dplyr")
#install.packages("ggplot2")
#install.packages("knitr")
#install.packages("tidyr")
#install.packages("readr")

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, union

library(ggplot2)
library(knitr)
library(tidyr)
library(readr)

voterdata <- read_csv("C:/Users/PLESLIE100/Desktop/R Studio Class Work/Abbreviated Dataset Labeled(October Only)V2(1).csv")

## Parsed with column specification:
## cols(
##   .default = col_character(),
##   NumChildren = col_double(),
##   ft_fem_2017 = col_double(),
##   ft_immig_2017 = col_double(),
##   ft_police_2017 = col_double(),
##   ft_dem_2017 = col_double(),
##   ft_rep_2017 = col_double(),
##   ft_evang_2017 = col_double(),
##   ft_muslim_2017 = col_double(),
##   ft_jew_2017 = col_double(),
##   ft_christ_2017 = col_double(),
##   ft_gays_2017 = col_double(),
##   ft_unions_2017 = col_double(),
##   ft_altright_2017 = col_double(),
##   ft_black_2017 = col_double(),
##   ft_white_2017 = col_double(),
##   ft_hisp_2017 = col_double()
## )

## See spec(...) for full column specifications.

names(voterdata)

##  [1] "gender"                  "race"                   
##  [3] "education"               "familyincome"           
##  [5] "children"                "region"                 
##  [7] "urbancity"               "Vote2012"               
##  [9] "Vote2016"                "TrumpSanders"           
## [11] "PartyRegistration"       "PartyIdentification"    
## [13] "PartyIdentification2"    "PartyIdentification3"   
## [15] "NewsPublicAffairs"       "DemPrimary"             
## [17] "RepPrimary"              "ImmigrantContributions" 
## [19] "ImmigrantNaturalization" "ImmigrationShouldBe"    
## [21] "Abortion"                "GayMarriage"            
## [23] "DeathPenalty"            "DeathPenaltyFreq"       
## [25] "TaxWealthy"              "Healthcare"             
## [27] "GlobWarmExist"           "GlobWarmingSerious"     
## [29] "AffirmativeAction"       "Religion"               
## [31] "ReligiousImportance"     "ChurchAttendance"       
## [33] "PrayerFrequency"         "NumChildren"            
## [35] "areatype"                "GunOwnership"           
## [37] "ft_fem_2017"             "ft_immig_2017"          
## [39] "ft_police_2017"          "ft_dem_2017"            
## [41] "ft_rep_2017"             "ft_evang_2017"          
## [43] "ft_muslim_2017"          "ft_jew_2017"            
## [45] "ft_christ_2017"          "ft_gays_2017"           
## [47] "ft_unions_2017"          "ft_altright_2017"       
## [49] "ft_black_2017"           "ft_white_2017"          
## [51] "ft_hisp_2017"

“ft_rep_2017”, “ft_black_2017”, “race”, “PartyRegistration”,“PartyIdentification”, “ft_white_2017”, “ft_dem_2017”, “ft_hisp_2017”

Topic 2: Party & Race

How do the democrat & republican parties differ in the racial/ethnic composition of their members?

How do they differ in their attitudes towards various ethnic groups?

Therefore we need need to examine the following variables “PartyIdentification” and “Race” to answer part one of the question that will be a cross tabulation. To determine how the republicans and democrats differ in their attitudes between the races we must run averages using the following variables for part two of the question “PartyIdentification”, “ft_black_2017”, “ft_white_2017”, “ft_hisp_2017”

voterdata%>%
filter(!is.na(PartyIdentification))%>%
  filter(!is.na(race))%>%
  group_by(PartyIdentification, race)%>%
  summarise(n=n())%>%
 mutate(percent=n/sum(n))%>%
  ggplot()+
  geom_col(aes(PartyIdentification, y=percent, fill=race))+
  coord_flip()

voterdata%>%
 filter(!is.na(PartyIdentification))%>%
  filter(PartyIdentification %in% c("Democrat", "Republican"))%>%
  group_by(PartyIdentification)%>%
summarise(avg_ft_blacks = mean(ft_black_2017, na.rm = TRUE), avg_ft_whites =mean(ft_white_2017, na.rm = TRUE), avg_ft_hispanics =  mean(ft_hisp_2017, na.rm = TRUE))%>%
  gather(group, rating, -PartyIdentification)

## # A tibble: 6 x 3
##   PartyIdentification group            rating
##   <chr>               <chr>             <dbl>
## 1 Democrat            avg_ft_blacks      77.9
## 2 Republican          avg_ft_blacks      65.7
## 3 Democrat            avg_ft_whites      74.3
## 4 Republican          avg_ft_whites      80.9
## 5 Democrat            avg_ft_hispanics   74.5
## 6 Republican          avg_ft_hispanics   66.2

voterdata%>%
  filter(!is.na(PartyIdentification))%>%
  filter(PartyIdentification %in% c("Democrat", "Republican"))%>%

  ggplot()+
  geom_histogram(aes(x=ft_black_2017, fill=PartyIdentification))+
  facet_wrap(~PartyIdentification)

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Warning: Removed 2121 rows containing non-finite values (stat_bin).

voterdata%>%
  filter(!is.na(PartyIdentification))%>%
  filter(PartyIdentification %in% c("Democrat", "Republican"))%>%

  ggplot()+
  geom_histogram(aes(x=ft_white_2017, fill=PartyIdentification))+
  facet_wrap(~PartyIdentification)

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Warning: Removed 2104 rows containing non-finite values (stat_bin).

voterdata%>%
  filter(!is.na(PartyIdentification))%>%
  filter(PartyIdentification %in% c("Democrat", "Republican"))%>%

  ggplot()+
  geom_histogram(aes(x=ft_hisp_2017, fill=PartyIdentification))+
  facet_wrap(~PartyIdentification)

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Warning: Removed 2129 rows containing non-finite values (stat_bin).