PEW assignment

glimpse(pew)

Observations: 2,002
Variables: 70
$ respid      <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 13, 14, 15…
$ sample      <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
$ comp        <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
$ int_date    <dbl> 180103, 180103, 180103, 180103, 180103, 18010…
$ lang        <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, …
$ cregion     <dbl> 1, 3, 1, 3, 1, 3, 3, 1, 3, 3, 3, 3, 1, 3, 3, …
$ state       <dbl> 42, 45, 34, 24, 33, 37, 12, 34, 51, 54, 51, 1…
$ density     <dbl> 5, 2, 5, 4, 2, 3, 5, 5, 1, 2, 2, 5, 4, 1, 2, …
$ usr         <chr> "U", "S", "S", "S", "R", "U", "U", "S", "R", …
$ qs1         <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
$ sex         <dbl> 2, 2, 2, 2, 1, 1, 2, 1, 1, 2, 1, 2, 1, 2, 2, …
$ eminuse     <dbl> 1, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 2, 1, 1, …
$ intmob      <dbl> 1, 2, 2, 1, 1, 1, 1, 1, 2, 1, 1, 1, 2, 1, 1, …
$ intfreq     <dbl> 1, NA, 3, 4, 2, 2, 2, 2, NA, 2, 2, 2, NA, 3, …
$ home4nw     <dbl> 1, NA, 1, 1, 1, 1, 1, 1, NA, 1, 1, 1, NA, 1, …
$ bbhome1     <dbl> 2, NA, 2, 2, 2, 2, 2, 2, NA, 2, 2, 2, NA, 2, …
$ bbhome2     <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
$ device1a    <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 2, 1, 1, …
$ smart2      <dbl> 1, 2, 1, 1, 1, 1, 1, 1, NA, 1, 1, 1, NA, 1, 1…
$ snsint2     <dbl> 1, 2, 2, 1, 1, 1, 1, 1, 2, 1, 2, 1, 2, 1, 1, …
$ device1b    <dbl> 1, 2, 1, 2, 1, 1, 2, 1, 2, 1, 1, 1, 2, 2, 2, …
$ device1c    <dbl> 1, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 2, 1, 2, …
$ device1d    <dbl> 1, 2, 2, 2, 1, 2, 2, 2, 2, 1, 2, 2, 2, 2, 9, …
$ web1a       <dbl> 2, 2, 2, 2, 2, 1, 2, 2, NA, 2, 1, 2, NA, 1, 2…
$ web1b       <dbl> 1, 2, 2, 2, 2, 2, 2, 2, NA, 2, 1, 2, NA, 2, 2…
$ web1c       <dbl> 1, 2, 2, 1, 1, 1, 1, 1, NA, 1, 1, 1, NA, 1, 1…
$ web1d       <dbl> 1, 2, 2, 2, 2, 2, 2, 2, NA, 2, 2, 2, NA, 2, 2…
$ web1e       <dbl> 1, 2, 2, 2, 1, 1, 1, 1, NA, 1, 1, 1, NA, 1, 2…
$ web1f       <dbl> 1, 2, 2, 2, 2, 2, 2, 2, NA, 2, 2, 2, NA, 1, 2…
$ web1g       <dbl> 2, 2, 2, 2, 1, 1, 1, 1, NA, 2, 2, 2, NA, 1, 1…
$ web1h       <dbl> 2, 2, 2, 2, 1, 1, 1, 1, NA, 2, 2, 2, NA, 2, 2…
$ sns2a       <dbl> NA, NA, NA, NA, NA, 2, NA, NA, NA, NA, 1, NA,…
$ sns2b       <dbl> 1, NA, NA, NA, NA, NA, NA, NA, NA, NA, 4, NA,…
$ sns2c       <dbl> 1, NA, NA, 3, 3, 1, 3, 2, NA, 2, 3, 5, NA, 1,…
$ sns2d       <dbl> 3, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ sns2e       <dbl> 3, NA, NA, NA, 2, 3, 5, 4, NA, 4, 4, 3, NA, 4…
$ pial5a      <dbl> 2, 2, 1, 2, 1, 3, 3, 2, 6, 1, 1, 2, 1, 1, 3, …
$ pial5b      <dbl> 1, 3, 2, 3, 2, 5, 3, 2, NA, 2, 4, 1, NA, 3, 1…
$ pial5c      <dbl> 2, NA, 1, 3, 1, 1, 3, 2, NA, 2, 1, 1, NA, 1, …
$ pial5d      <dbl> 3, NA, NA, 3, 3, 1, 4, 3, NA, 3, NA, 4, NA, 3…
$ pial11      <dbl> 1, 8, 1, 2, 1, 3, 8, 1, 8, 1, 1, 1, 8, 1, 2, …
$ pial11a     <dbl> 1, NA, 1, 1, 1, NA, NA, 1, NA, 1, 1, 1, NA, 1…
$ `pial11ao@` <chr> "information has become available more freque…
$ pial11_igbm <dbl> 1, 9, 2, 5, 1, 9, 9, 1, 9, 1, 1, 1, 9, 1, 8, …
$ pial12      <dbl> 1, NA, 1, 1, 1, 1, 1, 1, NA, 1, 1, 1, NA, 1, …
$ books1      <dbl> 1, 5, 0, 2, 6, 18, 3, 2, 3, 97, 5, 8, 6, 3, 9…
$ books2a     <dbl> 1, 1, NA, 1, 1, 1, 1, 1, 2, 2, 1, 1, 2, 1, 1,…
$ books2b     <dbl> 2, 2, NA, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2,…
$ books2c     <dbl> 2, 2, NA, 2, 1, 1, 1, 1, 2, 1, 1, 2, 2, 1, 2,…
$ age         <dbl> 33, 76, 99, 60, 55, 58, 99, 72, 58, 68, 65, 6…
$ marital     <dbl> 2, 1, 5, 2, 1, 1, 1, 1, 6, 1, 1, 1, 1, 1, 1, …
$ educ2       <dbl> 3, 98, 5, 5, 4, 7, 5, 6, 1, 6, 7, 6, 7, 6, 7,…
$ emplnw      <dbl> 1, 3, 5, 8, 1, 1, 5, 4, 4, 3, 3, 2, 3, 3, 4, …
$ hisp        <dbl> 2, 2, 2, 2, 2, 2, 9, 2, 2, 2, 2, 2, 2, 2, 2, …
$ racem1      <dbl> 1, 1, 1, 1, 1, 1, 9, 1, 2, 1, 1, 1, 3, 1, 1, …
$ racem2      <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
$ racem3      <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
$ racem4      <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
$ racecmb     <dbl> 1, 1, 1, 1, 1, 1, 9, 1, 2, 1, 1, 1, 3, 1, 1, …
$ birth_hisp  <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
$ inc         <dbl> 6, 4, 4, 2, 7, 7, 9, 6, 1, 2, 2, 6, 4, 5, 99,…
$ party       <dbl> 2, 3, 1, 2, 1, 3, 2, 3, 1, 4, 1, 3, 2, 1, 1, …
$ partyln     <dbl> NA, 8, NA, NA, NA, 2, NA, 2, NA, 8, NA, 1, NA…
$ hh1         <dbl> 5, 2, 1, 2, 3, 2, 2, 2, 1, 2, 5, 2, 2, 2, 9, …
$ hh3         <dbl> 4, 2, NA, 2, 3, 2, 2, 2, NA, 2, 4, 2, 2, 2, 2…
$ ql1         <dbl> 1, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 2, 1, 1, …
$ ql1a        <dbl> NA, 2, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA…
$ qc1         <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
$ weight      <dbl> 1.7463586, 1.6597644, 0.4908044, 0.9479652, 0…
$ cellweight  <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…

pew <- pew %>% 
  mutate(web1c = as.factor(web1c))


pew %>% 
  count(web1c)

pew <- pew %>% 
  mutate(educ2 = as.factor(educ2))


pew %>% 
  count(educ2)

pew <- pew %>% 
  mutate(web1c = as.factor(web1c))


pew %>% 
  count(web1c)

pew <- pew %>%
  mutate(web1c = fct_recode( web1c,
                              "Yes" = "1",
                              "No" = "2",
                               NULL = "8",
                              NULL = "9"))

pew %>% 
  count(web1c)

pew <- pew %>% 
  mutate(educ2 = as.factor(educ2))


pew %>% 
  count(educ2)

pew <- pew %>%
  mutate(educ2 = fct_recode( educ2,
                              "Less than HS" = "1", 
                             "Some HS" = "2",
                             "HS graduate" = "3", 
                             "Some college" = "4", 
                             "Associate degree" = "5" , 
                             "College degree" = "6",
                             "Some grad school" = "7" ,
                            "Grad degree" = "8",
                             "Don't know" = "98",
                             "Refused" = "99"))

pew %>% 
  count(educ2)

pew %>% 

drop_na(educ2,web1c)

pew %>% 
  count(educ2, web1c)

pew %>% 
  drop_na(web1c) %>% 
  ggplot(aes(x = educ2, fill = web1c)) +
  geom_bar( position = "fill" ) + scale_fill_viridis_d() + coord_flip()

pew %>% 
  drop_na(educ2) %>% 
  ggplot(aes(x = educ2)) +
  geom_bar()

pew %>% 
  drop_na(web1c) %>% 
  ggplot(aes(x = web1c)) +
  geom_bar()

pew %>% 
  drop_na(educ2) %>% 
  ggplot(aes(x = educ2)) +
  geom_bar() +
  facet_wrap(vars(web1c)) +
  coord_flip() +
  theme_minimal() +
  labs(y = "Facebook usge", 
       x = "Highschool/ College level", 
       title = "Facebook Users Vs Schooling")

pew <- pew %>% 
  mutate(edu2_simple = fct_collapse(educ2,
                                            Highschool = c("Less than HS", 
                                                              "Some HS", 
                                                              "HS graduate"),
                                            College = c("Some college", 
                                                                "Associate degree","College degree", "Some grad school", "Grad degree", "Don't know", "Refused")))

pew %>% 
  count(edu2_simple)

pew %>% 
  drop_na(web1c) %>% 
  ggplot(aes(x = edu2_simple)) +
  geom_bar()