Data viz
Trung Hoang
1 Import dataset
Reproducible report
library(readxl)
df<- read_excel("fire data.xlsx",
sheet = "ALL",
range = "A1:D73")
df <- as.data.frame(df)
df$country <- factor(df$country,
levels = c("Germany", "France", "Austria",
"Switzerland", "Slovenia", "Italy"))2 Check dataset
dim(df)## [1] 72 4str(df)## 'data.frame': 72 obs. of 4 variables:
## $ country : Factor w/ 6 levels "Germany","France",..: 3 3 3 3 3 3 3 3 3 3 ...
## $ year : num 2012 2013 2014 2015 2016 ...
## $ number_of_forest_fires: num 259 199 146 280 141 278 174 244 234 164 ...
## $ burnt_area_ha : num 48 102 92 114 23 25 19 20 60 117 ...summary(df)## country year number_of_forest_fires burnt_area_ha
## Germany :12 Min. :2012 Min. : 32 Min. : 18.00
## France :12 1st Qu.:2015 1st Qu.: 118 1st Qu.: 68.25
## Austria :12 Median :2018 Median : 352 Median : 381.50
## Switzerland:12 Mean :2018 Mean :1547 Mean : 14920.64
## Slovenia :12 3rd Qu.:2020 3rd Qu.:2761 3rd Qu.: 8807.25
## Italy :12 Max. :2023 Max. :8252 Max. :161987.00sapply(df, class)## country year number_of_forest_fires
## "factor" "numeric" "numeric"
## burnt_area_ha
## "numeric"3 Vẽ biểu đồ cột
3.1 Biểu đồ cột đơn giản
library(ggplot2)
df_Austria <- df |> subset(country == "Austria")
p_Austria <- ggplot(data = df_Austria,
mapping = aes(x = year,
y = number_of_forest_fires)) +
# geom_col() +
geom_bar(stat = "identity")
p_Austria
library(ggplot2)
df_Germany <- df |> subset(country == "Germany")
p_Germany <- ggplot(data = df_Germany,
mapping = aes(x = year,
y = number_of_forest_fires)) +
# geom_col() +
geom_bar(stat = "identity")
p_Germany
library(patchwork)
p_Austria + p_Germany
p_Austria / p_Germany
3.2 Facet biểu đồ
ggplot(data = df,
mapping = aes(x = year,
y = number_of_forest_fires)) +
geom_col() +
# facet_wrap(~ country,
# scales = "free_y", # free cho y
# nrow = 2,
# ncol = 3
# )
facet_wrap(~ country,
scales = "fixed", # đồng bộ scale x và y
nrow = 2,
ncol = 3
)
3.3 Vẽ cho các nước phía Bắc
df_north <- df |> subset(country == "Austria" | country == "Germany" |
country == "France")
p_north <- ggplot(data = df_north,
mapping = aes(x = year,
y = number_of_forest_fires)) +
geom_col() +
# facet_wrap(~ country,
# scales = "free_y", # free cho y
# nrow = 2,
# ncol = 3
# )
facet_wrap(~ country,
scales = "fixed", # đồng bộ scale x và y
nrow = 1,
ncol = 3
)
df_north## country year number_of_forest_fires burnt_area_ha
## 1 Austria 2012 259 48
## 2 Austria 2013 199 102
## 3 Austria 2014 146 92
## 4 Austria 2015 280 114
## 5 Austria 2016 141 23
## 6 Austria 2017 278 25
## 7 Austria 2018 174 19
## 8 Austria 2019 244 20
## 9 Austria 2020 234 60
## 10 Austria 2021 164 117
## 11 Austria 2022 217 550
## 12 Austria 2023 119 21
## 13 France 2012 2763 7584
## 14 France 2013 1510 2735
## 15 France 2014 1730 4735
## 16 France 2015 2898 8169
## 17 France 2016 2775 14101
## 18 France 2017 3220 23093
## 19 France 2018 1634 3940
## 20 France 2019 2949 13394
## 21 France 2020 2760 10722
## 22 France 2021 2332 12779
## 23 France 2022 4215 58123
## 24 France 2023 2666 5361
## 25 Germany 2012 701 269
## 26 Germany 2013 515 199
## 27 Germany 2014 429 120
## 28 Germany 2015 1071 526
## 29 Germany 2016 608 283
## 30 Germany 2017 424 395
## 31 Germany 2018 1708 2349
## 32 Germany 2019 1523 2711
## 33 Germany 2020 1360 368
## 34 Germany 2021 548 148
## 35 Germany 2022 2397 3058
## 36 Germany 2023 1059 12403.4 Vẽ cho các nước phía Nam
df_south <- df |> subset(country == "Switzerland" | country == "Slovenia" |
country == "Italy")
p_south <- ggplot(data = df_south,
mapping = aes(x = year,
y = number_of_forest_fires)) +
geom_col() +
# facet_wrap(~ country,
# scales = "free_y", # free cho y
# nrow = 2,
# ncol = 3
# )
facet_wrap(~ country,
scales = "fixed", # đồng bộ scale x và y
nrow = 1,
ncol = 3
)3.5 Combine
library(patchwork)
p_north / p_south
4 Vẽ biểu đồ đường với scale chung
ggplot(data = df,
mapping = aes(x = year,
y = burnt_area_ha,
color = country)) +
geom_line(linewidth = 1) +
facet_wrap(~ country,
scales = "fixed",
nrow = 2,
ncol = 3
) +
labs(x = "Year",
y = "Burn area (ha)",
title = "Forest") +
scale_color_manual(name = "Country",
values = c("red",
"blue",
"darkgreen",
"#0a57c0",
"brown",
"purple")) +
theme_bw(base_size = 15) +
theme(strip.text = element_text(face = "bold")) +
theme(strip.background = element_rect(fill = "lightyellow"))
ggsave(filename = "burn_forest.png",
width = 10,
height = 5,
dpi = 300,
units = "in")5 Vẽ biểu đồ đường với scale riêng
ggplot(data = df,
mapping = aes(x = year,
y = burnt_area_ha,
color = country)) +
geom_line(linewidth = 1) +
facet_wrap(~ country,
scales = "free_y",
nrow = 2,
ncol = 3
) +
labs(x = "Year",
y = "Burn area (ha)",
title = "Forest") +
scale_color_manual(name = "Country",
values = c("red",
"blue",
"darkgreen",
"#0a57c0",
"brown",
"purple")) +
theme_bw(base_size = 15) +
theme(strip.text = element_text(face = "bold")) +
theme(strip.background = element_rect(fill = "lightyellow"))
ggsave(filename = "burn_forest_scale_y.png",
width = 10,
height = 5,
dpi = 300,
units = "in")6 Vẽ donut
library(tidyverse)
data <- read.csv("FORMAT_DONUT.csv")
library(ggplot2)
### fire june
names(data) <- c("category", "fraction")
data$fraction <- data$fraction / sum(data$fraction)
data$ymax <- cumsum(data$fraction)
data$ymin <- c(0, head(data$ymax, n = -1))
data$labelPosition <- (data$ymax + data$ymin) / 2
data$label <- paste0(round(data$fraction * 100, 1),
"%")
data$label[which(data$fraction == 0)] <- ""
fire_july <- ggplot(data,
aes(ymax = ymax,
ymin = ymin,
xmax = 4,
xmin = 2,
fill = category)) +
geom_rect(color = "black",
show.legend = T) +
geom_text(x = 3,
aes(y = labelPosition,
label = label,),
color = "black",
size = 5,
fontface = "bold") +
scale_fill_manual(name = "Quality Levels",
values = c("#e75d56",
"#aee1f4",
"#eac861",
"#139f72",
"yellow")) +
coord_polar(theta = "y",
direction = 1) +
xlim(c(-1, 4)) +
theme_void() +
theme(plot.margin = margin(t = 0, b = 0, l = 0, r = 0)) +
# theme(panel.grid.major = element_blank(),
# panel.grid.minor = element_blank(),
# panel.background = element_rect(colour = "black", size = 1)) +
labs(title = "July") +
theme(plot.title = element_text(size = "22",
face = "bold",
colour = "black",
angle = 0,
hjust = 0.5,
vjust = -2,
margin = margin(t = 0, r = 0, b = 10, l = 0, unit = "pt")))
fire_july
ggsave(filename = "fire_july.png",
plot = fire_july,
width = 10,
height = 5,
dpi = 300,
bg = "white",
units = "in")library(tidyverse)
data <- read.csv("FORMAT_DONUT.csv")
library(ggplot2)
### fire june
names(data) <- c("category", "fraction")
data$fraction <- data$fraction / sum(data$fraction)
data$ymax <- cumsum(data$fraction)
data$ymin <- c(0, head(data$ymax, n = -1))
data$labelPosition <- (data$ymax + data$ymin) / 2
data$label <- paste0(round(data$fraction * 100, 1),
"%")
data$label[which(data$fraction == 0)] <- ""
fire_aug <- ggplot(data,
aes(ymax = ymax,
ymin = ymin,
xmax = 4,
xmin = 2,
fill = category)) +
geom_rect(color = "black",
show.legend = T) +
geom_text(x = 3,
aes(y = labelPosition,
label = label,),
color = "black",
size = 5,
fontface = "bold") +
scale_fill_manual(name = "Quality Levels",
values = c("#e75d56",
"#aee1f4",
"#eac861",
"#139f72",
"yellow")) +
coord_polar(theta = "y",
direction = 1) +
xlim(c(-1, 4)) +
theme_void() +
theme(plot.margin = margin(t = 0, b = 0, l = 0, r = 0)) +
# theme(panel.grid.major = element_blank(),
# panel.grid.minor = element_blank(),
# panel.background = element_rect(colour = "black", size = 1)) +
labs(title = "August") +
theme(plot.title = element_text(size = "22",
face = "bold",
colour = "black",
angle = 0,
hjust = 0.5,
vjust = -2,
margin = margin(t = 0, r = 0, b = 10, l = 0, unit = "pt")))
fire_aug
ggsave(filename = "fire_aug.png",
plot = fire_aug,
width = 10,
height = 5,
dpi = 300,
bg = "white",
units = "in")library(patchwork)
fire_july + fire_aug + plot_layout(guides = "collect") &
theme(legend.position = "bottom",
legend.key.size = unit(1, "cm"),
legend.text = element_text(size = 15),
legend.key.width = unit(2, "cm"),
legend.key.spacing.x = unit(0.5, "cm"),
legend.key.spacing.y = unit(0.5, "cm"),
legend.title = element_blank()) 
ggsave(filename = "donut_gop.png",
width = 10,
height = 7,
dpi = 300,
bg = "white",
units = "in")7 Tham khảo format
https://r-graph-gallery.com/line-chart-dual-Y-axis-ggplot2.html
# Libraries
library(ggplot2)
library(dplyr)
library(patchwork) # To display 2 charts together
library(hrbrthemes)
# Build dummy data
data <- data.frame(
day = as.Date("2019-01-01") + 0:99,
temperature = runif(100) + seq(1,100)^2.5 / 10000,
price = runif(100) + seq(100,1)^1.5 / 10
)
# Most basic line chart
p1 <- ggplot(data, aes(x=day, y=temperature)) +
geom_line(color="#69b3a2", size=2) +
ggtitle("Temperature: range 1-10") +
theme_ipsum()
p2 <- ggplot(data, aes(x=day, y=price)) +
geom_line(color="grey",size=2) +
ggtitle("Price: range 1-100") +
theme_ipsum()
# Display both charts side by side thanks to the patchwork package
p1 + p2
8 Tài liệu tham khảo
Các dạng plot cần vẽ
https://docs.google.com/document/d/1VFcD0xis9tFeLE7i0gDQIcKjrWznJlXK4xhmQ8hUAnQ/edit?tab=t.0
Hướng dẫn cú pháp R Markdown
https://epirhandbook.com/vn/new_pages/rmarkdown.vn.html