# install.packages("randomNames")
library(randomNames)
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.7
## v tidyr 1.1.4 v stringr 1.4.0
## v readr 2.1.1 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
# for replication, set the seed to 2022
set.seed(2022)
# generate names
names <- randomNames(100);
# look at the top 5 names
names[1:5]
## [1] "al-Asad, Nu'ma" "al-Kazi, Zuhair" "Finley, Lauren" "Poghosyan, Randy"
## [5] "Ka, Gerald"
The mean grade is 70 with a standard deviation of 15.
#set seed to 2020 for replication
set.seed(2022)
# generating the grades using rnorm and floor function
grades <- rnorm(100, mean = 70, sd = 15) %>%
floor()
# look at top 5 grades
grades[1:5]
## [1] 83 52 56 48 65
students.grade.df <- tibble(names, grades)
# head function of top 10 names
head(students.grade.df,10)
## # A tibble: 10 x 2
## names grades
## <chr> <dbl>
## 1 al-Asad, Nu'ma 83
## 2 al-Kazi, Zuhair 52
## 3 Finley, Lauren 56
## 4 Poghosyan, Randy 48
## 5 Ka, Gerald 65
## 6 Little, Kaitlyn 26
## 7 Rioja Piedras, Jacina 54
## 8 Gonzalez, Kahlin 74
## 9 al-Ismail, Sadeeda 81
## 10 Roach, Miranda 73
write_csv(students.grade.df, "student_grades.csv")
The write_csv from readr package is approximately twice as fast compared to the write.csv base command. The outcome is also a clean csv file without row names included as a column.