-
-
Save toyeiei/538795a3ff4071829a5d7a79c1af7614 to your computer and use it in GitHub Desktop.
generate data R for Excel users
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
## generate vectors | |
set.seed(99) | |
id <- 1:100 | |
student_name <- replicate(100, paste0(sample(LETTERS, size = 5, replace = T), collapse = "")) | |
gender <- factor(sample(c(0,1), size = 100, replace = T, prob = c(.7, .3)), | |
labels = c("M", "F")) | |
age <- sample(19:32, size = 100, replace = T) | |
gpa <- rnorm(n = 100, mean = 3.15, sd = 0.25) | |
gpa <- ifelse(gpa > 4, 4.00, gpa) | |
nationality <- factor(sample(c(0,1,2), size = 100, replace = T, prob = c(0.5, 0.3, 0.2)), | |
labels = c("TH", "US", "CH")) | |
## create a dataframe from vectors | |
df <- data.frame(id, student_name, gender, age, gpa, nationality) | |
head(df) | |
## create a lookup table in this example | |
set.seed(99) | |
us_students <- df %>% filter(nationality == "US") %>% .[["id"]] | |
lookup_state <- data.frame(us_students, | |
states = sample(state.name, size = length(us_students), replace = TRUE)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment