library("dplyr")
## Warning: package 'dplyr' was built under R version 4.2.3
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library("ggplot2")
## Warning: package 'ggplot2' was built under R version 4.2.3
library("ggfortify")
library("gridExtra")
## Warning: package 'gridExtra' was built under R version 4.2.2
##
## Attaching package: 'gridExtra'
## The following object is masked from 'package:dplyr':
##
## combine
library("carData")
library("car")
## Warning: package 'car' was built under R version 4.2.3
##
## Attaching package: 'car'
## The following object is masked from 'package:dplyr':
##
## recode
library("factoextra")
## Warning: package 'factoextra' was built under R version 4.2.3
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
library("corrplot")
## Warning: package 'corrplot' was built under R version 4.2.2
## corrplot 0.92 loaded
library(readxl)
## Warning: package 'readxl' was built under R version 4.2.3
Data <- read_excel("D:/Lily/(10_25) Lab Result.xlsx")
head(Data)
## # A tibble: 6 × 8
## Stasiun `Nitrat (mg/L)` `Fosfat (mg/L)` DO Salinitas Temperature pH
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 1 0.126 0.212 7.87 1.56 30.5 4.31
## 2 2 0.0747 0.182 4.51 9.92 29.6 8.06
## 3 3 0.0349 0.185 3.66 19.4 31.7 7.93
## 4 4 0.0199 0.189 7.74 18 31.2 8.62
## 5 5 0.0134 0.187 8.45 26 31.4 8.33
## 6 6 0.00737 0.183 8.58 26 30.6 8.22
## # ℹ 1 more variable: Kecerahan <dbl>
data <- Data %>%
select(-Stasiun) %>%
mutate(across(everything(), ~as.numeric(.)))
str(data)
## tibble [33 × 7] (S3: tbl_df/tbl/data.frame)
## $ Nitrat (mg/L): num [1:33] 0.1261 0.0747 0.0349 0.0199 0.0134 ...
## $ Fosfat (mg/L): num [1:33] 0.212 0.182 0.185 0.189 0.187 0.183 0.184 0.19 0.183 0.192 ...
## $ DO : num [1:33] 7.87 4.51 3.66 7.74 8.45 ...
## $ Salinitas : num [1:33] 1.56 9.92 19.39 18 26 ...
## $ Temperature : num [1:33] 30.5 29.6 31.7 31.2 31.4 ...
## $ pH : num [1:33] 4.31 8.06 7.93 8.62 8.33 ...
## $ Kecerahan : num [1:33] 25 34.5 28.5 27.5 18.8 ...
#View(data)
pca_result <- prcomp(data, scale = TRUE)
print(pca_result)
## Standard deviations (1, .., p=7):
## [1] 1.7146614 1.1504144 1.1119227 0.7918597 0.6081847 0.5491408 0.4490265
##
## Rotation (n x k) = (7 x 7):
## PC1 PC2 PC3 PC4 PC5
## Nitrat (mg/L) -0.49451372 0.15532225 -0.04928073 0.1913844 -0.65543039
## Fosfat (mg/L) -0.36583331 -0.54343058 0.12018123 -0.3743179 0.38422114
## DO -0.24120447 0.60865967 0.36539539 0.2585531 0.55546102
## Salinitas 0.49897890 0.06408111 -0.11359697 -0.2805945 0.01573817
## Temperature 0.18339329 -0.52003611 0.45487109 0.6567573 -0.03121462
## pH 0.52356319 0.15076909 0.03061512 0.1497428 -0.04666553
## Kecerahan 0.08192147 0.11320932 0.79300998 -0.4732041 -0.33293912
## PC6 PC7
## Nitrat (mg/L) 0.33572532 -0.38726491
## Fosfat (mg/L) 0.10920693 -0.50669493
## DO 0.22247952 -0.11382557
## Salinitas 0.80689795 -0.06280237
## Temperature 0.22661971 0.07321612
## pH -0.33690534 -0.75107070
## Kecerahan -0.09959524 0.08317414
eig.val<-get_eigenvalue(pca_result)
eig.val
## eigenvalue variance.percent cumulative.variance.percent
## Dim.1 2.9400637 42.000910 42.00091
## Dim.2 1.3234534 18.906477 60.90739
## Dim.3 1.2363721 17.662458 78.56985
## Dim.4 0.6270418 8.957740 87.52759
## Dim.5 0.3698886 5.284123 92.81171
## Dim.6 0.3015556 4.307937 97.11965
## Dim.7 0.2016248 2.880355 100.00000
# Variansi yang dijelaskan oleh masing-masing komponen
fviz_eig(pca_result, addlabels = TRUE, ylim = c(0, 60), title = "")
# Plot individu
fviz_pca_ind(pca_result,
repel = TRUE,
pointsize = 3,
col.ind = "steelblue",
title = "")
# Plot kontribusi tiap variabel
fviz_pca_var(pca_result,
col.var = "contrib", # warna = kontribusi
gradient.cols = c("#00AFBB", "#E7B800", "#FC4E07"),
repel = TRUE,
title = "")
# Biplot gabungan (individu + variabel)
fviz_pca_biplot(pca_result, repel = TRUE, title = "")
library(plotly)
## Warning: package 'plotly' was built under R version 4.2.3
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
# Ambil skor individu
pca_ind <- as.data.frame(pca_result$x)
# Plot interaktif 3D (PC1, PC2, PC3)
plot_ly(pca_ind, x = ~PC1, y = ~PC2, z = ~PC3,
type = "scatter3d", mode = "markers",
marker = list(size = 4, color = 'steelblue')) %>%
layout(scene = list(
xaxis = list(title = "PC1"),
yaxis = list(title = "PC2"),
zaxis = list(title = "PC3")
))
library(factoextra)
pca_scores <- pca_result$x
# Tentukan jumlah cluster (misal 3)
set.seed(123)
kmeans_result <- kmeans(pca_scores[, 1:3], centers = 2) # pakai PC1 dan PC24
# Plot PCA dengan warna berdasarkan hasil k-means cluster
fviz_pca_ind(pca_result,
geom.ind = "point",
col.ind = as.factor(kmeans_result$cluster),
palette = "jco",
addEllipses = TRUE,
ellipse.level = 0.95,
legend.title = "Cluster",
title="",
repel = TRUE) +
theme_minimal()
library(factoextra)
# Ambil skor PCA
pca_scores <- pca_result$x
# Tentukan jumlah cluster (3 cluster)
set.seed(123)
kmeans_result <- kmeans(pca_scores[, 1:3], centers = 2) # gunakan PC1, PC2, dan PC3
# Tambahkan hasil cluster ke dalam data PCA
cluster_pca <- data.frame(pca_scores[, 1:3], Cluster = as.factor(kmeans_result$cluster))
# Plot hasil PCA dengan warna berdasarkan cluster
fviz_pca_ind(pca_result,
geom.ind = "point",
col.ind = as.factor(kmeans_result$cluster),
palette = "jco",
addEllipses = TRUE,
ellipse.level = 0.95,
legend.title = "Cluster",
title="",
repel = TRUE) +
theme_minimal()
fviz_pca_biplot(pca_result,
geom.ind = c("point", "text"), # tampilkan titik + label stasiun
col.ind = as.factor(kmeans_result$cluster), # warna per cluster
palette = "jco", # palet warna
addEllipses = TRUE, # tampilkan area klaster
ellipse.level = 0.95,
label = "all", # tampilkan label stasiun + variabel
repel = TRUE, # hindari tumpang tindih teks
col.var = "red", # warna panah variabel
arrowsize = 0.8, # ukuran panah
legend.title = "Cluster") +
theme_minimal() +
ggtitle("") +
theme(plot.title = element_text(hjust = 0.5))
# --- 1️⃣ Pastikan kolom 'Stasiun' ada di data ---
# (kalau nama kolomnya beda, sesuaikan ya)
head(Data$Stasiun)
## [1] 1 2 3 4 5 6
# --- 2️⃣ Ambil hanya variabel numerik untuk PCA ---
data_num <- Data %>% select(where(is.numeric))
# --- 3️⃣ Jalankan PCA dengan data numerik ---
pca_result <- prcomp(data_num, scale. = TRUE)
pca_scores <- as.data.frame(pca_result$x) # ubah ke data.frame biar bisa pakai rownames
# --- 4️⃣ Tambahkan kolom Stasiun agar tidak hilang ---
pca_scores$Stasiun <- Data$Stasiun
# --- 5️⃣ Jalankan K-Means berdasarkan PC1 & PC2 ---
set.seed(123)
kmeans_result <- kmeans(pca_scores[, 1:2], centers = 2)
# --- 6️⃣ Gabungkan hasil klaster ke skor PCA ---
pca_scores$Cluster <- as.factor(kmeans_result$cluster)
# --- 7️⃣ Lihat hasil tabel klaster ---
head(pca_scores[, c("Stasiun", "Cluster")])
## Stasiun Cluster
## 1 1 2
## 2 2 2
## 3 3 2
## 4 4 2
## 5 5 2
## 6 6 2
# Gabungkan hasil cluster dengan data awal (variabel numerik)
data_clustered <- cbind(Data, Cluster = pca_scores$Cluster)
# Hitung rata-rata tiap variabel per klaster
cluster_summary <- data_clustered %>%
group_by(Cluster) %>%
summarise(across(where(is.numeric), mean, na.rm = TRUE))
## Warning: There was 1 warning in `summarise()`.
## ℹ In argument: `across(where(is.numeric), mean, na.rm = TRUE)`.
## ℹ In group 1: `Cluster = 1`.
## Caused by warning:
## ! The `...` argument of `across()` is deprecated as of dplyr 1.1.0.
## Supply arguments directly to `.fns` through an anonymous function instead.
##
## # Previously
## across(a:b, mean, na.rm = TRUE)
##
## # Now
## across(a:b, \(x) mean(x, na.rm = TRUE))
View(data_clustered)
# --- Ambil 2 faktor utama dari PCA ---
faktor_df <- pca_result$x[, 1:2] %>%
as.data.frame() %>%
mutate(Stasiun = Data$Stasiun) %>%
rename(Faktor1 = PC1,
Faktor2 = PC2)
# --- Gabungkan dengan data_clustered ---
data_final <- data_clustered %>%
left_join(faktor_df, by = "Stasiun")
# --- Lihat hasil akhir ---
print(data_final)
## Stasiun Nitrat (mg/L) Fosfat (mg/L) DO Salinitas Temperature
## 1 1 0.12607798 0.212 7.87333333 1.56100 30.50000
## 2 2 0.07473914 0.182 4.51333333 9.92390 29.56667
## 3 3 0.03488772 0.185 3.66000000 19.38500 31.70000
## 4 4 0.01985480 0.189 7.74000000 18.00000 31.20000
## 5 5 0.01340199 0.187 8.45000000 26.00000 31.40000
## 6 6 0.00737464 0.183 8.58000000 26.00000 30.60000
## 7 7 0.09324665 0.184 9.39000000 25.00000 29.80000
## 8 8 0.04956609 0.190 9.08000000 25.00000 30.70000
## 9 9 0.03176768 0.183 8.91000000 26.00000 31.20000
## 10 10 0.02829309 0.192 10.04000000 26.00000 30.20000
## 11 11 0.04212054 0.184 9.60000000 27.00000 31.60000
## 12 12 0.04488603 0.189 10.20000000 20.00000 31.90000
## 13 13 0.03389498 0.186 7.44000000 19.00000 36.60000
## 14 14 0.03736957 0.193 8.91000000 18.00000 34.30000
## 15 15 0.03779503 0.188 9.86000000 20.00000 33.60000
## 16 16 0.02098936 0.186 10.50000000 19.00000 32.30000
## 17 17 0.01467837 0.183 10.38000000 24.00000 32.10000
## 18 18 0.01808205 0.186 9.77000000 23.00000 34.50000
## 19 19 -0.00085092 0.189 1.82041636 18.66660 31.13333
## 20 20 0.00368732 0.186 0.09484366 30.00000 30.53333
## 21 21 0.00361641 0.184 0.09380820 33.33333 31.60000
## 22 22 0.00631099 0.187 0.09665549 34.66667 31.90000
## 23 23 0.00794192 0.186 2.16628064 33.33333 32.43333
## 24 24 0.00390005 0.186 0.09495002 31.73333 35.31667
## 25 25 0.01872024 0.184 0.10136012 29.33333 35.06667
## 26 26 0.04552422 0.189 2.94260807 20.33333 36.28333
## 27 27 0.03212223 0.197 0.11456112 20.66667 33.01667
## 28 28 0.01850751 0.194 0.10625376 16.66667 33.33333
## 29 29 0.03304406 0.192 5.92468135 25.66667 33.40000
## 30 30 0.02914401 0.196 0.11257201 21.66667 32.98333
## 31 31 -0.00482188 0.198 7.10005937 20.66667 34.33333
## 32 32 0.00503461 0.188 0.09651730 30.70000 32.65000
## 33 33 -0.00078001 0.196 0.09761000 30.00000 33.91667
## pH Kecerahan Cluster Faktor1 Faktor2
## 1 4.313333 25.00 2 -7.60699518 -3.30328887
## 2 8.060000 34.50 2 -2.47021278 1.46772674
## 3 7.926667 28.50 2 -1.01851160 0.90989852
## 4 8.620000 27.50 2 -0.89070036 1.17252083
## 5 8.330000 18.75 2 -0.39787789 1.51657401
## 6 8.220000 47.50 2 -0.15637996 1.96294916
## 7 8.240000 50.00 2 -1.80949074 1.89263682
## 8 8.140000 47.50 2 -1.18930262 1.05050595
## 9 8.240000 85.00 2 -0.19373272 1.60472783
## 10 8.150000 60.00 2 -0.83218991 0.98952710
## 11 8.100000 45.00 2 -0.53069487 1.42459279
## 12 8.120000 90.00 2 -0.95429898 0.53245643
## 13 7.940000 45.00 1 -0.15503562 -0.47417891
## 14 8.000000 75.00 2 -0.74816558 -0.67357327
## 15 8.120000 57.50 2 -0.56495321 0.16912305
## 16 8.130000 50.00 2 -0.48284141 0.67871937
## 17 8.140000 40.00 2 0.04210964 1.16927975
## 18 8.020000 115.00 1 0.50047658 -0.01188109
## 19 7.966667 43.10 1 0.19984455 -0.25260187
## 20 8.163333 58.40 1 1.24804383 0.40714075
## 21 8.390000 54.20 1 1.85441850 0.53712768
## 22 8.466667 36.90 1 1.83054405 0.23037708
## 23 8.610000 21.80 1 1.74233203 0.38197243
## 24 8.416667 48.00 1 2.29734396 -0.65756642
## 25 8.606667 34.40 1 2.03289498 -0.44301498
## 26 8.423333 43.60 1 0.74270614 -1.46262902
## 27 8.193333 51.75 1 0.36899265 -1.90479233
## 28 8.203333 50.30 1 0.54116121 -1.82374455
## 29 8.343333 46.10 1 0.65448481 -0.86155991
## 30 8.266667 52.50 1 0.69266553 -1.87151962
## 31 8.236667 66.00 1 0.89548966 -1.86064895
## 32 8.383333 44.40 1 2.06123046 -0.68511851
## 33 8.590000 74.00 1 2.29664485 -1.81173798