Class Assignments of R
Eric NZABIHIMANA
2026-10-31
#———————————————————————————– # Hw1: Import data from statistical package and from Database management system
Installation of packages open the files from statistical packages
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#——————————————————————————-
Hw2: Class activities practice
Vector: The foundational R data strucure
## 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,give.attr=FALSE)## tibble [10 × 10] (S3: tbl_df/tbl/data.frame)
## $ student_id : num [1:10] 1 2 3 4 5 6 7 8 9 10
## $ student_name : chr [1:10] "Kelvin Ardan" "Mira Solen" "Tobias Renk" "Lena Vorik" ...
## $ gender : chr [1:10] "M" "F" "M" "F" ...
## $ age : num [1:10] 17 16 18 17 16 17 18 16 17 18
## $ math : num [1:10] 78 88 54 92 67 73 45 81 60 95
## $ english : num [1:10] 65 91 60 87 72 80 52 76 68 89
## $ science : num [1:10] 72 85 48 94 61 77 40 83 55 97
## $ history : num [1:10] 80 79 66 85 70 84 58 72 63 92
## $ geography : num [1:10] 69 90 58 88 75 81 49 79 66 94
## $ attendance_pct: num [1:10] 95 98 82 100 90 93 75 96 85 99names(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 0Exploratory Data Analysis using built in data in R
Examine your variables
data("women")
women## height weight
## 1 58 115
## 2 59 117
## 3 60 120
## 4 61 123
## 5 62 126
## 6 63 129
## 7 64 132
## 8 65 135
## 9 66 139
## 10 67 142
## 11 68 146
## 12 69 150
## 13 70 154
## 14 71 159
## 15 72 164names(women)## [1] "height" "weight"dim(women)## [1] 15 2Summary Statistics
# Summary Statistics
summary(women)## height weight
## Min. :58.0 Min. :115.0
## 1st Qu.:61.5 1st Qu.:124.5
## Median :65.0 Median :135.0
## Mean :65.0 Mean :136.7
## 3rd Qu.:68.5 3rd Qu.:148.0
## Max. :72.0 Max. :164.0str(women,give.attr=FALSE)## 'data.frame': 15 obs. of 2 variables:
## $ height: num 58 59 60 61 62 63 64 65 66 67 ...
## $ weight: num 115 117 120 123 126 129 132 135 139 142 ...apply(women,1,mean)## [1] 86.5 88.0 90.0 92.0 94.0 96.0 98.0 100.0 102.5 104.5 107.0 109.5
## [13] 112.0 115.0 118.0apply(women,2,sd)## height weight
## 4.472136 15.498694c(mean(women$weight),sd(women$weight))## [1] 136.73333 15.49869c(mean(women$height),sd(women$height))## [1] 65.000000 4.472136c(Mean=mean(women$height),SD=sd(women$height))## Mean SD
## 65.000000 4.472136c(Mean=mean(women$weight),SD=sd(women$weight))## Mean SD
## 136.73333 15.49869Variation & Co-variation using both Numerical & graphs
Relationship between categorical and continuous variables
data("iris")
head(iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosamean(iris$Sepal.Length)## [1] 5.843333# Mean of Petal.length by setosa category
mean(iris$Petal.Length[iris$Species=="setosa"])## [1] 1.462# Mean of Petal.length by Versicolor category
mean(iris$Petal.Length[iris$Species=="versicolor"])## [1] 4.26# Mean of Petal.length by virginica category
mean(iris$Petal.Length[iris$Species=="virginica"])## [1] 5.552# Examine the mean by Shortcut
by(iris$Petal.Length,iris$Species,mean)## iris$Species: setosa
## [1] 1.462
## ------------------------------------------------------------
## iris$Species: versicolor
## [1] 4.26
## ------------------------------------------------------------
## iris$Species: virginica
## [1] 5.552# Examine the SD by Shortcut
by(iris$Petal.Length,iris$Species,sd)## iris$Species: setosa
## [1] 0.173664
## ------------------------------------------------------------
## iris$Species: versicolor
## [1] 0.469911
## ------------------------------------------------------------
## iris$Species: virginica
## [1] 0.5518947# Examine summary by Shortcut
by(iris$Petal.Length,iris$Species,summary)## iris$Species: setosa
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 1.400 1.500 1.462 1.575 1.900
## ------------------------------------------------------------
## iris$Species: versicolor
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.00 4.00 4.35 4.26 4.60 5.10
## ------------------------------------------------------------
## iris$Species: virginica
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.500 5.100 5.550 5.552 5.875 6.900Visualize the differences in continouus variables btn categoarical using Box_and_Whisker plot
boxplot(iris$Sepal.Length~iris$Species,data = iris,main="Comparison of Categorical VS Quantitative")
## Relationship btn two categorical variables
ucba<-data.frame(UCBAdmissions)
head(ucba)## Admit Gender Dept Freq
## 1 Admitted Male A 512
## 2 Rejected Male A 313
## 3 Admitted Female A 89
## 4 Rejected Female A 19
## 5 Admitted Male B 353
## 6 Rejected Male B 207# Cross tabulation # Contigency table
(cross<-xtabs(Freq~Gender+Admit,data = ucba))## Admit
## Gender Admitted Rejected
## Male 1198 1493
## Female 557 1278# Is there gender bias in UCB graduate admission process?
prop.table(cross,1)## Admit
## Gender Admitted Rejected
## Male 0.4451877 0.5548123
## Female 0.3035422 0.6964578Simpson’s paradox
Phenomenon, where a trend that appears in combined groups of data disappears or reverses when broken down into groups.
cross2<-xtabs(Freq~Gender+Admit,data = ucba[ucba$Dept=="F",])
prop.table(cross2,1)## Admit
## Gender Admitted Rejected
## Male 0.05898123 0.94101877
## Female 0.07038123 0.92961877Bar Chart
data1<-read.table(text = "ProdA ProdB ProdC ProdD
1 110 50 60 70
2 120 50 80 65",header= TRUE)
barplot(as.matrix(data1),beside=TRUE,col=c("red","green"))
#barplot(as.matrix(data2),beside=TRUE,col=c("Gold3","red"))
data2<- read.table(text = "A B C D E F G
1 10 80 30 90 70 60 90
2 20 50 70 50 40 10 40
3 60 80 80 60 60 30 1560
4 20 40 70 80 20 10 70",header=TRUE)
barplot(as.matrix(data2))
# Scatter Plot
plot(weight~height,data = women)
plot(women$weight,women$height)
plot(women[,1],women[,2],main = "Graph")
# Linear Model
plot(weight~height,data = women)
abline(lm(weight~height,data = women)$coefficient)
data_lm<-lm(height~weight,data = women)
s<-summary(data_lm)
round(s$coefficients,5)## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 25.72346 1.04375 24.64531 0
## weight 0.28725 0.00759 37.85531 0plot(data_lm)
hist(women$height,col = "green")
hist(women$weight,col = "darkblue")
# Linear with other line
plot(weight~height,data = women)
abline(lm(weight~height,data = women)$coefficient)
lines(lowess(women$height,women$height),col="red")
cor(women$height,women$weight)## [1] 0.9954948lm(weight~height,women)##
## Call:
## lm(formula = weight ~ height, data = women)
##
## Coefficients:
## (Intercept) height
## -87.52 3.45Data Management
Create another Variable
# Convert pounds to kilogram and Inches to meters
BMI<-(women$weight*0.453592)/(women$height*0.0254)^2
round(BMI,1)## [1] 24.0 23.6 23.4 23.2 23.0 22.9 22.7 22.5 22.4 22.2 22.2 22.2 22.1 22.2 22.2# attach it to data frame and get new data frame
women$BMI <-round(703*women$weight/women$height^2,1)
head(women)## height weight BMI
## 1 58 115 24.0
## 2 59 117 23.6
## 3 60 120 23.4
## 4 61 123 23.2
## 5 62 126 23.0
## 6 63 129 22.8summary(women$BMI)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 22.10 22.20 22.50 22.71 23.10 24.00# Summary of BMI
summary(women$BMI)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 22.10 22.20 22.50 22.71 23.10 24.00stem(BMI,scale = 2)##
## The decimal point is 1 digit(s) to the left of the |
##
## 220 | 058
## 222 | 044
## 224 | 36
## 226 | 6
## 228 | 5
## 230 | 5
## 232 | 4
## 234 | 4
## 236 | 3
## 238 |
## 240 | 3Date
today<- Sys.Date()
format(today,format="%B %d %Y")## [1] "November 14 2026"format(today,format = "%A")## [1] "Saturday"today<-Sys.Date()
dob<-as.Date("1998-11-06")
#today<-as.Date()
difftime(today,dob,units = "days")## Time difference of 10235 daysstartdate<-as.Date("2022-11-01")
enddate<-as.Date("2026-11-14")
days<-enddate-startdate
days## Time difference of 1474 daysSubsetting
Creation of leadership data Interest: How men and women differ in the way they lead their organizations. 5 questions were asked in this study. Example of the question: Do men and women in management position differ in the degree to which they defer to superiors? 1: strongly disagree, 2: disagree, 3:neither agree nor disagree,4: agree, 5: strongly agree
# Use of $,[] or [[]]
manager <- c(1,2,3,4,5)
country<- c("US","US","UK","UK","UK")
gender<-c("M","F","F","M","F")
age<-c(32,45,25,39,99)
q1<-c(5,3,3,3,2)
q2<-c(4,5,5,3,2)
q3<-c(5,2,5,4,1)
q4<-c(5,5,5,NA,2)
q5<-c(5,5,2,NA,1)
leadership<-data.frame(manager,country, gender, age, q1,q2,q3,q4,q5, stringsAsFactors = TRUE)
leadership<-data.frame(manager,country, gender, age, q1,q2,q3,q4,q5)
str(leadership)## 'data.frame': 5 obs. of 9 variables:
## $ manager: num 1 2 3 4 5
## $ country: chr "US" "US" "UK" "UK" ...
## $ gender : chr "M" "F" "F" "M" ...
## $ age : num 32 45 25 39 99
## $ q1 : num 5 3 3 3 2
## $ q2 : num 4 5 5 3 2
## $ q3 : num 5 2 5 4 1
## $ q4 : num 5 5 5 NA 2
## $ q5 : num 5 5 2 NA 1names(leadership)## [1] "manager" "country" "gender" "age" "q1" "q2" "q3"
## [8] "q4" "q5"Missing Value
leadership$age[leadership$age==99]<-NA
View(leadership)leadership$agecat[leadership$age>75]<-"Elder"
leadership$agecat[leadership$age>=5 & leadership$age<=75]<-"Middle aged"
leadership$agecat[leadership$age<35]<-"Young"One way of handling missing value
Deleting all observations with missing data ( Listwise deletion) is one of the several methods of handling incomplete datasets. Note: You can also replacing the missing value by the average of the remaining data.
is.na(leadership[,5:9])## q1 q2 q3 q4 q5
## [1,] FALSE FALSE FALSE FALSE FALSE
## [2,] FALSE FALSE FALSE FALSE FALSE
## [3,] FALSE FALSE FALSE FALSE FALSE
## [4,] FALSE FALSE FALSE TRUE TRUE
## [5,] FALSE FALSE FALSE FALSE FALSEnew_leadersh<-na.omit(leadership)
new_leadersh## manager country gender age q1 q2 q3 q4 q5 agecat
## 1 1 US M 32 5 4 5 5 5 Young
## 2 2 US F 45 3 5 2 5 5 Middle aged
## 3 3 UK F 25 3 5 5 5 2 YoungSorting Data
order(leadership$age)## [1] 3 1 4 2 5new_leadersh2<-leadership[order(leadership$age)]merging Data-sets
To merge two data frame horizontally, you use merge() function. In most cases, two data frames are joined by one or more common key variables. -example 1: merge(dataframeA, dataframeB,by=“ID”) -example 2: merge(dataframeA,dataframeB, by=c(“ID”,“country”))
the second merge the two dataframes by ID and country
To join two data frame( datasets) vertically, use rbind() function: Note that the two data set must have the same variables
Subset (selecting variables,dropping variables,selecting observation )
(new_ledersh3<-leadership[,c(5:9)])## q1 q2 q3 q4 q5
## 1 5 4 5 5 5
## 2 3 5 2 5 5
## 3 3 5 5 5 2
## 4 3 3 4 NA NA
## 5 2 2 1 2 1new_leadersh4<-leadership[,c(-1,-2)]
(new_leadersh4<-leadership[,-(1:5)])## q2 q3 q4 q5 agecat
## 1 4 5 5 5 Young
## 2 5 2 5 5 Middle aged
## 3 5 5 5 2 Young
## 4 3 4 NA NA Middle aged
## 5 2 1 2 1 <NA>new_leadersh5<-leadership[,c(-1,-7)]
leadership[[4]]## [1] 32 45 25 39 NAnew_leadersh6<-leadership[c(-1,-3),]
new_leadersh6<-leadership[c(2,4,5),]
new_leadersh7<-subset(leadership,age>=35|age<24,select=c(q1,q2,q3,q4,q5))attach(leadership)## The following objects are masked _by_ .GlobalEnv:
##
## age, country, gender, manager, q1, q2, q3, q4, q5(new_leadersh7<-leadership[gender=="M" & age>30,])## manager country gender age q1 q2 q3 q4 q5 agecat
## 1 1 US M 32 5 4 5 5 5 Young
## 4 4 UK M 39 3 3 4 NA NA Middle aged