Imputasi Curah Hujan dengan Miss Forest
Muthi’ah Iffa Karimah
2026-04-10
# Library Bawaan & Manipulasi Data
library(readxl)
library(readr)
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(tidyr)
library(lubridate)##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlibrary(stringr)
# Library Analisis Missing Value
library(naniar)## Warning: package 'naniar' was built under R version 4.5.3library(VIM)## Loading required package: colorspace## Loading required package: grid## VIM is ready to use.## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues##
## Attaching package: 'VIM'## The following object is masked from 'package:datasets':
##
## sleep# Library Visualisasi & Tabel Interaktif
library(ggplot2)
library(ggcorrplot)
library(DT)Meteorologi
Input data
# Input Data
data_met= read_xlsx("D:\\deska_baru2\\Data Meteotologi.xlsx")
str(data_met)## tibble [12,053 × 8] (S3: tbl_df/tbl/data.frame)
## $ Tanggal : POSIXct[1:12053], format: "1990-01-01" "1990-01-02" ...
## $ Tn (suhu minimum) : num [1:12053] 19 19 20 19 19 20 19 19 20 20 ...
## $ Tx ( suhu maksimum) : num [1:12053] 28.4 27 26.8 28.4 28.6 22 27.8 28.2 28.2 24.8 ...
## $ Tavg (rata rata suhu) : num [1:12053] 22.2 22.5 23.1 22.5 21.5 20.3 22.3 23.3 23.2 21.8 ...
## $ RH_avg(kelembaban) : num [1:12053] 86 83 85 85 86 94 84 72 79 87 ...
## $ RR (curah hujan ) : num [1:12053] 6 47 0 12 16.5 1 13 1.5 2 0 ...
## $ ss ( penyinaran) : num [1:12053] 4.1 0.4 6.2 4.3 NA 0.1 5.2 2.8 5.1 0.4 ...
## $ ff_avg (angin rata rata): num [1:12053] 0 0 1 2 2 1 1 2 2 2 ...head(data_met)## # A tibble: 6 × 8
## Tanggal `Tn (suhu minimum)` `Tx ( suhu maksimum)`
## <dttm> <dbl> <dbl>
## 1 1990-01-01 00:00:00 19 28.4
## 2 1990-01-02 00:00:00 19 27
## 3 1990-01-03 00:00:00 20 26.8
## 4 1990-01-04 00:00:00 19 28.4
## 5 1990-01-05 00:00:00 19 28.6
## 6 1990-01-06 00:00:00 20 22
## # ℹ 5 more variables: `Tavg (rata rata suhu)` <dbl>,
## # `RH_avg(kelembaban)` <dbl>, `RR (curah hujan )` <dbl>,
## # `ss ( penyinaran)` <dbl>, `ff_avg (angin rata rata)` <dbl>pre-processing Data
# Ganti nama kolom
data_met = data_met %>%
rename_with(~ str_remove(., "\\s*\\(.*\\)"))
str(data_met)## tibble [12,053 × 8] (S3: tbl_df/tbl/data.frame)
## $ Tanggal: POSIXct[1:12053], format: "1990-01-01" "1990-01-02" ...
## $ Tn : num [1:12053] 19 19 20 19 19 20 19 19 20 20 ...
## $ Tx : num [1:12053] 28.4 27 26.8 28.4 28.6 22 27.8 28.2 28.2 24.8 ...
## $ Tavg : num [1:12053] 22.2 22.5 23.1 22.5 21.5 20.3 22.3 23.3 23.2 21.8 ...
## $ RH_avg : num [1:12053] 86 83 85 85 86 94 84 72 79 87 ...
## $ RR : num [1:12053] 6 47 0 12 16.5 1 13 1.5 2 0 ...
## $ ss : num [1:12053] 4.1 0.4 6.2 4.3 NA 0.1 5.2 2.8 5.1 0.4 ...
## $ ff_avg : num [1:12053] 0 0 1 2 2 1 1 2 2 2 ...# Mengubah kode 99.9 dalam data menjadi NA
data_met[data_met==8888] = NA EDA
Nilai Statistik
summary(data_met)## Tanggal Tn Tx Tavg
## Min. :1990-01-01 Min. :13.00 Min. :18.80 Min. :18.40
## 1st Qu.:1998-04-02 1st Qu.:19.00 1st Qu.:28.10 1st Qu.:22.80
## Median :2006-07-02 Median :20.00 Median :29.00 Median :23.40
## Mean :2006-07-02 Mean :19.38 Mean :29.01 Mean :23.39
## 3rd Qu.:2014-10-01 3rd Qu.:20.00 3rd Qu.:30.00 3rd Qu.:24.00
## Max. :2022-12-31 Max. :29.00 Max. :36.00 Max. :28.90
## NA's :578 NA's :326 NA's :156
## RH_avg RR ss ff_avg
## Min. :42.00 Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.:73.00 1st Qu.: 0.000 1st Qu.: 3.300 1st Qu.: 1.000
## Median :79.00 Median : 0.800 Median : 5.100 Median : 2.000
## Mean :77.99 Mean : 6.738 Mean : 4.924 Mean : 1.736
## 3rd Qu.:84.00 3rd Qu.: 7.800 3rd Qu.: 6.800 3rd Qu.: 2.000
## Max. :96.00 Max. :160.000 Max. :10.000 Max. :15.000
## NA's :330 NA's :1342 NA's :492 NA's :114Missing Value
# Missing Value
data_met = data_met %>%
mutate(tahun = year(Tanggal))
missing_tahunan <- data_met %>%
group_by(tahun) %>%
summarise(
RR_na = sum(is.na(RR)),
Tn_na = sum(is.na(Tn)),
Tx_na = sum(is.na(Tx))
)
library(DT)
# Membuat tabel interaktif
datatable(missing_tahunan,
options = list(pageLength = 33),
caption = 'Tabel Missing Value Tahunan')# Visualisasi
# A. Menggunakan naniar: Melihat peta sebaran data kosong
# Hitam = Data ada, Abu-abu = Data kosong (NA)
vis_miss(data_met) +
labs(title = "Peta Sebaran Missing Value Data Meteorologi")
# B. Menggunakan VIM: Melihat kombinasi variabel yang sering kosong bersamaan
aggr(data_met,
col = c('navyblue','red'),
numbers = TRUE,
sortVars = TRUE,
labels = names(data_met),
cex.axis = .7,
gap = 3,
ylab = c("Proporsi Missing Data", "Pola Kombinasi Kosong"))## Warning in plot.aggr(res, ...): not enough vertical space to display
## frequencies (too many combinations)
##
## Variables sorted by number of missings:
## Variable Count
## RR 0.111341575
## Tn 0.047954866
## ss 0.040819713
## RH_avg 0.027379076
## Tx 0.027047208
## Tavg 0.012942836
## ff_avg 0.009458226
## Tanggal 0.000000000
## tahun 0.000000000Korelasi
# Korelasi
data_numeric = na.omit(data_met[, 2:8]) # Buang kolom Tanggal dan hapus NA sementara khusus untuk hitung korelasi
data_numeric = na.omit(data_met[, 2:8])
matriks_korelasi <- cor(data_numeric)
# Visualisasi
ggcorrplot(matriks_korelasi,
method = "square",
type = "lower", # Hanya menampilkan separuh bawah matriks
lab = TRUE, # Menampilkan angka korelasi
colors = c("red", "white", "blue"),
title = "Matriks Korelasi Variabel Meteorologi Bandung")## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## ℹ The deprecated feature was likely used in the ggcorrplot package.
## Please report the issue at <https://github.com/kassambara/ggcorrplot/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
matriks_korelasi = cor(data_numeric)Distribusi Data
# Histogram
data_long = data_met %>%
select(Tn, Tx, RR) %>%
pivot_longer(cols = everything(), names_to = "Variabel", values_to = "Nilai")
# Visualisasi
ggplot(data_long, aes(x = Variabel, y = Nilai, fill = Variabel)) +
geom_boxplot(alpha = 0.7, outlier.colour = "red", outlier.shape = 16) +
coord_flip() +
theme_minimal() +
labs(title = "Distribusi Suhu (Tn, Tx) & Curah Hujan (RR)",
x = "Variabel Iklim",
y = "Nilai Pengukuran")## Warning: Removed 2246 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
Tren Curah hujan
# Line chart untuk Curah Hujan (RR)
ggplot(data_met, aes(x = Tanggal, y = RR)) +
geom_line(color = "dodgerblue", alpha = 0.8) +
theme_minimal() +
labs(title = "Tren Runtun Waktu Curah Hujan (RR) Kota Bandung 1990-2022",
x = "Tahun",
y = "Curah Hujan (mm)")
# Line chart untuk Suhu Rata-rata (Tavg)
ggplot(data_met, aes(x = Tanggal, y = Tavg)) +
geom_line(color = "firebrick", alpha = 0.8) +
theme_minimal() +
labs(title = "Tren Runtun Waktu Suhu Rata-rata (Tavg) Kota Bandung 1990-2022",
x = "Tahun",
y = "Suhu Rata-rata (°C)")
Uji Algoritma MF: Skema Penghapusan Data
# Data Ground Truth
gt_met = na.omit(data_met[,2:8])
anyNA(gt_met) # Cek data sudah bersih NA ## [1] FALSESkema Rendah (10%)
Duplikasi data dan hilangkan 10% nilai dalam data
set.seed(123)
uji_1 = gt_met
for (col in names(uji_1)) {
n_hilang <- round(0.1 * nrow(uji_1))
idx <- sample(1:nrow(uji_1), n_hilang)
uji_1[idx, col] <- NA
}
# Simpan nilai asli yang nanti akan kita tebak
mask_1 <- is.na(uji_1)
nilai_asli_1 <- gt_met[mask_1]Skema Sedang (40%)
Duplikasi data dan hilangkan 40% nilai dalam data
set.seed(123)
uji_2 = gt_met
for (col in names(uji_2)) {
n_hilang <- round(0.4 * nrow(uji_2))
idx <- sample(1:nrow(uji_2), n_hilang)
uji_2[idx, col] <- NA
}
# Simpan nilai asli yang nanti akan kita tebak
mask_2 <- is.na(uji_2)
nilai_asli_2 <- gt_met[mask_2]Skema Tinggi (70%)
Duplikasi data dan hilangkan 40% nilai dalam data
set.seed(123)
uji_3 = gt_met
for (col in names(uji_3)) {
n_hilang <- round(0.4 * nrow(uji_3))
idx <- sample(1:nrow(uji_3), n_hilang)
uji_3[idx, col] <- NA
}
# Simpan nilai asli yang nanti akan kita tebak
mask_3 <- is.na(uji_3)
nilai_asli_3 <- gt_met[mask_3]Missing Forest
library(missForest)## Warning: package 'missForest' was built under R version 4.5.3##
## Attaching package: 'missForest'## The following object is masked from 'package:VIM':
##
## nrmselibrary(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ tibble 3.3.0
## ✔ purrr 1.1.0## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsMF_1 <- missForest(as.matrix(uji_1))
MF_1 <- as.data.frame(MF_1$ximp)
MF_2 <- missForest(as.matrix(uji_2))
MF_2 <- as.data.frame(MF_2$ximp)
MF_3 <- missForest(as.matrix(uji_3))
MF_3 <- as.data.frame(MF_3$ximp)prediksi_mf_1 <- MF_1[mask_1]
prediksi_mf_2 <- MF_2[mask_2]
prediksi_mf_3 <- MF_3[mask_3]Evaluasi
RMSE
# RMSE
rmse <- function(asli, prediksi) sqrt(mean((asli - prediksi)^2, na.rm = TRUE))
rmse.mf_1 <- rmse(nilai_asli_1, prediksi_mf_1)
rmse.mf_2 <- rmse(nilai_asli_2, prediksi_mf_2)
rmse.mf_3 <- rmse(nilai_asli_3, prediksi_mf_3)Standar Deviasi
# standar deviasi
sd_asli_1 <- sd(nilai_asli_1, na.rm = TRUE)
sd_asli_2 <- sd(nilai_asli_2, na.rm = TRUE)
sd_asli_3 <- sd(nilai_asli_3, na.rm = TRUE)Hasil
# Output
results <- data.frame(
Skema = c("Rendah", "Sedang", "Tinggi"),
missForest = c(rmse.mf_1, rmse.mf_2, rmse.mf_3),
SD = c(sd_asli_1, sd_asli_2, sd_asli_3)
)
results## Skema missForest SD
## 1 Rendah 4.603724 24.88453
## 2 Sedang 5.362874 24.88799
## 3 Tinggi 5.365027 24.88799Gabungan (Meteorologi dan CHIRPS)
Input Data
# Data Meteorologi (variabel-variabel lain)
data_met = data_met %>%
select(-tahun)
str(data_met)## tibble [12,053 × 8] (S3: tbl_df/tbl/data.frame)
## $ Tanggal: POSIXct[1:12053], format: "1990-01-01" "1990-01-02" ...
## $ Tn : num [1:12053] 19 19 20 19 19 20 19 19 20 20 ...
## $ Tx : num [1:12053] 28.4 27 26.8 28.4 28.6 22 27.8 28.2 28.2 24.8 ...
## $ Tavg : num [1:12053] 22.2 22.5 23.1 22.5 21.5 20.3 22.3 23.3 23.2 21.8 ...
## $ RH_avg : num [1:12053] 86 83 85 85 86 94 84 72 79 87 ...
## $ RR : num [1:12053] 6 47 0 12 16.5 1 13 1.5 2 0 ...
## $ ss : num [1:12053] 4.1 0.4 6.2 4.3 NA 0.1 5.2 2.8 5.1 0.4 ...
## $ ff_avg : num [1:12053] 0 0 1 2 2 1 1 2 2 2 ...# Data Chirps (satelit)
data_chrp = read_xlsx("D:\\deska_baru2\\DATA CH Bandung CHRIPS.xlsx")
# Ubah nama kolom ke-2 agar lebih mudah
data_chrp = data_chrp %>%
rename(RR_chrp = 2)
str(data_chrp)## tibble [12,053 × 2] (S3: tbl_df/tbl/data.frame)
## $ Tanggal: POSIXct[1:12053], format: "1990-01-01" "1990-01-02" ...
## $ RR_chrp: num [1:12053] 13.22 3.86 4.41 11.57 3.86 ...head(data_chrp)## # A tibble: 6 × 2
## Tanggal RR_chrp
## <dttm> <dbl>
## 1 1990-01-01 00:00:00 13.2
## 2 1990-01-02 00:00:00 3.86
## 3 1990-01-03 00:00:00 4.41
## 4 1990-01-04 00:00:00 11.6
## 5 1990-01-05 00:00:00 3.86
## 6 1990-01-06 00:00:00 9.17Pre-Proecessing Data
# Gabungkan data Meteorologi dengan data Satelit
data_gab = data_met %>%
left_join(data_chrp, by = "Tanggal")
# Ubah kode 8888 jadi NA
data_gab[data_gab==8888] = NA
str(data_gab)## tibble [12,053 × 9] (S3: tbl_df/tbl/data.frame)
## $ Tanggal: POSIXct[1:12053], format: "1990-01-01" "1990-01-02" ...
## $ Tn : num [1:12053] 19 19 20 19 19 20 19 19 20 20 ...
## $ Tx : num [1:12053] 28.4 27 26.8 28.4 28.6 22 27.8 28.2 28.2 24.8 ...
## $ Tavg : num [1:12053] 22.2 22.5 23.1 22.5 21.5 20.3 22.3 23.3 23.2 21.8 ...
## $ RH_avg : num [1:12053] 86 83 85 85 86 94 84 72 79 87 ...
## $ RR : num [1:12053] 6 47 0 12 16.5 1 13 1.5 2 0 ...
## $ ss : num [1:12053] 4.1 0.4 6.2 4.3 NA 0.1 5.2 2.8 5.1 0.4 ...
## $ ff_avg : num [1:12053] 0 0 1 2 2 1 1 2 2 2 ...
## $ RR_chrp: num [1:12053] 13.22 3.86 4.41 11.57 3.86 ...ncol(data_gab)## [1] 9EDA
Nilai Statistik
summary(data_gab)## Tanggal Tn Tx Tavg
## Min. :1990-01-01 Min. :13.00 Min. :18.80 Min. :18.40
## 1st Qu.:1998-04-02 1st Qu.:19.00 1st Qu.:28.10 1st Qu.:22.80
## Median :2006-07-02 Median :20.00 Median :29.00 Median :23.40
## Mean :2006-07-02 Mean :19.38 Mean :29.01 Mean :23.39
## 3rd Qu.:2014-10-01 3rd Qu.:20.00 3rd Qu.:30.00 3rd Qu.:24.00
## Max. :2022-12-31 Max. :29.00 Max. :36.00 Max. :28.90
## NA's :578 NA's :326 NA's :156
## RH_avg RR ss ff_avg
## Min. :42.00 Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.:73.00 1st Qu.: 0.000 1st Qu.: 3.300 1st Qu.: 1.000
## Median :79.00 Median : 0.800 Median : 5.100 Median : 2.000
## Mean :77.99 Mean : 6.738 Mean : 4.924 Mean : 1.736
## 3rd Qu.:84.00 3rd Qu.: 7.800 3rd Qu.: 6.800 3rd Qu.: 2.000
## Max. :96.00 Max. :160.000 Max. :10.000 Max. :15.000
## NA's :330 NA's :1342 NA's :492 NA's :114
## RR_chrp
## Min. : 0.000
## 1st Qu.: 0.000
## Median : 3.079
## Mean : 6.063
## 3rd Qu.: 9.865
## Max. :90.572
## Missing Value
# Missing Value
data_gab = data_gab %>%
mutate(tahun = year(Tanggal))
missing_tahunan2 <- data_gab %>%
group_by(tahun) %>%
summarise(
RR_na = sum(is.na(RR)),
Tn_na = sum(is.na(Tn)),
Tx_na = sum(is.na(Tx))
)
library(DT)
# Membuat tabel interaktif
datatable(missing_tahunan2,
options = list(pageLength = 33),
caption = 'Tabel Missing Value Tahunan')# Visualisasi
# A. Menggunakan naniar: Melihat peta sebaran data kosong
# Hitam = Data ada, Abu-abu = Data kosong (NA)
vis_miss(data_gab) +
labs(title = "Peta Sebaran Missing Value Data Meteorologi")
# B. Menggunakan VIM: Melihat kombinasi variabel yang sering kosong bersamaan
aggr(data_gab,
col = c('navyblue','red'),
numbers = TRUE,
sortVars = TRUE,
labels = names(data_gab),
cex.axis = .7,
gap = 3,
ylab = c("Proporsi Missing Data", "Pola Kombinasi Kosong"))## Warning in plot.aggr(res, ...): not enough vertical space to display
## frequencies (too many combinations)
##
## Variables sorted by number of missings:
## Variable Count
## RR 0.111341575
## Tn 0.047954866
## ss 0.040819713
## RH_avg 0.027379076
## Tx 0.027047208
## Tavg 0.012942836
## ff_avg 0.009458226
## Tanggal 0.000000000
## RR_chrp 0.000000000
## tahun 0.000000000Korelasi
# Korelasi
data_numeric2 = na.omit(data_gab[, 2:8]) # Buang kolom Tanggal dan hapus NA sementara khusus untuk hitung korelasi
data_numeric2 = na.omit(data_gab[, 2:8])
matriks_korelasi <- cor(data_numeric2)
# Visualisasi
ggcorrplot(matriks_korelasi,
method = "square",
type = "lower", # Hanya menampilkan separuh bawah matriks
lab = TRUE, # Menampilkan angka korelasi
colors = c("red", "white", "blue"),
title = "Matriks Korelasi Variabel Meteorologi Bandung")
matriks_korelasi = cor(data_numeric2)Distribusi Data
# Histogram
data_long2 = data_gab %>%
select(Tn, Tx, RR) %>%
pivot_longer(cols = everything(), names_to = "Variabel", values_to = "Nilai")
# Visualisasi
ggplot(data_long2, aes(x = Variabel, y = Nilai, fill = Variabel)) +
geom_boxplot(alpha = 0.7, outlier.colour = "red", outlier.shape = 16) +
coord_flip() +
theme_minimal() +
labs(title = "Distribusi Suhu (Tn, Tx) & Curah Hujan (RR)",
x = "Variabel Iklim",
y = "Nilai Pengukuran")## Warning: Removed 2246 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
Tren Curah Hujan
# Line chart untuk Curah Hujan (RR)
ggplot(data_gab, aes(x = Tanggal, y = RR)) +
geom_line(color = "dodgerblue", alpha = 0.8) +
theme_minimal() +
labs(title = "Tren Runtun Waktu Curah Hujan (RR) Kota Bandung 1990-2022",
x = "Tahun",
y = "Curah Hujan (mm)")
# Line chart untuk Suhu Rata-rata (Tavg)
ggplot(data_gab, aes(x = Tanggal, y = Tavg)) +
geom_line(color = "firebrick", alpha = 0.8) +
theme_minimal() +
labs(title = "Tren Runtun Waktu Suhu Rata-rata (Tavg) Kota Bandung 1990-2022",
x = "Tahun",
y = "Suhu Rata-rata (°C)")
Uji Algoritma
# Data Ground Truth
gt_gab = na.omit(data_gab[,2:8])
anyNA(gt_gab) # Cek data sudah bersih NA ## [1] FALSESkema Rendah (10%)
Duplikasi data dan hilangkan 10% nilai dalam data
set.seed(123)
uji1 = gt_gab
for (col in names(uji1)) {
n_hilang = round(0.1 * nrow(uji1))
idx = sample(1:nrow(uji1), n_hilang)
uji1[idx, col] = NA
}
# Simpan nilai asli 10%
mask1 = is.na(uji1)
nilai_asli1 = gt_gab[mask1]Skema Rendah (40%)
Duplikasi data dan hilangkan 40% nilai dalam data
set.seed(123)
uji2 = gt_gab
for (col in names(uji2)) {
n_hilang = round(0.4 * nrow(uji2))
idx = sample(1:nrow(uji2), n_hilang)
uji2[idx, col] = NA
}
# Simpan nilai asli 40%
mask2 = is.na(uji2)
nilai_asli2 = gt_gab[mask2]Skema Rendah (70%)
Duplikasi data dan hilangkan 70% nilai dalam data
set.seed(123)
uji3 = gt_gab
for (col in names(uji3)) {
n_hilang = round(0.7 * nrow(uji3))
idx = sample(1:nrow(uji3), n_hilang)
uji3[idx, col] = NA
}
# Simpan nilai asli 70%
mask3 = is.na(uji3)
nilai_asli3 = gt_gab[mask3]Missing Forest
MF1 <- missForest(as.matrix(uji1))
MF1 <- as.data.frame(MF1$ximp)
MF2 <- missForest(as.matrix(uji2))
MF2 <- as.data.frame(MF2$ximp)
MF3 <- missForest(as.matrix(uji3))
MF3 <- as.data.frame(MF3$ximp)prediksi_mf1 <- MF1[mask1]
prediksi_mf2 <- MF2[mask2]
prediksi_mf3 <- MF3[mask3]Evaluasi
RMSE
# RMSE
rmse <- function(asli, prediksi) sqrt(mean((asli - prediksi)^2, na.rm = TRUE))
rmse.mf1 <- rmse(nilai_asli1, prediksi_mf1)
rmse.mf2 <- rmse(nilai_asli2, prediksi_mf2)
rmse.mf3 <- rmse(nilai_asli3, prediksi_mf3)Standar Deviasi
# standar deviasi
sd_asli1 <- sd(nilai_asli1, na.rm = TRUE)
sd_asli2 <- sd(nilai_asli2, na.rm = TRUE)
sd_asli3 <- sd(nilai_asli3, na.rm = TRUE)Hasil
# Output
results <- data.frame(
Skema = c("Rendah", "Sedang", "Tinggi"),
missForest = c(rmse.mf1, rmse.mf2, rmse.mf3),
SD = c(sd_asli1, sd_asli2, sd_asli3)
)
results## Skema missForest SD
## 1 Rendah 4.551962 24.88453
## 2 Sedang 5.288929 24.88799
## 3 Tinggi 6.110610 24.91973Imputasi
# Imputasi Meteorologi
data1 = data_met %>%
select(-Tanggal)
MF.1 <- missForest(as.matrix(data1))
MF.1 <- as.data.frame(MF.1$ximp)
# Imputasi Gabungan (Meteorologi + Chirps)
data2 = data_gab %>%
select(-Tanggal, -tahun)
MF.2 <- missForest(as.matrix(data2))
MF.2 <- as.data.frame(MF.2$ximp)Data Final
# Meteorologi
#final_met = data.frame(
#Tanggal = data_met$Tanggal,
#CH = MF.1$RR,
#Tn = MF.1$Tn,
#Tx = MF.1$Tx
#)
#head(final_met)
#anyNA(final_met)# Gabungan (Meteorologi + Satelit)
#final_gab = data.frame(
#Tanggal = data_gab$Tanggal,
#CH = MF.2$RR,
#Tn = MF.2$Tn,
#Tx = MF.2$Tx
#)
#head(final_gab)
#anyNA(final_gab)# Excel
#library(writexl)
#path_met = "D:\\deska_baru2\\Meteorologi.xlsx"
#path_gab = "D:\\deska_baru2\\Gabungan.xlsx"
# Simpan hasil imputasi stasiun saja ke folder Downloads
#write_xlsx(final_met, path_met)
# Simpan hasil imputasi gabungan (stasiun + satelit) ke folder Downloads
#write_xlsx(final_gab, path_gab)# CSV
#library(readr)
#path_met_csv = "D:\\deska_baru2\\Meteorologi.csv"
#path_gab_csv = "D:\\deska_baru2\\Gabungan.csv"
# Meteorologi
#write_csv(final_met, path_met_csv)
# Gabungan
#write_csv(final_gab, path_gab_csv)