Tugas
2025-11-12
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(corrplot)## Warning: package 'corrplot' was built under R version 4.5.2## corrplot 0.95 loadedlibrary(ggplot2)setwd("C:/UNNES/Semester 1/Pengantar Sains Data/Latihan R")student <- read.csv("student-mat.csv", sep = ";", header = TRUE)
student$G3 <- as.numeric(student$G3)str(student)## 'data.frame': 395 obs. of 33 variables:
## $ school : chr "GP" "GP" "GP" "GP" ...
## $ sex : chr "F" "F" "F" "F" ...
## $ age : int 18 17 15 15 16 16 16 17 15 15 ...
## $ address : chr "U" "U" "U" "U" ...
## $ famsize : chr "GT3" "GT3" "LE3" "GT3" ...
## $ Pstatus : chr "A" "T" "T" "T" ...
## $ Medu : int 4 1 1 4 3 4 2 4 3 3 ...
## $ Fedu : int 4 1 1 2 3 3 2 4 2 4 ...
## $ Mjob : chr "at_home" "at_home" "at_home" "health" ...
## $ Fjob : chr "teacher" "other" "other" "services" ...
## $ reason : chr "course" "course" "other" "home" ...
## $ guardian : chr "mother" "father" "mother" "mother" ...
## $ traveltime: int 2 1 1 1 1 1 1 2 1 1 ...
## $ studytime : int 2 2 2 3 2 2 2 2 2 2 ...
## $ failures : int 0 0 3 0 0 0 0 0 0 0 ...
## $ schoolsup : chr "yes" "no" "yes" "no" ...
## $ famsup : chr "no" "yes" "no" "yes" ...
## $ paid : chr "no" "no" "yes" "yes" ...
## $ activities: chr "no" "no" "no" "yes" ...
## $ nursery : chr "yes" "no" "yes" "yes" ...
## $ higher : chr "yes" "yes" "yes" "yes" ...
## $ internet : chr "no" "yes" "yes" "yes" ...
## $ romantic : chr "no" "no" "no" "yes" ...
## $ famrel : int 4 5 4 3 4 5 4 4 4 5 ...
## $ freetime : int 3 3 3 2 3 4 4 1 2 5 ...
## $ goout : int 4 3 2 2 2 2 4 4 2 1 ...
## $ Dalc : int 1 1 2 1 1 1 1 1 1 1 ...
## $ Walc : int 1 1 3 1 2 2 1 1 1 1 ...
## $ health : int 3 3 3 5 5 5 3 1 1 5 ...
## $ absences : int 6 4 10 2 4 10 0 6 0 0 ...
## $ G1 : int 5 5 7 15 6 15 12 6 16 14 ...
## $ G2 : int 6 5 8 14 10 15 12 5 18 15 ...
## $ G3 : num 6 6 10 15 10 15 11 6 19 15 ...head(student)## school sex age address famsize Pstatus Medu Fedu Mjob Fjob reason
## 1 GP F 18 U GT3 A 4 4 at_home teacher course
## 2 GP F 17 U GT3 T 1 1 at_home other course
## 3 GP F 15 U LE3 T 1 1 at_home other other
## 4 GP F 15 U GT3 T 4 2 health services home
## 5 GP F 16 U GT3 T 3 3 other other home
## 6 GP M 16 U LE3 T 4 3 services other reputation
## guardian traveltime studytime failures schoolsup famsup paid activities
## 1 mother 2 2 0 yes no no no
## 2 father 1 2 0 no yes no no
## 3 mother 1 2 3 yes no yes no
## 4 mother 1 3 0 no yes yes yes
## 5 father 1 2 0 no yes yes no
## 6 mother 1 2 0 no yes yes yes
## nursery higher internet romantic famrel freetime goout Dalc Walc health
## 1 yes yes no no 4 3 4 1 1 3
## 2 no yes yes no 5 3 3 1 1 3
## 3 yes yes yes no 4 3 2 2 3 3
## 4 yes yes yes yes 3 2 2 1 1 5
## 5 yes yes no no 4 3 2 1 2 5
## 6 yes yes yes no 5 4 2 1 2 5
## absences G1 G2 G3
## 1 6 5 6 6
## 2 4 5 5 6
## 3 10 7 8 10
## 4 2 15 14 15
## 5 4 6 10 10
## 6 10 15 15 15summary(student)## school sex age address
## Length:395 Length:395 Min. :15.0 Length:395
## Class :character Class :character 1st Qu.:16.0 Class :character
## Mode :character Mode :character Median :17.0 Mode :character
## Mean :16.7
## 3rd Qu.:18.0
## Max. :22.0
## famsize Pstatus Medu Fedu
## Length:395 Length:395 Min. :0.000 Min. :0.000
## Class :character Class :character 1st Qu.:2.000 1st Qu.:2.000
## Mode :character Mode :character Median :3.000 Median :2.000
## Mean :2.749 Mean :2.522
## 3rd Qu.:4.000 3rd Qu.:3.000
## Max. :4.000 Max. :4.000
## Mjob Fjob reason guardian
## Length:395 Length:395 Length:395 Length:395
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## traveltime studytime failures schoolsup
## Min. :1.000 Min. :1.000 Min. :0.0000 Length:395
## 1st Qu.:1.000 1st Qu.:1.000 1st Qu.:0.0000 Class :character
## Median :1.000 Median :2.000 Median :0.0000 Mode :character
## Mean :1.448 Mean :2.035 Mean :0.3342
## 3rd Qu.:2.000 3rd Qu.:2.000 3rd Qu.:0.0000
## Max. :4.000 Max. :4.000 Max. :3.0000
## famsup paid activities nursery
## Length:395 Length:395 Length:395 Length:395
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## higher internet romantic famrel
## Length:395 Length:395 Length:395 Min. :1.000
## Class :character Class :character Class :character 1st Qu.:4.000
## Mode :character Mode :character Mode :character Median :4.000
## Mean :3.944
## 3rd Qu.:5.000
## Max. :5.000
## freetime goout Dalc Walc
## Min. :1.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:3.000 1st Qu.:2.000 1st Qu.:1.000 1st Qu.:1.000
## Median :3.000 Median :3.000 Median :1.000 Median :2.000
## Mean :3.235 Mean :3.109 Mean :1.481 Mean :2.291
## 3rd Qu.:4.000 3rd Qu.:4.000 3rd Qu.:2.000 3rd Qu.:3.000
## Max. :5.000 Max. :5.000 Max. :5.000 Max. :5.000
## health absences G1 G2
## Min. :1.000 Min. : 0.000 Min. : 3.00 Min. : 0.00
## 1st Qu.:3.000 1st Qu.: 0.000 1st Qu.: 8.00 1st Qu.: 9.00
## Median :4.000 Median : 4.000 Median :11.00 Median :11.00
## Mean :3.554 Mean : 5.709 Mean :10.91 Mean :10.71
## 3rd Qu.:5.000 3rd Qu.: 8.000 3rd Qu.:13.00 3rd Qu.:13.00
## Max. :5.000 Max. :75.000 Max. :19.00 Max. :19.00
## G3
## Min. : 0.00
## 1st Qu.: 8.00
## Median :11.00
## Mean :10.42
## 3rd Qu.:14.00
## Max. :20.00colSums(is.na(student))## school sex age address famsize Pstatus Medu
## 0 0 0 0 0 0 0
## Fedu Mjob Fjob reason guardian traveltime studytime
## 0 0 0 0 0 0 0
## failures schoolsup famsup paid activities nursery higher
## 0 0 0 0 0 0 0
## internet romantic famrel freetime goout Dalc Walc
## 0 0 0 0 0 0 0
## health absences G1 G2 G3
## 0 0 0 0 0sum(duplicated(student))## [1] 0- Analisis Karakteristik Siswa, Untuk menganalisis komposisi siswa, kita menggunakan bar plot frekuensi.
# Komposisi Jenis Kelamin (sex)
ggplot(student, aes(x = sex, fill = sex)) +
geom_bar() +
labs(title = "Komposisi Siswa Berdasarkan Jenis Kelamin", x = "Jenis Kelamin (F=Wanita, M=Pria)", y = "Jumlah Siswa") +
theme_minimal()
# Komposisi Tempat Tinggal (address)
ggplot(student, aes(x = address, fill = address)) +
geom_bar() +
labs(title = "Komposisi Siswa Berdasarkan Tempat Tinggal", x = "Tempat Tinggal (U=Urban, R=Rural)", y = "Jumlah Siswa") +
theme_minimal()
# Komposisi Waktu Belajar (studytime)
ggplot(student, aes(x = factor(studytime), fill = factor(studytime))) +
geom_bar() +
labs(title = "Komposisi Siswa Berdasarkan Waktu Belajar",
x = "Waktu Belajar (1: <2j, 2: 2-5j, 3: 5-10j, 4: >10j)", y = "Jumlah Siswa") +
scale_fill_discrete(name = "Waktu Belajar") +
theme_minimal()
Persebaran Nilai Akhir (G3) dan Outlier
# Distribusi Nilai Akhir (G3)
hist(student$G3,
main = "Distribusi Nilai Akhir (G3)",
xlab = "Nilai Akhir",
col = "lightblue",
border = "black")
# Pengecekan Outlier pada Absences
boxplot(student$absences,
main = "Pengecekan Outlier pada Absences",
ylab = "Jumlah Ketidakhadiran",
col = "lightcoral")
summary(student$G3)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 8.00 11.00 10.42 14.00 20.00- Analisis Nilai Akademik Siswa, Tujuan utama adalah menguji pengaruh G1 dan G2 terhadap G3. Korelasi dan visualisasi scatter plot digunakan untuk eksplorasi, diikuti dengan model regresi untuk mengukur pengaruh.
Korelasi dan Hubungan G1, G2 dengan G3
# Korelasi G1 dan G3
cor_G1_G3 <- cor(student$G1, student$G3)
print(paste("Korelasi G1 dan G3:", round(cor_G1_G3, 3)))## [1] "Korelasi G1 dan G3: 0.801"# Korelasi G2 dan G3
cor_G2_G3 <- cor(student$G2, student$G3)
print(paste("Korelasi G2 dan G3:", round(cor_G2_G3, 3)))## [1] "Korelasi G2 dan G3: 0.905"# Hubungan G1 dengan G3
plot(student$G1, student$G3,
main="Hubungan G1 dengan G3",
xlab="Nilai G1", ylab="Nilai G3",
pch=19, col="darkorange")
# Hubungan G2 dengan G3
plot(student$G2, student$G3,
main="Hubungan G2 dengan G3",
xlab="Nilai G2", ylab="Nilai G3",
pch=19, col="blue")
Pengaruh G1 dan G2 terhadap G3
# Menguji pengaruh G1 dan G2 menggunakan Regresi Linear
model_akademik <- lm(G3 ~ G1 + G2, data = student)
summary(model_akademik)##
## Call:
## lm(formula = G3 ~ G1 + G2, data = student)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.5713 -0.3888 0.2885 0.9725 3.7089
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.83001 0.33531 -5.458 8.57e-08 ***
## G1 0.15327 0.05618 2.728 0.00665 **
## G2 0.98687 0.04957 19.909 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.937 on 392 degrees of freedom
## Multiple R-squared: 0.8222, Adjusted R-squared: 0.8213
## F-statistic: 906.1 on 2 and 392 DF, p-value: < 2.2e-16Korelasi dan Hubungan G1, G2 dengan G3
# Korelasi G1 dan G3
cor_G1_G3 <- cor(student$G1, student$G3)
print(paste("Korelasi G1 dan G3:", round(cor_G1_G3, 3)))## [1] "Korelasi G1 dan G3: 0.801"# Korelasi G2 dan G3
cor_G2_G3 <- cor(student$G2, student$G3)
print(paste("Korelasi G2 dan G3:", round(cor_G2_G3, 3)))## [1] "Korelasi G2 dan G3: 0.905"# Hubungan G1 dengan G3
plot(student$G1, student$G3,
main="Hubungan G1 dengan G3",
xlab="Nilai G1", ylab="Nilai G3",
pch=19, col="darkorange")
# Hubungan G2 dengan G3
plot(student$G2, student$G3,
main="Hubungan G2 dengan G3",
xlab="Nilai G2", ylab="Nilai G3",
pch=19, col="blue")
Pengaruh G1 dan G2 terhadap G3
# Menguji pengaruh G1 dan G2 menggunakan Regresi Linear
model_akademik <- lm(G3 ~ G1 + G2, data = student)
summary(model_akademik)##
## Call:
## lm(formula = G3 ~ G1 + G2, data = student)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.5713 -0.3888 0.2885 0.9725 3.7089
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.83001 0.33531 -5.458 8.57e-08 ***
## G1 0.15327 0.05618 2.728 0.00665 **
## G2 0.98687 0.04957 19.909 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.937 on 392 degrees of freedom
## Multiple R-squared: 0.8222, Adjusted R-squared: 0.8213
## F-statistic: 906.1 on 2 and 392 DF, p-value: < 2.2e-16- Analisis Pengaruh Faktor Non-Akademik, Pengaruh Absences dan Jenis Kelamin
# Hubungan Absences dengan G3
cor_absences_G3 <- cor(student$absences, student$G3)
print(paste("Korelasi Absences dan G3:", round(cor_absences_G3, 3)))## [1] "Korelasi Absences dan G3: 0.034"plot(student$absences, student$G3,
main="Hubungan Absences dengan Nilai Akhir (G3)",
xlab="Jumlah Ketidakhadiran", ylab="Nilai G3",
pch=19, col="darkgreen")
# Perbedaan G3 berdasarkan Jenis Kelamin
boxplot(G3 ~ sex, data = student,
main="G3 Berdasarkan Jenis Kelamin",
xlab="Jenis Kelamin", ylab="Nilai Akhir",
col=c("pink","lightblue"))
Pengaruh Waktu Belajar (Studytime)
# Rata-rata G3 per Waktu Belajar
avg_study <- student %>%
group_by(studytime) %>%
summarise(mean_G3 = mean(G3), .groups = 'drop')
barplot(avg_study$mean_G3, names.arg = avg_study$studytime,
main="Rata-rata G3 per Waktu Belajar",
xlab="Waktu Belajar (1-4)", ylab="Rata-rata G3",
col="skyblue")
# Analisis Lanjutan: Rata-rata G3 berdasarkan Waktu Belajar dan Jenis Kelamin
avg_study_sex <- student %>%
group_by(studytime, sex) %>%
summarise(mean_G3 = mean(G3), .groups = 'drop')
ggplot(avg_study_sex, aes(x = factor(studytime), y = mean_G3, fill = sex)) +
geom_bar(stat = "identity", position = position_dodge()) +
labs(title = "Rata-rata G3 Berdasarkan Waktu Belajar dan Jenis Kelamin",
x = "Waktu Belajar (1-4)", y = "Rata-rata Nilai G3") +
scale_fill_manual(values = c("F" = "pink", "M" = "lightblue")) +
theme_minimal()
- Analisis Korelasi Seluruh Variabel Numerik Tujuan untuk mengidentifikasi variabel numerik mana yang paling kuat hubungannya dengan G3.
# Pilih variabel numerik secara eksplisit untuk keamanan
num_cols <- c("age", "Medu", "Fedu", "traveltime", "studytime",
"failures", "famrel", "freetime", "goout", "Dalc",
"Walc", "health", "absences", "G1", "G2", "G3")# Ambil data numerik
num_data_clean <- student %>%
select(all_of(num_cols)) %>%
mutate(across(everything(), as.numeric))# Hitung Matriks Korelasi
cor_matrix <- cor(num_data_clean)# 4. Visualisasi Korelasi
corrplot(cor_matrix,
method="color",
type="upper",
tl.col="black",
tl.srt=45,
addCoef.col = "black",
diag = FALSE)