Dealing With Missing Data

# Load Packages ----------------------------------------------------------

library(tidyverse)
library(fs)
library(readxl)
library(janitor)

# Create Directory -------------------------------------------------------

dir_create("data-raw")

# Download Data ----------------------------------------------------------

# https://www.oregon.gov/ode/reports-and-data/students/Pages/Student-Enrollment-Reports.aspx

# download.file(
#   url = "https://www.oregon.gov/ode/reports-and-data/students/Documents/fallmembershipreport_20222023.xlsx",
#   mode = "wb",
#   destfile = "data-raw/fallmembershipreport_20222023.xlsx"
# )

# download.file(
#   "https://www.oregon.gov/ode/reports-and-data/students/Documents/fallmembershipreport_20212022.xlsx",
#   mode = "wb",
#   destfile = "data-raw/fallmembershipreport_20212022.xlsx"
# )

# download.file(
#   "https://www.oregon.gov/ode/reports-and-data/students/Documents/fallmembershipreport_20202021.xlsx",
#   mode = "wb",
#   destfile = "data-raw/fallmembershipreport_20202021.xlsx"
# )

# download.file(
#   "https://www.oregon.gov/ode/reports-and-data/students/Documents/fallmembershipreport_20192020.xlsx",
#   mode = "wb",
#   destfile = "data-raw/fallmembershipreport_20192020.xlsx"
# )

# download.file(
#   "https://www.oregon.gov/ode/reports-and-data/students/Documents/fallmembershipreport_20182019.xlsx",
#   mode = "wb",
#   destfile = "data-raw/fallmembershipreport_20182019.xlsx"
# )

# Import Data ------------------------------------------------------------

enrollment_2022_2023 <-
  read_excel(
    path = "data-raw/fallmembershipreport_20222023.xlsx",
    sheet = "School 2022-23"
  ) |>
  clean_names()

# Tidy and Clean Data ----------------------------------------------------

enrollment_by_race_ethnicity_2022_2023 <-
  enrollment_2022_2023 |>
  select(
    district_institution_id,
    school_institution_id,
    x2022_23_american_indian_alaska_native:x2022_23_multi_racial
  ) |>
  select(-contains("percent")) |>
  pivot_longer(
    cols = -c(district_institution_id, school_institution_id),
    names_to = "race_ethnicity",
    values_to = "number_of_students"
  ) |>
  mutate(race_ethnicity = str_remove(race_ethnicity, "x2022_23_")) |>
  mutate(
    race_ethnicity = recode_values(
      race_ethnicity,
      "american_indian_alaska_native" ~ "American Indian Alaska Native",
      "asian" ~ "Asian",
      "black_african_american" ~ "Black/African American",
      "hispanic_latino" ~ "Hispanic/Latino",
      "multiracial" ~ "Multi-Racial",
      "native_hawaiian_pacific_islander" ~ "Native Hawaiian Pacific Islander",
      "white" ~ "White",
      "multi_racial" ~ "Multiracial"
    )
  ) |>
  mutate(number_of_students = parse_number(number_of_students))

enrollment_by_race_ethnicity_2022_2023 |>
  mutate(number_of_students = replace_na(number_of_students, 0)) |>
  filter(is.na(number_of_students))