Changing Variable Types

This lesson is called Changing Variable Types, part of the Going Deeper with R course. This lesson is called Changing Variable Types, part of the Going Deeper with R course.

Transcript

Click on the transcript to go to that point in the video. Please note that transcripts are auto generated and may contain minor inaccuracies.

View code shown in video

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

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

# Create Directories ------------------------------------------------------

dir_create("data-raw")

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

# https://www.oregon.gov/ode/educator-resources/assessment/Pages/Assessment-Group-Reports.aspx

# download.file("https://www.oregon.gov/ode/educator-resources/assessment/Documents/TestResults2122/pagr_schools_math_tot_raceethnicity_2122.xlsx",
#               mode = "wb",
#               destfile = "data-raw/pagr_schools_math_tot_raceethnicity_2122.xlsx")
#
# download.file("https://www.oregon.gov/ode/educator-resources/assessment/Documents/TestResults2122/TestResults2019/pagr_schools_math_tot_raceethnicity_1819.xlsx",
#               mode = "wb",
#               destfile = "data-raw/pagr_schools_math_tot_raceethnicity_1819.xlsx")
#
# download.file("https://www.oregon.gov/ode/educator-resources/assessment/TestResults2018/pagr_schools_math_raceethnicity_1718.xlsx",
#               mode = "wb",
#               destfile = "data-raw/pagr_schools_math_raceethnicity_1718.xlsx")
#
# download.file("https://www.oregon.gov/ode/educator-resources/assessment/TestResults2017/pagr_schools_math_raceethnicity_1617.xlsx",
#               mode = "wb",
#               destfile = "data-raw/pagr_schools_math_raceethnicity_1617.xlsx")
#
# download.file("https://www.oregon.gov/ode/educator-resources/assessment/TestResults2016/pagr_schools_math_raceethnicity_1516.xlsx",
#               mode = "wb",
#               destfile = "data-raw/pagr_schools_math_raceethnicity_1516.xlsx")

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

math_scores_2021_2022 <-
  read_excel(path = "data-raw/pagr_schools_math_tot_raceethnicity_2122.xlsx") |>
  clean_names()


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

third_grade_math_proficiency_2021_2022 <-
  math_scores_2021_2022 |>
  filter(student_group == "Total Population (All Students)") |>
  filter(grade_level == "Grade 3") |>
  select(academic_year, school_id, contains("number_level")) |>
  pivot_longer(
    cols = starts_with("number_level"),
    names_to = "proficiency_level",
    values_to = "number_of_students"
  ) |>
  mutate(
    proficiency_level = recode_values(
      proficiency_level,
      "number_level_4" ~ "4",
      "number_level_3" ~ "3",
      "number_level_2" ~ "2",
      "number_level_1" ~ "1"
    )
  )

third_grade_math_proficiency_2021_2022 |>
  mutate(number_of_students = as.numeric(number_of_students)) |>
  summarize(total_student = sum(number_of_students, na.rm = TRUE))

third_grade_math_proficiency_2021_2022 |>
  mutate(number_of_students = parse_number(number_of_students)) |>
  summarize(total_student = sum(number_of_students, na.rm = TRUE))

Your Turn

Solution

# 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"
    )
  )

enrollment_by_race_ethnicity_2022_2023 |>
  mutate(number_of_students = as.numeric(number_of_students))

enrollment_by_race_ethnicity_2022_2023 |>
  mutate(number_of_students = parse_number(number_of_students)) |>
  summarize(total_students = sum(number_of_students, na.rm = TRUE))

Convert the number_of_students variable to numeric by using as.numeric() and parse_number().
Make sure you can use your number_of_students variable to count the total number of students in Oregon.

Use the following starter code to help you:

# 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"
    )
  )

Have any questions? Put them below and we will help you out!

You need to be signed-in to comment on this post. Login.

Leigh Barton • April 15, 2026

When I use recode_values() I get the following error:

Error in mutate(): ℹ In argument: race_ethnicity = recode_values(...). Caused by error in recode_values(): ! could not find function "recode_values"

I was able to work around the error by using case_when() instead, just wondering why recode_values won't work for me. Thanks!

Gracielle Higino Coach • April 15, 2026

Hi Leigh! The recode_values() is a very new function released in the latest version of {dplyr}. Make sure you have the latest version of this package installed (1.2.1), and if not, try installing the package again in a new R session.