#install.packages("readr")
library(readr)
library(knitr)
voterdata<-read_csv("/Users/meiminshan/Desktop/Abbreviated Dataset Labeled(October Only)V2.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.
head(voterdata)
## # A tibble: 6 x 51
## gender race education familyincome children region urbancity Vote2012
## <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 Female White 4-year Prefer not … No West Suburb Barack …
## 2 Female White Some Col… $60K-$69,999 No West Rural Ar… Mitt Ro…
## 3 Male White High Sch… $50K-$59,999 No Midwe… City Mitt Ro…
## 4 Male White Some Col… $70K-$79,999 No South City Barack …
## 5 Male White 4-year $40K-$49,999 No South Suburb Mitt Ro…
## 6 Female White 2-year $30K-$39,999 No West Suburb Barack …
## # … with 43 more variables: Vote2016 <chr>, TrumpSanders <chr>,
## # PartyRegistration <chr>, PartyIdentification <chr>,
## # PartyIdentification2 <chr>, PartyIdentification3 <chr>,
## # NewsPublicAffairs <chr>, DemPrimary <chr>, RepPrimary <chr>,
## # ImmigrantContributions <chr>, ImmigrantNaturalization <chr>,
## # ImmigrationShouldBe <chr>, Abortion <chr>, GayMarriage <chr>,
## # DeathPenalty <chr>, DeathPenaltyFreq <chr>, TaxWealthy <chr>,
## # Healthcare <chr>, GlobWarmExist <chr>, GlobWarmingSerious <chr>,
## # AffirmativeAction <chr>, Religion <chr>, ReligiousImportance <chr>,
## # ChurchAttendance <chr>, PrayerFrequency <chr>, NumChildren <dbl>,
## # areatype <chr>, GunOwnership <chr>, ft_fem_2017 <dbl>,
## # ft_immig_2017 <dbl>, ft_police_2017 <dbl>, ft_dem_2017 <dbl>,
## # ft_rep_2017 <dbl>, ft_evang_2017 <dbl>, ft_muslim_2017 <dbl>,
## # ft_jew_2017 <dbl>, ft_christ_2017 <dbl>, ft_gays_2017 <dbl>,
## # ft_unions_2017 <dbl>, ft_altright_2017 <dbl>, ft_black_2017 <dbl>,
## # ft_white_2017 <dbl>, ft_hisp_2017 <dbl>
str(voterdata)
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 8000 obs. of 51 variables:
## $ gender : chr "Female" "Female" "Male" "Male" ...
## $ race : chr "White" "White" "White" "White" ...
## $ education : chr "4-year" "Some College" "High School Graduate" "Some College" ...
## $ familyincome : chr "Prefer not to say" "$60K-$69,999" "$50K-$59,999" "$70K-$79,999" ...
## $ children : chr "No" "No" "No" "No" ...
## $ region : chr "West" "West" "Midwest" "South" ...
## $ urbancity : chr "Suburb" "Rural Area" "City" "City" ...
## $ Vote2012 : chr "Barack Obama" "Mitt Romney" "Mitt Romney" "Barack Obama" ...
## $ Vote2016 : chr "Hillary Cinton" "Donald Trump" "Hillary Cinton" "Gary Johnson" ...
## $ TrumpSanders : chr "Bernie Sanders" "Donald Trump" "Bernie Sanders" "Bernie Sanders" ...
## $ PartyRegistration : chr NA "Republican" NA "Decline/No Party/Independent" ...
## $ PartyIdentification : chr "Democrat" "Republican" "Republican" "Independent" ...
## $ PartyIdentification2 : chr "Not very strong Democrat" "Strong Republican" "Strong Republican" "Independent" ...
## $ PartyIdentification3 : chr "Moderate" "Conservative" "Moderate" "Moderate" ...
## $ NewsPublicAffairs : chr "Most of the time" "Most of the time" "Most of the time" "Most of the time" ...
## $ DemPrimary : chr "Hillary Clinton" NA "Hillary Clinton" "Someone Else" ...
## $ RepPrimary : chr NA "Donald Trump" NA NA ...
## $ ImmigrantContributions : chr "Mostly Contribute" "Mostly a Drain" "Mostly Contribute" "Mostly Contribute" ...
## $ ImmigrantNaturalization: chr "Favor" "Not Sure" "Favor" "Favor" ...
## $ ImmigrationShouldBe : chr "Slightly Easier" "No change" "Much Easier" "Much Easier" ...
## $ Abortion : chr "Legal in all cases" "Legal in some cases and Illegal in others" "Legal in all cases" "Legal in some cases and Illegal in others" ...
## $ GayMarriage : chr "Favor" "Oppose" "Favor" "Favor" ...
## $ DeathPenalty : chr "Oppose" "Favor" "Favor" "Favor" ...
## $ DeathPenaltyFreq : chr "Too Often" "Not Often Enough" "Not Often Enough" "About Right" ...
## $ TaxWealthy : chr "Favor" "Oppose" "Favor" "Favor" ...
## $ Healthcare : chr "Yes" "No" "Yes" "Yes" ...
## $ GlobWarmExist : chr "Definitely is happening" "Definitely not happening" "Definitely is happening" "Definitely is happening" ...
## $ GlobWarmingSerious : chr "Very Serious" NA "Very Serious" "Somewhat Serious" ...
## $ AffirmativeAction : chr "Favor" "Oppose" "Favor" "Favor" ...
## $ Religion : chr "Roman Catholic" "Mormon" "Agnostic" "Nothing in Particular" ...
## $ ReligiousImportance : chr "Somewhat Important" "Very Important" "Not at all Important" "Not at all Important" ...
## $ ChurchAttendance : chr "Seldom" "More than once a week" "Seldom" "Seldom" ...
## $ PrayerFrequency : chr "Once a day" "Several times a day" "Never" "A few times a month" ...
## $ NumChildren : num 0 0 0 0 0 0 1 0 0 0 ...
## $ areatype : chr "Suburb" "Rural Area" "City" "City" ...
## $ GunOwnership : chr "No Gun in Household" "Gun in Household" "Gun in Household" "No Gun in Household" ...
## $ ft_fem_2017 : num 99 65 74 NA 25 100 73 50 100 100 ...
## $ ft_immig_2017 : num 95 96 77 NA 91 100 100 1 90 80 ...
## $ ft_police_2017 : num 76 95 78 NA 94 28 24 95 60 16 ...
## $ ft_dem_2017 : num 88 86 91 NA 22 99 53 1 90 84 ...
## $ ft_rep_2017 : num 21 96 20 NA 83 NA 4 50 10 5 ...
## $ ft_evang_2017 : num 50 96 2 NA 70 NA 53 50 25 6 ...
## $ ft_muslim_2017 : num 50 61 49 NA 80 100 100 1 69 71 ...
## $ ft_jew_2017 : num 50 100 25 NA 91 100 100 50 71 71 ...
## $ ft_christ_2017 : num 50 98 50 NA 94 28 100 95 70 51 ...
## $ ft_gays_2017 : num 50 82 77 NA 71 100 54 1 100 71 ...
## $ ft_unions_2017 : num 80 62 100 NA 20 100 80 1 90 81 ...
## $ ft_altright_2017 : num 1 50 0 NA 50 NA 4 50 0 0 ...
## $ ft_black_2017 : num 51 98 87 NA 90 100 98 10 56 72 ...
## $ ft_white_2017 : num 50 90 90 NA 85 50 70 50 41 70 ...
## $ ft_hisp_2017 : num 79 95 91 NA 90 100 99 26 56 71 ...
## - attr(*, "spec")=
## .. cols(
## .. gender = col_character(),
## .. race = col_character(),
## .. education = col_character(),
## .. familyincome = col_character(),
## .. children = col_character(),
## .. region = col_character(),
## .. urbancity = col_character(),
## .. Vote2012 = col_character(),
## .. Vote2016 = col_character(),
## .. TrumpSanders = col_character(),
## .. PartyRegistration = col_character(),
## .. PartyIdentification = col_character(),
## .. PartyIdentification2 = col_character(),
## .. PartyIdentification3 = col_character(),
## .. NewsPublicAffairs = col_character(),
## .. DemPrimary = col_character(),
## .. RepPrimary = col_character(),
## .. ImmigrantContributions = col_character(),
## .. ImmigrantNaturalization = col_character(),
## .. ImmigrationShouldBe = col_character(),
## .. Abortion = col_character(),
## .. GayMarriage = col_character(),
## .. DeathPenalty = col_character(),
## .. DeathPenaltyFreq = col_character(),
## .. TaxWealthy = col_character(),
## .. Healthcare = col_character(),
## .. GlobWarmExist = col_character(),
## .. GlobWarmingSerious = col_character(),
## .. AffirmativeAction = col_character(),
## .. Religion = col_character(),
## .. ReligiousImportance = col_character(),
## .. ChurchAttendance = col_character(),
## .. PrayerFrequency = col_character(),
## .. NumChildren = col_double(),
## .. areatype = col_character(),
## .. GunOwnership = col_character(),
## .. 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()
## .. )
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
voterdata%>%
summarize(Avg_FT_feminists = mean(ft_fem_2017,na.rm=TRUE))
## # A tibble: 1 x 1
## Avg_FT_feminists
## <dbl>
## 1 52.1
library(dplyr)
voterdata%>%
group_by(education)%>%
summarize(Avg_FT_feminists = mean(ft_fem_2017,na.rm=TRUE))
## # A tibble: 7 x 2
## education Avg_FT_feminists
## <chr> <dbl>
## 1 2-year 50.0
## 2 4-year 54.8
## 3 High School Graduate 47.6
## 4 No High School 43.3
## 5 Post Grad 57.4
## 6 Some College 52.1
## 7 <NA> 53.4
library(ggplot2)
voterdata%>%
ggplot()+
geom_histogram(aes(x=ft_fem_2017))
library(ggplot2)
voterdata%>%
ggplot()+
geom_histogram(aes(x=ft_fem_2017))+
facet_wrap(~education)
library(dplyr)
voterdata%>%
summarize(Avg_FT_hispanics = mean(ft_hisp_2017,na.rm=TRUE))
## # A tibble: 1 x 1
## Avg_FT_hispanics
## <dbl>
## 1 70.2
library(dplyr)
voterdata%>%
group_by(gender)%>%
summarize(Avg_FT_hispanics = mean(ft_hisp_2017,na.rm=TRUE))
## # A tibble: 2 x 2
## gender Avg_FT_hispanics
## <chr> <dbl>
## 1 Female 71.1
## 2 Male 69.1
library(ggplot2)
voterdata%>%
ggplot()+
geom_histogram(aes(x=ft_hisp_2017))
library(ggplot2)
voterdata%>%
ggplot()+
geom_histogram(aes(x=ft_hisp_2017))+
facet_wrap(~gender)
library(dplyr)
voterdata%>%
summarize(Avg_FT_whites = mean(ft_white_2017,na.rm=TRUE))
## # A tibble: 1 x 1
## Avg_FT_whites
## <dbl>
## 1 76.1
library(dplyr)
voterdata%>%
group_by(familyincome)%>%
summarize(Avg_FT_ = mean(ft_white_2017,na.rm=TRUE))
## # A tibble: 18 x 2
## familyincome Avg_FT_
## <chr> <dbl>
## 1 $100K-$119,999 75.8
## 2 $10K-$19,999 75.5
## 3 $120K-$149,999 73.6
## 4 $150K or more 73.7
## 5 $150K-$199,999 73.9
## 6 $200K-$249,999 75.5
## 7 $20K-$29,999 77.1
## 8 $250K-$349,999 75.9
## 9 $30K-$39,999 77.8
## 10 $350K-$499,999 77.4
## 11 $40K-$49,999 77.2
## 12 $500K or more 77.9
## 13 $50K-$59,999 75.8
## 14 $60K-$69,999 76.6
## 15 $70K-$79,999 75.5
## 16 $80K-$99,999 76.1
## 17 Less than $10K 74.2
## 18 Prefer not to say 76.7
library(ggplot2)
voterdata%>%
ggplot()+
geom_histogram(aes(x=ft_white_2017))
library(ggplot2)
voterdata%>%
ggplot()+
geom_histogram(aes(x=ft_white_2017))+
facet_wrap(~familyincome)
