#———————————————————————————– # Hw1: Import data from statistical package and from Database management system
install.packages(c(“haven”,“readxl”,“readr”))
## Load the packages
library(haven)
library(readxl)
library(readr)## Load the data # Excel format
excel_data <-read_excel("C:/Users/enzabihimana/OneDrive - SanlamAllianz/Documents/R/R-first-project/student_marks.xlsx")## summarizing the data
head(excel_data)## # A tibble: 6 × 10
## student_id student_name gender age math english science history geography
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 Kelvin Ardan M 17 78 65 72 80 69
## 2 2 Mira Solen F 16 88 91 85 79 90
## 3 3 Tobias Renk M 18 54 60 48 66 58
## 4 4 Lena Vorik F 17 92 87 94 85 88
## 5 5 Dario Pell M 16 67 72 61 70 75
## 6 6 Nora Beshti F 17 73 80 77 84 81
## # ℹ 1 more variable: attendance_pct <dbl>tail(excel_data)## # A tibble: 6 × 10
## student_id student_name gender age math english science history geography
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 5 Dario Pell M 16 67 72 61 70 75
## 2 6 Nora Beshti F 17 73 80 77 84 81
## 3 7 Sami Orlan M 18 45 52 40 58 49
## 4 8 Ayla Merrow F 16 81 76 83 72 79
## 5 9 Jonas Tarek M 17 60 68 55 63 66
## 6 10 Brina Kolt F 18 95 89 97 92 94
## # ℹ 1 more variable: attendance_pct <dbl>summary(excel_data$science)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 40.0 56.5 74.5 71.2 84.5 97.0## Load the data # CSV format
csv_data <- read_csv("C:/Users/enzabihimana/OneDrive - SanlamAllianz/Documents/R/R-first-project/student_marks.csv",show_col_types=FALSE)## Summarize the data
head(csv_data)## # A tibble: 6 × 10
## student_id student_name gender age math english science history geography
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 Kelvin Ardan M 17 78 65 72 80 69
## 2 2 Mira Solen F 16 88 91 85 79 90
## 3 3 Tobias Renk M 18 54 60 48 66 58
## 4 4 Lena Vorik F 17 92 87 94 85 88
## 5 5 Dario Pell M 16 67 72 61 70 75
## 6 6 Nora Beshti F 17 73 80 77 84 81
## # ℹ 1 more variable: attendance_pct <dbl>tail(csv_data)## # A tibble: 6 × 10
## student_id student_name gender age math english science history geography
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 5 Dario Pell M 16 67 72 61 70 75
## 2 6 Nora Beshti F 17 73 80 77 84 81
## 3 7 Sami Orlan M 18 45 52 40 58 49
## 4 8 Ayla Merrow F 16 81 76 83 72 79
## 5 9 Jonas Tarek M 17 60 68 55 63 66
## 6 10 Brina Kolt F 18 95 89 97 92 94
## # ℹ 1 more variable: attendance_pct <dbl>summary(csv_data$science)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 40.0 56.5 74.5 71.2 84.5 97.0## Load the data # Stata format
dta_data <- read_dta("C:/Users/enzabihimana/OneDrive - SanlamAllianz/Documents/R/R-first-project/student_marks.dta")## Summarize the data
head(dta_data)## # A tibble: 6 × 10
## student_id student_name gender age math english science history geography
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 Kelvin Ardan M 17 78 65 72 80 69
## 2 2 Mira Solen F 16 88 91 85 79 90
## 3 3 Tobias Renk M 18 54 60 48 66 58
## 4 4 Lena Vorik F 17 92 87 94 85 88
## 5 5 Dario Pell M 16 67 72 61 70 75
## 6 6 Nora Beshti F 17 73 80 77 84 81
## # ℹ 1 more variable: attendance_pct <dbl>tail(dta_data)## # A tibble: 6 × 10
## student_id student_name gender age math english science history geography
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 5 Dario Pell M 16 67 72 61 70 75
## 2 6 Nora Beshti F 17 73 80 77 84 81
## 3 7 Sami Orlan M 18 45 52 40 58 49
## 4 8 Ayla Merrow F 16 81 76 83 72 79
## 5 9 Jonas Tarek M 17 60 68 55 63 66
## 6 10 Brina Kolt F 18 95 89 97 92 94
## # ℹ 1 more variable: attendance_pct <dbl>summary(dta_data$science)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 40.0 56.5 74.5 71.2 84.5 97.0#——————————————————————————-
## Examples
# Example 1
age<-c(25,20,16)
summary(age)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 16.00 18.00 20.00 20.33 22.50 25.00# Example 2
age <-c(35,24,15,27)
mean(age)## [1] 25.25## Character
x <- c("a","b","c")
class<-c("M","F","F","M")
## Logical
x <-c(TRUE,FALSE)
x <-c(T,F)
## Complex
x<-c (1+0i,2+4i)
## Integer
x <- 9:29
x## [1] 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29## Matrix and operation with in matrices
(x<-matrix(1:6,nrow=2,ncol=3))## [,1] [,2] [,3]
## [1,] 1 3 5
## [2,] 2 4 6(y<-matrix(1:6,nrow=3,ncol=2))## [,1] [,2]
## [1,] 1 4
## [2,] 2 5
## [3,] 3 6x%*%y## [,1] [,2]
## [1,] 22 49
## [2,] 28 64### Exploratory data Analysis
dta_data## # A tibble: 10 × 10
## student_id student_name gender age math english science history geography
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 Kelvin Ardan M 17 78 65 72 80 69
## 2 2 Mira Solen F 16 88 91 85 79 90
## 3 3 Tobias Renk M 18 54 60 48 66 58
## 4 4 Lena Vorik F 17 92 87 94 85 88
## 5 5 Dario Pell M 16 67 72 61 70 75
## 6 6 Nora Beshti F 17 73 80 77 84 81
## 7 7 Sami Orlan M 18 45 52 40 58 49
## 8 8 Ayla Merrow F 16 81 76 83 72 79
## 9 9 Jonas Tarek M 17 60 68 55 63 66
## 10 10 Brina Kolt F 18 95 89 97 92 94
## # ℹ 1 more variable: attendance_pct <dbl>summary(dta_data)## student_id student_name gender age math
## Min. : 1.00 Length :10 Length :10 Min. :16.00 Min. :45.00
## 1st Qu.: 3.25 N.unique :10 N.unique : 2 1st Qu.:16.25 1st Qu.:61.75
## Median : 5.50 N.blank : 0 N.blank : 0 Median :17.00 Median :75.50
## Mean : 5.50 Min.nchar:10 Min.nchar: 1 Mean :17.00 Mean :73.30
## 3rd Qu.: 7.75 Max.nchar:12 Max.nchar: 1 3rd Qu.:17.75 3rd Qu.:86.25
## Max. :10.00 Max. :18.00 Max. :95.00
## english science history geography attendance_pct
## Min. :52.00 Min. :40.0 Min. :58.0 Min. :49.00 Min. : 75.00
## 1st Qu.:65.75 1st Qu.:56.5 1st Qu.:67.0 1st Qu.:66.75 1st Qu.: 86.25
## Median :74.00 Median :74.5 Median :75.5 Median :77.00 Median : 94.00
## Mean :74.00 Mean :71.2 Mean :74.9 Mean :74.90 Mean : 91.30
## 3rd Qu.:85.25 3rd Qu.:84.5 3rd Qu.:83.0 3rd Qu.:86.25 3rd Qu.: 97.50
## Max. :91.00 Max. :97.0 Max. :92.0 Max. :94.00 Max. :100.00str(dta_data)## tibble [10 × 10] (S3: tbl_df/tbl/data.frame)
## $ student_id : num [1:10] 1 2 3 4 5 6 7 8 9 10
## ..- attr(*, "label")= chr "Student ID"
## ..- attr(*, "format.stata")= chr "%12.0g"
## $ student_name : chr [1:10] "Kelvin Ardan" "Mira Solen" "Tobias Renk" "Lena Vorik" ...
## ..- attr(*, "label")= chr "Student name (random)"
## ..- attr(*, "format.stata")= chr "%12s"
## $ gender : chr [1:10] "M" "F" "M" "F" ...
## ..- attr(*, "label")= chr "Gender (M/F)"
## ..- attr(*, "format.stata")= chr "%1s"
## $ age : num [1:10] 17 16 18 17 16 17 18 16 17 18
## ..- attr(*, "label")= chr "Age in years"
## ..- attr(*, "format.stata")= chr "%12.0g"
## $ math : num [1:10] 78 88 54 92 67 73 45 81 60 95
## ..- attr(*, "label")= chr "Mathematics mark"
## ..- attr(*, "format.stata")= chr "%12.0g"
## $ english : num [1:10] 65 91 60 87 72 80 52 76 68 89
## ..- attr(*, "label")= chr "English mark"
## ..- attr(*, "format.stata")= chr "%12.0g"
## $ science : num [1:10] 72 85 48 94 61 77 40 83 55 97
## ..- attr(*, "label")= chr "Science mark"
## ..- attr(*, "format.stata")= chr "%12.0g"
## $ history : num [1:10] 80 79 66 85 70 84 58 72 63 92
## ..- attr(*, "label")= chr "History mark"
## ..- attr(*, "format.stata")= chr "%12.0g"
## $ geography : num [1:10] 69 90 58 88 75 81 49 79 66 94
## ..- attr(*, "label")= chr "Geography mark"
## ..- attr(*, "format.stata")= chr "%12.0g"
## $ attendance_pct: num [1:10] 95 98 82 100 90 93 75 96 85 99
## ..- attr(*, "label")= chr "Attendance (%)"
## ..- attr(*, "format.stata")= chr "%12.0g"names(dta_data)## [1] "student_id" "student_name" "gender" "age"
## [5] "math" "english" "science" "history"
## [9] "geography" "attendance_pct"categ_anal=table(Gender=dta_data$gender,Grade=dta_data$science)
round(prop.table(categ_anal,1)*100,1)## Grade
## Gender 40 48 55 61 72 77 83 85 94 97
## F 0 0 0 0 0 20 20 20 20 20
## M 20 20 20 20 20 0 0 0 0 0