IDA R Notebook

# Packages for cleaning, wrangling, and visualizing
library(tidyverse)
library(janitor)
library(scales)

Read in the data

ipeds_two <- read_csv("ipeds_final.csv")

Examine the data

head(ipeds)

Clean the data

#Clean variable names 
ipeds_two <- clean_names(ipeds_two)

#Rename Variables names 

ipeds_rename <- ipeds_two %>% 
  rename(
    total_enrollment = 3,
    total_bachelors_4 = 4, 
    total_bachelors_6 = 5,
    race_unknown_men = 6, 
    race_unknown_women = 7, 
    Male = 8, 
    Female = 9, 
    hispanic_men = 10, 
    hispanic_women = 11, 
    aian_men = 12, 
    aian_women = 13, 
    asian_men = 14, 
    asian_women = 15, 
    black_men = 16, 
    black_women = 17, 
    nhpi_men = 18, 
    nhpi_women = 19, 
    white_men = 20, 
    white_women = 21, 
    multi_men = 22, 
    multi_women = 23) %>% 
  select(-24)

Wrangle the Data

Prepare Data for Graduation Rate Visualization

#Prepare data for visualization Graduate rate 
ipeds_grad_overall <- ipeds_rename %>% 
  select(2:5)

ipeds_grad_overall <- ipeds_grad_overall %>% 
  mutate(graduation_four_rate = round(total_bachelors_4/total_enrollment,2),
         graduation_six_rate = round(total_bachelors_6/total_enrollment,2),
         perc_four_rate = paste0(sprintf("%4.1f", total_bachelors_4 / total_enrollment * 100), "%"),
         perc_six_rate = paste0(sprintf("%4.1f", total_bachelors_6 / total_enrollment * 100), "%")) 

Prepare Data for Disaggregation

#Prepare data to visualize by Gender 
ipeds_gender <- ipeds_rename %>% 
  pivot_longer(cols = Male:Female, names_to = "sex", values_to = "total_enrolled") %>% 
  select(-(race_unknown_men:multi_women)) %>% 
   mutate(graduation_four_rate = round(total_bachelors_4/total_enrollment,4),
         graduation_six_rate = round(total_bachelors_6/total_enrollment,4),
         perc_four_rate = paste0(sprintf("%4.1f", total_bachelors_4 / total_enrollment * 100), "%"),
         perc_six_rate = paste0(sprintf("%4.1f", total_bachelors_6 / total_enrollment * 100), "%")) %>% 
  rename(Graduation = total_enrolled) %>% 
  select(-(graduation_four_rate:perc_six_rate)) %>% 
  select(-total_bachelors_4, -total_bachelors_6) %>% 
  mutate(Graduation_perc = round(Graduation/total_enrollment,4),
         perc_rate = paste0(sprintf("%4.1f", Graduation/total_enrollment * 100), "%")) 

Visualize the Data

4-year Graduation Rate

#Visualize 4- year Graduate rate 
ipeds_grad_overall %>% 
  mutate(highlight = ifelse(institution_name == "University of Washington-Seattle Campus", T, F)) %>% 
  ggplot(aes(x = reorder(institution_name, graduation_four_rate), y = graduation_four_rate)) + 
  geom_col(aes(fill = highlight)) + 
  scale_fill_manual(values = c("grey60", "#4b2e83")) +
  coord_flip() +
  labs(title = "4-year Graduation Rate",
       subtitle = "For Far West Public Research Institutions",
       x = "",
       y = "",
       fill= "Institution Name",
       caption = "Data provided by Integrated Postsecondary Education Data System") +
  theme_minimal() +
  theme(axis.text.x = element_blank(),
        axis.ticks.x = element_blank(),
        axis.ticks.y = element_blank(),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()) +
  geom_text(aes(label = perc_four_rate), hjust = 1, nudge_x = .1, color = "white", fontface = "bold" ) +
  scale_y_continuous(labels = scales::percent)

6-Year Graduation Rate

# Visualize 6 year graduation rate 
ipeds_grad_overall %>% 
  mutate(highlight = ifelse(institution_name == "University of Washington-Seattle Campus", T, F)) %>% 
  ggplot(aes(x = reorder(institution_name, graduation_six_rate), y = graduation_six_rate)) + 
  geom_col(aes(fill = highlight)) + 
  scale_fill_manual(values = c("grey60", "#4b2e83")) +
  coord_flip() +
  labs(title = "6-year Graduation Rate",
       subtitle = "For Far West Public Research Institutions",
       x = "",
       y = "",
       fill= "Institution Name",
       caption = "Data provided by Integrated Postsecondary Education Data System") +
  theme_minimal() +
  theme(axis.text.x = element_blank(),
        axis.ticks.x = element_blank(),
        axis.ticks.y = element_blank(),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()) +
  geom_text(aes(label = perc_six_rate), hjust = 1, nudge_x = .1, color = "white", fontface = "bold" ) +
  scale_y_continuous(labels = scales::percent)

Female Graduation Rate

#Female Visualization 
ipeds_gender %>% 
  filter(sex == "Female") %>% 
  mutate(highlight = ifelse(institution_name == "University of Washington-Seattle Campus", T, F)) %>% 
  ggplot(aes(x = reorder(institution_name, Graduation_perc), y = Graduation_perc)) + 
  geom_col(aes(fill = highlight)) + 
  scale_fill_manual(values = c("grey60", "#4b2e83")) +
  coord_flip() +
  labs(title = "Female Graduation Rate",
       subtitle = "For Far West Public Research Institutions",
       x = "",
       y = "",
       fill= "Institution Name",
       caption = "Data provided by Integrated Postsecondary Education Data System") +
  theme_minimal() +
  theme(axis.text.x = element_blank(),
        axis.ticks.x = element_blank(),
        axis.ticks.y = element_blank(),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()) +
  geom_text(aes(label = perc_rate), hjust = 1, nudge_x = .1, color = "white", fontface = "bold" ) +
  scale_y_continuous(labels = scales::percent)

Male Graduation Rate

#Male Visualization 
ipeds_gender %>% 
  filter(sex == "Male") %>% 
  mutate(highlight = ifelse(institution_name == "University of Washington-Seattle Campus", T, F)) %>% 
  ggplot(aes(x = reorder(institution_name, Graduation_perc), y = Graduation_perc)) + 
  geom_col(aes(fill = highlight)) + 
  scale_fill_manual(values = c("grey60", "#4b2e83")) +
  coord_flip() +
  labs(title = "Male Graduation Rate",
       subtitle = "For Far West Public Research Institutions",
       x = "",
       y = "",
       fill= "Institution Name",
       caption = "Data provided by Integrated Postsecondary Education Data System") +
  theme_minimal() +
  theme(axis.text.x = element_blank(),
        axis.ticks.x = element_blank(),
        axis.ticks.y = element_blank(),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()) +
  geom_text(aes(label = perc_rate), hjust = 1, nudge_x = .1, color = "white", fontface = "bold" ) +
  scale_y_continuous(labels = scales::percent)

Facet Wrap of Female and Male Graduation Rate

ipeds_gender %>% 
  mutate(highlight = ifelse(institution_name == "University of Washington-Seattle Campus", T, F)) %>% 
  ggplot(aes(x = reorder(institution_name, Graduation_perc), y = Graduation_perc)) + 
  geom_col(aes(fill = highlight)) + 
  scale_fill_manual(values = c("grey60", "#4b2e83")) +
  coord_flip() +
  labs(title = "Graduation Rate",
       subtitle = "For Far West Public Research Institutions",
       x = "",
       y = "",
       fill= "Institution Name",
       caption = "Data provided by Integrated Postsecondary Education Data System") +
  theme_minimal() +
  theme(axis.text.x = element_blank(),
        axis.ticks.x = element_blank(),
        axis.ticks.y = element_blank(),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()) +
  geom_text(aes(label = perc_rate), hjust = 1, nudge_x = .1, color = "white", fontface = "bold" ) +
  scale_y_continuous(labels = scales::percent) +
  facet_wrap(~sex)