TUGAS INDIVIDU AED
G1401231008_Shafi Faris Arif Rabbani
2025-03-15
IMPORT DATA
library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.3.3library(dplyr)## Warning: package 'dplyr' was built under R version 4.3.3##
## 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 4.3.3## corrplot 0.95 loadedlibrary(reshape2)## Warning: package 'reshape2' was built under R version 4.3.3library(patchwork)## Warning: package 'patchwork' was built under R version 4.3.3library(psych)## Warning: package 'psych' was built under R version 4.3.3##
## Attaching package: 'psych'## The following objects are masked from 'package:ggplot2':
##
## %+%, alphaMembaca Data
data_kaggle <- read.csv("C:/Users/M S I/Downloads/Students_Grading_Dataset (1).csv")
head(data_kaggle)## Student_ID First_Name Last_Name Email Gender Age
## 1 S1000 Omar Williams student0@university.com Female 22
## 2 S1001 Maria Brown student1@university.com Male 18
## 3 S1002 Ahmed Jones student2@university.com Male 24
## 4 S1003 Omar Williams student3@university.com Female 24
## 5 S1004 John Smith student4@university.com Female 23
## 6 S1005 Liam Brown student5@university.com Male 21
## Department Attendance.... Midterm_Score Final_Score Assignments_Avg
## 1 Engineering 52.29 55.03 57.82 84.22
## 2 Engineering 97.27 97.23 45.80 NA
## 3 Business 57.19 67.05 93.68 67.70
## 4 Mathematics 95.15 47.79 80.63 66.06
## 5 CS 54.18 46.59 78.89 96.85
## 6 Engineering NA 78.85 43.53 71.40
## Quizzes_Avg Participation_Score Projects_Score Total_Score Grade
## 1 74.06 3.99 85.90 56.09 F
## 2 94.24 8.32 55.65 50.64 A
## 3 85.70 5.05 73.79 70.30 D
## 4 93.51 6.54 92.12 61.63 A
## 5 83.70 5.97 68.42 66.13 F
## 6 52.20 6.38 67.29 62.08 B
## Study_Hours_per_Week Extracurricular_Activities Internet_Access_at_Home
## 1 6.2 No Yes
## 2 19.0 No Yes
## 3 20.7 No Yes
## 4 24.8 Yes Yes
## 5 15.4 Yes Yes
## 6 8.5 Yes Yes
## Parent_Education_Level Family_Income_Level Stress_Level..1.10.
## 1 High School Medium 5
## 2 None Medium 4
## 3 Master's Low 6
## 4 High School High 3
## 5 High School High 2
## 6 PhD High 1
## Sleep_Hours_per_Night
## 1 4.7
## 2 9.0
## 3 6.2
## 4 6.7
## 5 7.1
## 6 5.0# rename variabel
data_kaggle <- data_kaggle %>%
rename(
Attendance = Attendance....,
Study_Hours = Study_Hours_per_Week,
Stress_Level= Stress_Level..1.10.,
Sleep_Hours = Sleep_Hours_per_Night,
Internet = Internet_Access_at_Home,
Parent_Education = Parent_Education_Level
)
colnames(data_kaggle)## [1] "Student_ID" "First_Name"
## [3] "Last_Name" "Email"
## [5] "Gender" "Age"
## [7] "Department" "Attendance"
## [9] "Midterm_Score" "Final_Score"
## [11] "Assignments_Avg" "Quizzes_Avg"
## [13] "Participation_Score" "Projects_Score"
## [15] "Total_Score" "Grade"
## [17] "Study_Hours" "Extracurricular_Activities"
## [19] "Internet" "Parent_Education"
## [21] "Family_Income_Level" "Stress_Level"
## [23] "Sleep_Hours"write.csv(data_kaggle, "data_kaggle_clean.csv", row.names = FALSE)MEMBACA TOTAL BARIS DAN KOLOM
dim(data_kaggle)## [1] 5000 23summary(data_kaggle)## Student_ID First_Name Last_Name Email
## Length:5000 Length:5000 Length:5000 Length:5000
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
##
## Gender Age Department Attendance
## Length:5000 Min. :18.00 Length:5000 Min. : 50.01
## Class :character 1st Qu.:19.00 Class :character 1st Qu.: 63.27
## Mode :character Median :21.00 Mode :character Median : 75.72
## Mean :21.05 Mean : 75.43
## 3rd Qu.:23.00 3rd Qu.: 87.47
## Max. :24.00 Max. :100.00
## NA's :516
## Midterm_Score Final_Score Assignments_Avg Quizzes_Avg
## Min. :40.00 Min. :40.00 Min. :50.00 Min. :50.03
## 1st Qu.:55.46 1st Qu.:54.67 1st Qu.:62.09 1st Qu.:62.49
## Median :70.51 Median :69.73 Median :74.81 Median :74.69
## Mean :70.33 Mean :69.64 Mean :74.80 Mean :74.91
## 3rd Qu.:84.97 3rd Qu.:84.50 3rd Qu.:86.97 3rd Qu.:87.63
## Max. :99.98 Max. :99.98 Max. :99.98 Max. :99.96
## NA's :517
## Participation_Score Projects_Score Total_Score Grade
## Min. : 0.000 Min. : 50.01 Min. :50.02 Length:5000
## 1st Qu.: 2.440 1st Qu.: 62.32 1st Qu.:62.84 Class :character
## Median : 4.955 Median : 74.98 Median :75.39 Mode :character
## Mean : 4.980 Mean : 74.92 Mean :75.12
## 3rd Qu.: 7.500 3rd Qu.: 87.37 3rd Qu.:87.65
## Max. :10.000 Max. :100.00 Max. :99.99
##
## Study_Hours Extracurricular_Activities Internet
## Min. : 5.00 Length:5000 Length:5000
## 1st Qu.:11.40 Class :character Class :character
## Median :17.50 Mode :character Mode :character
## Mean :17.66
## 3rd Qu.:24.10
## Max. :30.00
##
## Parent_Education Family_Income_Level Stress_Level Sleep_Hours
## Length:5000 Length:5000 Min. : 1.000 Min. :4.000
## Class :character Class :character 1st Qu.: 3.000 1st Qu.:5.200
## Mode :character Mode :character Median : 5.000 Median :6.500
## Mean : 5.481 Mean :6.488
## 3rd Qu.: 8.000 3rd Qu.:7.700
## Max. :10.000 Max. :9.000
## Menampilkan jumlah missing value pada tiap kolom sebelum penggantian
cat("Jumlah missing value sebelum penggantian:\n")## Jumlah missing value sebelum penggantian:print(sapply(data_kaggle, function(x) sum(is.na(x))))## Student_ID First_Name
## 0 0
## Last_Name Email
## 0 0
## Gender Age
## 0 0
## Department Attendance
## 0 516
## Midterm_Score Final_Score
## 0 0
## Assignments_Avg Quizzes_Avg
## 517 0
## Participation_Score Projects_Score
## 0 0
## Total_Score Grade
## 0 0
## Study_Hours Extracurricular_Activities
## 0 0
## Internet Parent_Education
## 0 0
## Family_Income_Level Stress_Level
## 0 0
## Sleep_Hours
## 0(colSums(is.na(data_kaggle)) / nrow(data_kaggle)) * 100## Student_ID First_Name
## 0.00 0.00
## Last_Name Email
## 0.00 0.00
## Gender Age
## 0.00 0.00
## Department Attendance
## 0.00 10.32
## Midterm_Score Final_Score
## 0.00 0.00
## Assignments_Avg Quizzes_Avg
## 10.34 0.00
## Participation_Score Projects_Score
## 0.00 0.00
## Total_Score Grade
## 0.00 0.00
## Study_Hours Extracurricular_Activities
## 0.00 0.00
## Internet Parent_Education
## 0.00 0.00
## Family_Income_Level Stress_Level
## 0.00 0.00
## Sleep_Hours
## 0.00describe(data_kaggle)## vars n mean sd median trimmed mad
## Student_ID* 1 5000 2500.50 1443.52 2500.50 2500.50 1853.25
## First_Name* 2 5000 4.46 2.30 4.00 4.45 2.97
## Last_Name* 3 5000 3.49 1.69 3.00 3.48 1.48
## Email* 4 5000 2500.50 1443.52 2500.50 2500.50 1853.25
## Gender* 5 5000 1.51 0.50 2.00 1.51 0.00
## Age 6 5000 21.05 1.99 21.00 21.06 2.97
## Department* 7 5000 2.29 0.90 2.00 2.24 1.48
## Attendance 8 4484 75.43 14.37 75.72 75.50 17.87
## Midterm_Score 9 5000 70.33 17.21 70.51 70.38 21.90
## Final_Score 10 5000 69.64 17.24 69.74 69.58 22.16
## Assignments_Avg 11 4483 74.80 14.41 74.81 74.76 18.47
## Quizzes_Avg 12 5000 74.91 14.50 74.69 74.89 18.67
## Participation_Score 13 5000 4.98 2.89 4.96 4.97 3.76
## Projects_Score 14 5000 74.92 14.42 74.98 74.93 18.58
## Total_Score 15 5000 75.12 14.40 75.40 75.16 18.41
## Grade* 16 5000 2.72 1.47 3.00 2.65 1.48
## Study_Hours 17 5000 17.66 7.28 17.50 17.67 9.34
## Extracurricular_Activities* 18 5000 1.30 0.46 1.00 1.25 0.00
## Internet* 19 5000 1.90 0.30 2.00 2.00 0.00
## Parent_Education* 20 5000 3.42 1.75 3.00 3.40 2.97
## Family_Income_Level* 21 5000 2.19 0.75 2.00 2.23 1.48
## Stress_Level 22 5000 5.48 2.86 5.00 5.48 2.97
## Sleep_Hours 23 5000 6.49 1.45 6.50 6.49 1.93
## min max range skew kurtosis se
## Student_ID* 1.00 5000.00 4999.00 0.00 -1.20 20.41
## First_Name* 1.00 8.00 7.00 0.02 -1.25 0.03
## Last_Name* 1.00 6.00 5.00 0.01 -1.25 0.02
## Email* 1.00 5000.00 4999.00 0.00 -1.20 20.41
## Gender* 1.00 2.00 1.00 -0.04 -2.00 0.01
## Age 18.00 24.00 6.00 -0.04 -1.24 0.03
## Department* 1.00 4.00 3.00 0.22 -0.73 0.01
## Attendance 50.01 100.00 49.99 -0.04 -1.17 0.21
## Midterm_Score 40.00 99.98 59.98 -0.02 -1.18 0.24
## Final_Score 40.00 99.98 59.98 0.02 -1.20 0.24
## Assignments_Avg 50.00 99.98 49.98 0.02 -1.20 0.22
## Quizzes_Avg 50.03 99.96 49.93 0.02 -1.20 0.21
## Participation_Score 0.00 10.00 10.00 0.01 -1.21 0.04
## Projects_Score 50.01 100.00 49.99 0.00 -1.21 0.20
## Total_Score 50.02 99.99 49.97 -0.02 -1.19 0.20
## Grade* 1.00 5.00 4.00 0.24 -1.36 0.02
## Study_Hours 5.00 30.00 25.00 0.00 -1.22 0.10
## Extracurricular_Activities* 1.00 2.00 1.00 0.87 -1.25 0.01
## Internet* 1.00 2.00 1.00 -2.61 4.82 0.00
## Parent_Education* 1.00 6.00 5.00 0.05 -1.32 0.02
## Family_Income_Level* 1.00 3.00 2.00 -0.32 -1.19 0.01
## Stress_Level 1.00 10.00 9.00 0.01 -1.22 0.04
## Sleep_Hours 4.00 9.00 5.00 0.00 -1.20 0.02sum(duplicated(data_kaggle))## [1] 0# Mengisi NA pada kolom numerik dengan nilai rata-rata
data_kaggle$Assignments_Avg[is.na(data_kaggle$Assignments_Avg)] <- mean(data_kaggle$Assignments_Avg, na.rm = TRUE)
data_kaggle$Attendance[is.na(data_kaggle$Attendance)] <- mean(data_kaggle$Attendance, na.rm = TRUE)
# Definisikan fungsi untuk mencari modus
get_mode <- function(v) {
uniqv <- unique(v)
uniqv[which.max(tabulate(match(v, uniqv)))]
}# Mengisi NA pada kolom kategorikal dengan modus
data_kaggle$Parent_Education_Level[is.na(data_kaggle$Parent_Education_Level)] <- get_mode(data_kaggle$Parent_Education_Level)# 1. Tentukan kolom yang akan digunakan untuk menghitung korelasi
correlation_columns <- c("Assignments_Avg", "Total_Score", "Midterm_Score", "Final_Score", "Quizzes_Avg", "Projects_Score")
# 2. Hitung matriks korelasi; gunakan 'use = "complete.obs"' untuk mengabaikan NA
corr_matrix <- cor(data_kaggle[, correlation_columns], use = "complete.obs")
# 3. Ubah matriks korelasi menjadi format 'long' agar bisa dipetakan oleh ggplot2
melted_corr <- melt(corr_matrix)
# 4. Plot heatmap menggunakan ggplot2
ggplot(data = melted_corr, aes(x = Var1, y = Var2, fill = value)) +
geom_tile(color = "black", size = 0.5) +
geom_text(aes(label = sprintf("%.2f", value)), color = "black", size = 4) +
scale_fill_gradient2(
low = "#F0E5FF",
mid = "#B19CD9",
high = "#4B0082",
midpoint = 0,
limits = c(-1, 1)
) +
ggtitle("Correlation Heatmap: Attendance, Scores, and Study Habits") +
theme_minimal() +
theme(
axis.text.x = element_text(angle = 45, hjust = 1, size = 12, color = "black"),
axis.text.y = element_text(size = 12, color = "black"),
plot.title = element_text(size = 14, face = "bold", color = "purple")
)## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
df_gender <- as.data.frame(table(data_kaggle$Gender))
colnames(df_gender) <- c("Gender", "Count")# Hitung persentase
df_gender$Percentage <- df_gender$Count / sum(df_gender$Count) * 100
color_map <- c("#9E93E8", "#D8BFD8")
ggplot(df_gender, aes(x = 2, y = Count, fill = Gender)) +
geom_bar(stat = "identity", color = "#FDF7F4", alpha = 0.8, width = 1) +
coord_polar("y", start = pi/2) +
xlim(0.5, 2.5) +
theme_void() +
theme(
legend.position = "left",
plot.title = element_text(hjust = 0.5, size = 14, face = "bold", color = "purple")
) +
geom_text(aes(label = paste0(round(Percentage, 2), "%")),
position = position_stack(vjust = 0.5), size = 5, color = "black") +
scale_fill_manual(values = color_map) +
ggtitle("Gender")
ggplot(data_kaggle, aes(x = Sleep_Hours, y = Total_Score, color = Grade)) +
geom_point() +
geom_smooth(method = "lm", formula = y ~ x + I(x^2), se = FALSE) +
labs(
title = "Polynomial Regression: Sleep Hours vs Total_Score",
x = "Sleep Hours per Night",
y = "Total Score"
) +
theme_minimal(base_size = 12) +
theme(
plot.title = element_text(size = 14, face = "bold", color = "purple"),
legend.position = "right"
)
Mengidentifikasi departemen tempat siswa lebih sering memperoleh nilai lebih tinggi.
Beberapa siswa mungkin belajar dalam waktu lama tetapi memperoleh nilai rendah karena teknik belajar yang tidak efektif atau stres. Mari kita analisis efisiensi belajar lintas jenis kelamin.
data_kaggle$Gender <- as.factor(data_kaggle$Gender)
data_kaggle$Department <- as.factor(data_kaggle$Department)
data_kaggle$Grade <- as.factor(data_kaggle$Grade)data_kaggle$Grade <- factor(data_kaggle$Grade, levels = c("A", "B", "C", "D", "F"))ggplot(data_kaggle, aes(x = Department, fill = Grade)) +
geom_bar(position = "stack") +
facet_wrap(~ Gender) +
labs(
title = "Grade Distribution by Gender and Department",
x = "Department",
y = "Number of Students"
) + scale_fill_brewer(palette = "RdPu") +
theme_minimal(base_size = 12) +
theme(
plot.title = element_text(hjust = 0.5, size = 14, face = "bold", color = "purple"),
legend.position = "top"
)
h_ts <- ggplot(data = data_kaggle, aes(x = Total_Score)) +
geom_histogram(aes(y = after_stat(density)),
bins = nclass.Sturges(data_kaggle$Total_Score),
fill = "pink", color = "black", alpha = 0.7) +
geom_density(color = "red", linewidth = 1.2) +
labs(title = "Total Score", x = "Total Score", y = "Density") +
theme_minimal()
# 2. Boxplot
bp_ts <- ggplot(data_kaggle, aes(y = Total_Score)) +
geom_boxplot(fill = "green", color = "black") +
labs(title = "Total Score", y = "Total Score") +
theme_minimal()
# 3. QQ Plot (untuk memeriksa normalitas)
qq_ts <- ggplot(data_kaggle, aes(sample = Total_Score)) +
stat_qq() +
stat_qq_line(color = "red", linewidth = 1) +
labs(title = "Normal Q-Q Plot",
x = "Theoretical Quantiles",
y = "Sample Quantiles") +
theme_minimal()
(h_ts | bp_ts) / qq_ts
Melakukan uji ANOVA satu arah
anova_result <- aov(Total_Score ~ Parent_Education, data = data_kaggle)
anova_summary <- summary(anova_result)
p_value <- anova_summary[[1]][["Pr(>F)"]][1]
cat(sprintf("ANOVA p-value: %.4f\n", p_value))## ANOVA p-value: 0.9189if (p_value < 0.05) {
cat("Parent education level significantly affects student performance!\n")
} else {
cat("No significant effect of parent education level on student performance.\n")
}## No significant effect of parent education level on student performance.Address Stress and Sleep Deficiency
# 1. Membuat variabel baru untuk Sleep Deficiency
data_kaggle$Sleep_Deficiency <- ifelse(data_kaggle$Sleep_Hours < 7, "Tidak Cukup", "Cukup")
data_kaggle$Sleep_Deficiency <- factor(data_kaggle$Sleep_Deficiency, levels = c("Cukup", "Tidak Cukup"))
# 2. Boxplot Total_Score berdasarkan Sleep_Deficiency
p1 <- ggplot(data_kaggle, aes(x = Sleep_Deficiency, y = Total_Score, fill = Sleep_Deficiency)) +
geom_boxplot() +
labs(title = "Student Performance by Sleep Deficiency",
x = "Sleep Category",
y = "Total Score") +
theme_minimal() +
scale_fill_manual(values = c("Cukup" = "green", "Tidak Cukup" = "red"))
# 3. Uji statistik (t-test) untuk membandingkan Total_Score antara kelompok tidur yang cukup dan tidak cukup
t_test_result <- t.test(Total_Score ~ Sleep_Deficiency, data = data_kaggle)
cat(sprintf("T-test p-value: %.4f\n", t_test_result$p.value))## T-test p-value: 0.7710if(t_test_result$p.value < 0.05) {
cat("Terdapat perbedaan signifikan pada Total Score antara kelompok Cukup dan Tidak Cukup.\n")
} else {
cat("Tidak terdapat perbedaan signifikan pada Total Score antara kedua kelompok.\n")
}## Tidak terdapat perbedaan signifikan pada Total Score antara kedua kelompok.# 4. (Opsional) Jika terdapat variabel Stress_Level, analisis korelasi antara Stress_Level dan Total_Score
if("Stress_Level" %in% colnames(data_kaggle)) {
# Menghitung korelasi
cor_result <- cor(data_kaggle$Stress_Level, data_kaggle$Total_Score, use = "complete.obs")
cat(sprintf("Correlation between Stress Level and Total Score: %.4f\n", cor_result))
# Membuat scatter plot dengan garis regresi
p2 <- ggplot(data_kaggle, aes(x = Stress_Level, y = Total_Score)) +
geom_point(color = "blue", alpha = 0.7) +
geom_smooth(method = "lm", se = FALSE, color = "red") +
labs(title = "Relationship between Stress Level and Total Score",
x = "Stress Level",
y = "Total Score") +
theme_minimal()
print(p2)
}## Correlation between Stress Level and Total Score: 0.0042## `geom_smooth()` using formula = 'y ~ x'
# Menampilkan boxplot
print(p1)
Visualisasi Distribusi Skor Total pada Berbagai Tingkat Stres dengan Violin Plot
ggplot(data_kaggle, aes(x = factor(Stress_Level), y = Total_Score, fill = factor(Stress_Level))) +
geom_violin(trim = FALSE) +
labs(
title = "Total Score by Stress Level",
x = "Stress Level",
y = "Total Score"
) +
theme_minimal()
KS-TEST
library(dplyr)
# Rata-rata Total_Score per Stress_Level
df_mean <- data_kaggle %>%
group_by(Stress_Level) %>%
summarize(mean_score = mean(Total_Score, na.rm = TRUE))
ggplot(df_mean, aes(x = Stress_Level, y = mean_score)) +
geom_line(color = "blue") +
geom_point(color = "red", size = 2) +
labs(
title = "Average Total Score by Stress Level",
x = "Stress Level",
y = "Mean of Total Score"
) +
theme_minimal()
ks_result <- ks.test(
data_kaggle$Total_Score,
"pnorm",
mean = mean(data_kaggle$Total_Score, na.rm = TRUE),
sd = sd(data_kaggle$Total_Score, na.rm = TRUE)
)## Warning in ks.test.default(data_kaggle$Total_Score, "pnorm", mean =
## mean(data_kaggle$Total_Score, : ties should not be present for the
## Kolmogorov-Smirnov test# Menampilkan hasil KS test
print(ks_result)##
## Asymptotic one-sample Kolmogorov-Smirnov test
##
## data: data_kaggle$Total_Score
## D = 0.058641, p-value = 2.331e-15
## alternative hypothesis: two-sidedVisualisasi dengan QQ Plot
qqnorm(data_kaggle$Total_Score, main = "QQ Plot: Total_Score")
qqline(data_kaggle$Total_Score, col = "red")
Berdasarkan hasil visualisasi menggunakan QQ Plot pada variabel
Total_Score, dapat disimpulkan bahwa distribusi data tidak sepenuhnya
mengikuti distribusi normal. Hal ini ditunjukkan oleh adanya
penyimpangan titik-titik data dari garis referensi merah pada bagian
ujung plot, baik di sisi kiri maupun kanan, yang mengindikasikan adanya
outlier atau distribusi dengan ekor tebal (heavy tails).