Code for 11/16

grad_methods_code_1116.R

error_bar <- function(wd){
  
  if(missing(wd)){
    
    geom_errorbar(aes(ymin=lower, ymax=upper), width=.2, position=position_dodge(.9)) 
  } else{
    
    geom_errorbar(aes(ymin=lower, ymax=upper), width=wd, position=position_dodge(.9)) 
  }
}

cces20 <- read_csv("https://www.dropbox.com/s/wuixmc67ae786wp/small_ces2020.csv?dl=1")


### CALCULATE THE SHARE OF EACH RACIAL GROUP THAT HAS A FOUR YEAR COLLEGE DEGREE #####

ed <- cces20 %>% 
  mutate(race = frcode(race == 1 ~ "White", 
                       race == 2 ~ "Black", 
                       race == 3 ~ "Hispanic",
                       race == 4 ~ "Asian", 
                       race == 5 ~ "Native American", 
                       race == 6 ~ "Two Or More",
                       race == 7 ~ "Other", 
                       race == 8 ~ "Middle Eastern")) %>% 
  mutate(ba = case_when(educ == 5 | educ == 6 ~ 1, 
                        educ <= 4 ~ 0))  %>% 
  group_by(race) %>% 
  mean_ci(ba)

ed %>% 
  ggplot(., aes(x = race, y = mean)) +
  geom_col() +
  coord_flip() +
  error_bar()


ed1 <- cces20 %>% 
  mutate(ba = case_when(educ == 5 | educ == 6 ~ 1, 
                        educ <= 4 ~ 0))  %>% 
  group_by(birthyr) %>% 
  mean_ci(ba)

ed1 %>% 
  filter(birthyr >= 1940) %>% 
  ggplot(., aes(x = birthyr, y = mean )) +
  geom_point() +
  error_bar()



ed2 <- cces20 %>% 
  mutate(race2 = frcode(race == 1 ~ "White", 
                        TRUE ~ "Non-White")) %>% 
  mutate(ba = case_when(educ == 5 | educ == 6 ~ 1, 
                        educ <= 4 ~ 0))  %>% 
  group_by(birthyr, race2) %>% 
  mean_ci(ba)


ed2 %>% 
  filter(birthyr >= 1940) %>% 
  ggplot(., aes(x = birthyr, y = mean, color = race2)) +
  geom_point() +
  error_bar()

## Republicans

gg1 <- cces20 %>% 
  filter(pid7 == 5 | pid7 == 6 | pid7 == 7) %>% 
  mutate(ba = case_when(educ == 5 | educ == 6 ~ 1, 
                        educ <= 4 ~ 0))  %>%
  mutate(gender = frcode(gender == 1 ~ "Men",
                         gender == 2 ~ "Women")) %>% 
  group_by(gender) %>% 
  mean_ci(ba) %>% 
  mutate(pid = "Republican")


gg2 <- cces20 %>% 
  filter(pid7 == 1 | pid7 == 2 | pid7 == 3) %>% 
  mutate(ba = case_when(educ == 5 | educ == 6 ~ 1, 
                        educ <= 4 ~ 0))  %>%
  mutate(gender = frcode(gender == 1 ~ "Men",
                         gender == 2 ~ "Women")) %>% 
  group_by(gender) %>% 
  mean_ci(ba) %>% 
  mutate(pid = "Democrat")

gg3 <- bind_rows(gg1, gg2)

gg3 %>% 
  ggplot(., aes(x = gender, y = mean, fill = pid)) +
  geom_col(position = "dodge") +
  error_bar() +
  scale_fill_manual(values = c("dodgerblue3", "firebrick3"))


bball <- read_csv("https://raw.githubusercontent.com/ryanburge/pls2003_sp17/master/bball.csv", guess_max = 25000) %>%
  rename(games = g, wins =w, losses = l, runs =r, atbats = ab, hits =h, homeruns =hr, walks = bb, strikeout = so, stolenbase = sb, earnedruns = era)

bball %>% 
  ggplot(., aes(x = runs, y = wins)) +
  geom_point() +
  geom_smooth(method = lm)

lm(wins ~ runs, data = bball)


bball %>% 
  ggplot(., aes(x = wins, y = attendance, color = league_id)) +
  geom_point() +
  geom_smooth(method = lm)

lm(attendance ~ wins, data = bball)

bball %>% 
  arrange(-runs)


## LEAST NUMBER OF RUNS SCORED IN 2003 ####

bball %>% 
  filter(year == 2003) %>% 
  arrange(runs)

bball %>% 
  select(team_id, wins, runs)