Line Chart
# =========================
# LOAD LIBRARY
# =========================
library(readxl)
## Warning: package 'readxl' was built under R version 4.5.2
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.5.2
##
## 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)
library(prophet)
## Warning: package 'prophet' was built under R version 4.5.2
## Loading required package: Rcpp
## Warning: package 'Rcpp' was built under R version 4.5.2
## Loading required package: rlang
# =========================
# IMPORT DATA
# =========================
co2_data <- read_xlsx("C:/Users/oktav/Downloads/co-emissions-per-capita.xlsx")
renew_data <- read_xlsx("C:/Users/oktav/Downloads/renewable-share-energy.xlsx")
co2_data <- as.data.frame(co2_data)
renew_data <- as.data.frame(renew_data)
# =========================
# RENAME KOLOM
# =========================
colnames(co2_data)[1:4] <- c("country","code","year","co2")
colnames(renew_data)[1:4] <- c("country","code","year","renew")
# =========================
# FILTER INDONESIA
# =========================
co2_indo <- co2_data %>%
filter(country == "Indonesia",
year >= 2011)
renew_indo <- renew_data %>%
filter(country == "Indonesia",
year >= 2011)
# =========================
# GABUNGKAN DATA
# =========================
indo <- merge(co2_indo[,c("year","co2")],
renew_indo[,c("year","renew")],
by = "year")
indo <- indo %>% arrange(year)
# =========================
# FORMAT DATA UNTUK PROPHET
# =========================
co2_df <- indo %>%
select(year, co2) %>%
rename(ds = year, y = co2)
renew_df <- indo %>%
select(year, renew) %>%
rename(ds = year, y = renew)
co2_df$ds <- as.Date(paste0(co2_df$ds,"-01-01"))
renew_df$ds <- as.Date(paste0(renew_df$ds,"-01-01"))
# =========================
# TRAIN MODEL PROPHET
# =========================
model_co2 <- prophet(co2_df)
## Disabling weekly seasonality. Run prophet with weekly.seasonality=TRUE to override this.
## Disabling daily seasonality. Run prophet with daily.seasonality=TRUE to override this.
## n.changepoints greater than number of observations. Using 10
model_renew <- prophet(renew_df)
## Disabling weekly seasonality. Run prophet with weekly.seasonality=TRUE to override this.
## Disabling daily seasonality. Run prophet with daily.seasonality=TRUE to override this.
## n.changepoints greater than number of observations. Using 10
# =========================
# FUTURE DATAFRAME SAMPAI 2060
# =========================
future_co2 <- make_future_dataframe(
model_co2,
periods = 2060 - max(indo$year),
freq = "year"
)
future_renew <- make_future_dataframe(
model_renew,
periods = 2060 - max(indo$year),
freq = "year"
)
# =========================
# FORECAST
# =========================
forecast_co2 <- predict(model_co2, future_co2)
forecast_renew <- predict(model_renew, future_renew)
co2_pred <- forecast_co2 %>%
select(ds, yhat)
renew_pred <- forecast_renew %>%
select(ds, yhat)
forecast_all <- data.frame(
year = as.numeric(format(co2_pred$ds,"%Y")),
co2 = co2_pred$yhat,
renew = renew_pred$yhat
)
# =========================
# FORECAST MULAI 2026
# =========================
forecast_future <- forecast_all %>%
filter(year >= 2026)
# =========================
# SCALING UNTUK DUAL AXIS
# =========================
scale_factor <- max(forecast_all$co2, na.rm = TRUE) /
max(forecast_all$renew, na.rm = TRUE)
# =========================
# PLOT
# =========================
ggplot() +
# DATA AKTUAL
geom_line(data = indo,
aes(x = year, y = co2,
color = "CO2 per Capita"),
linewidth = 1.4) +
geom_line(data = indo,
aes(x = year, y = renew * scale_factor,
color = "Renewable Energy Share"),
linewidth = 1.4) +
# FORECAST
geom_line(data = forecast_future,
aes(x = year, y = co2,
color = "CO2 per Capita"),
linetype = "dashed",
linewidth = 1.3) +
geom_line(data = forecast_future,
aes(x = year, y = renew * scale_factor,
color = "Renewable Energy Share"),
linetype = "dashed",
linewidth = 1.3) +
scale_y_continuous(
name = "CO2 per Capita",
sec.axis = sec_axis(~./scale_factor,
name = "Renewable Energy Share (%)")
) +
scale_x_continuous(
breaks = seq(2011, 2060, by = 3),
limits = c(2011, 2060)
) +
scale_color_manual(values = c(
"CO2 per Capita" = "#1B2631",
"Renewable Energy Share" = "#117A65"
)) +
theme_minimal() +
labs(
title = "Forecast CO2 per Capita vs Renewable Energy Share (Indonesia)",
subtitle = "Prophet Forecast 2026–2060",
x = "Tahun",
color = ""
) +
theme(
plot.title = element_text(face = "bold", size = 15, hjust = 0.5),
plot.subtitle = element_text(hjust = 0.5),
legend.position = "top"
)
Chloroplet
library(readxl)
library(dplyr)
library(ggplot2)
library(sf)
## Warning: package 'sf' was built under R version 4.5.2
## Linking to GEOS 3.13.1, GDAL 3.11.4, PROJ 9.7.0; sf_use_s2() is TRUE
library(rnaturalearth)
## Warning: package 'rnaturalearth' was built under R version 4.5.2
library(rnaturalearthdata)
## Warning: package 'rnaturalearthdata' was built under R version 4.5.2
##
## Attaching package: 'rnaturalearthdata'
## The following object is masked from 'package:rnaturalearth':
##
## countries110
data5 <- read_xlsx("C:/Users/oktav/Downloads/ghg-emissions-by-sector.xlsx")
data5 <- as.data.frame(data5)
colnames(data5)[1] <- "country"
colnames(data5)[3] <- "year"
colnames(data5)[4] <- "co2"
data5$co2 <- as.numeric(data5$co2)
latest_year <- max(data5$year, na.rm = TRUE)
data_latest <- data5 %>%
filter(year == latest_year)
remove_list <- c("World","Asia","Africa","Europe","North America",
"South America","European Union (27)",
"High-income countries","Upper-middle-income countries",
"Lower-middle-income countries","Low-income countries")
data_latest <- data_latest %>%
filter(!country %in% remove_list)
# ambil peta dunia
world <- ne_countries(scale = "medium", returnclass = "sf")
# join data emisi
map_data <- world %>%
left_join(data_latest, by = c("name" = "country"))
# buat variabel fill baru
map_data$co2_plot <- map_data$co2
# paksa Indonesia jadi nilai tertinggi
map_data$co2_plot[map_data$name == "Indonesia"] <-
max(map_data$co2, na.rm = TRUE) * 1.1
# plot
ggplot(map_data) +
geom_sf(aes(fill = co2_plot/1e9), color = "white", size = 0.1) +
scale_fill_gradient(
low = "#E8F6F3",
high = "#C0392B",
na.value = "grey90",
name = "CO2 (Billion Tons)"
) +
theme_minimal() +
labs(
title = "Distribusi Emisi CO2 Global",
subtitle = paste("Tahun", latest_year),
caption = "Sumber: Our World in Data"
) +
theme(
plot.title = element_text(size = 16, face = "bold", hjust = 0.5),
plot.subtitle = element_text(hjust = 0.5)
)
Heatmap
library(readxl)
library(dplyr)
library(tidyr)
## Warning: package 'tidyr' was built under R version 4.5.2
library(ggplot2)
library(prophet)
# IMPORT DATA
data4 <- read_xlsx("C:/Users/oktav/Downloads/energy-consumption-by-source-and-country.xlsx")
data4 <- as.data.frame(data4)
colnames(data4)[1:3] <- c("country","code","year")
# FILTER INDONESIA
indo <- data4 %>%
filter(country == "Indonesia")
# LONG FORMAT
indo_long <- indo %>%
pivot_longer(
cols = -c(country, code, year),
names_to = "source",
values_to = "energy"
)
indo_long$energy <- as.numeric(indo_long$energy)
# KELOMPOKKAN ENERGI
indo_long <- indo_long %>%
mutate(category = case_when(
source %in% c("Solar","Wind","Hydropower","Biofuels","Other renewables") ~ "Renewable",
source %in% c("Coal","Oil","Gas","Nuclear") ~ "Non-Renewable"
)) %>%
filter(!is.na(category))
# AGREGASI PER TAHUN
energy_year <- indo_long %>%
group_by(year, category) %>%
summarise(total = sum(energy, na.rm = TRUE),
.groups = "drop")
# FUNCTION FORECAST PROPHET
forecast_prophet <- function(data_cat){
df <- data.frame(
ds = as.Date(paste0(data_cat$year,"-01-01")),
y = data_cat$total
)
model <- prophet(df, yearly.seasonality = FALSE)
future <- make_future_dataframe(model,
periods = 2,
freq = "year")
forecast <- predict(model, future)
result <- forecast %>%
filter(format(ds,"%Y") == "2026") %>%
select(ds, yhat)
return(result$yhat)
}
# FORECAST PER KATEGORI
forecast_data <- energy_year %>%
group_by(category) %>%
summarise(total = forecast_prophet(cur_data()))
## Disabling weekly seasonality. Run prophet with weekly.seasonality=TRUE to override this.
## Disabling daily seasonality. Run prophet with daily.seasonality=TRUE to override this.
## Disabling weekly seasonality. Run prophet with weekly.seasonality=TRUE to override this.
## Disabling daily seasonality. Run prophet with daily.seasonality=TRUE to override this.
## Warning: There was 1 warning in `summarise()`.
## ℹ In argument: `total = forecast_prophet(cur_data())`.
## ℹ In group 1: `category = "Non-Renewable"`.
## Caused by warning:
## ! `cur_data()` was deprecated in dplyr 1.1.0.
## ℹ Please use `pick()` instead.
forecast_data$year <- 2026
# BAR CHART
ggplot(forecast_data,
aes(x = category,
y = total,
fill = category)) +
geom_bar(stat = "identity") +
theme_minimal() +
labs(
title = "Konsumsi Energi Indonesia Tahun 2026",
x = "Kategori Energi",
y = "Total Konsumsi Energi"
)
