scatterplot

Read and prepare data

Code

# gus 
cfilter <- c("Kyrgyz Republic", "Armenia", "Tajikistan", "Turkmenistan", "Belarus",
             "Kazakhstan", "Russian Federation","Uzbekistan", "Belarus", "Azerbaijan")
# read data ################################################################
gdp <- read.csv2(
  "https://raw.githubusercontent.com/sultanovf/my_datasets/refs/heads/main/GDPperCap_19902024.csv")
lfe <- read.csv2(
  "https://raw.githubusercontent.com/sultanovf/my_datasets/refs/heads/main/LifeExpectancy_19902024.csv")
pop <- read.csv2(
  "https://raw.githubusercontent.com/sultanovf/my_datasets/refs/heads/main/pop_gus.csv")


# gdp data ======================================================================
years <- paste(1980:2029) #, sep=",", collapse= ","
years <- unlist(strsplit(years, ","))
new_cnames <- c("country", "cc",  years)
colnames(gdp) <- new_cnames
# head(gdp)
# ncol(gdp)

# Formatting, comma to point, na, type from string to numeric ==================
# "no data" to NA
data <- 
  gdp |> 
  mutate(across(everything(), na_if, "no data")) |> 
  mutate_at(c(3:52), function(x) as.numeric(gsub(",", ".", x))) |> 
  mutate_if(is.numeric, function(x) round(x, digits = 1))
# Show Data
# glimpse(data)

# Filter =================================================================
df_gdp <-
  data |> 
  filter(country %in% cfilter) |> 
  select(c(country, cc, "1990":"2024")) |> 
  mutate(across(where(is.numeric), ~replace_na(., 0))) |> 
  rowwise() |> 
  mutate(
    country = case_when(
      country == "Kyrgyz Republic" ~ "Kyrgyzstan",
      country == "Russian Federation" ~ "Russia",
      TRUE ~ country
      )
    ) |> 
  pivot_longer(
    cols = !c(country, cc),
    names_to = "year",
    values_to = "gdp_per_cap"
  ) |> 
  mutate(
    year = as.integer(year)
  )

# read LifeExp data ############################################################

yrs <- paste(1990:2024) #, sep=",", collapse= ","
yrs <- unlist(strsplit(yrs, ","))
new_cnames <- c("country", "cc",  yrs)
colnames(lfe) <- new_cnames

# head(gdp)
# ncol(lfe)

# check if there NA
# colSums(is.na(lfe))
# oder
# na_counts <- lapply(lfe, function(x) sum(is.na(x)))

dat <-
lfe |> 
  mutate_at(c(3:37), function(x) as.numeric(gsub(",", ".", x))) |> 
  mutate_if(is.numeric, function(x) round(x, digits = 1))

df_lfe <- 
  dat |> 
  filter(country %in% cfilter) |> 
  rowwise() |> 
  mutate(
    country = case_when(
      country == "Kyrgyz Republic" ~ "Kyrgyzstan",
      country == "Russian Federation" ~ "Russia",
      TRUE ~ country
    )
  ) |> 
  mutate_at(c(3:37), function(x) as.numeric(gsub(",", ".", x))) |> 
  mutate_if(is.numeric, function(x) round(x, digits = 1)) |> 
  pivot_longer(
    cols = !c(country, cc),
    names_to = "year",
    values_to = "life_exp"
  ) |> 
  mutate(
    year = as.integer(year)
  )

# read Pop data ################################################################

#yrs <- paste(1990:2024) #, sep=",", collapse= ","
#yrs <- unlist(strsplit(yrs, ","))
new_cnames_pop <- c("country", "iso2", "cc", "year", "pop")
colnames(pop) <- new_cnames_pop

df_pop <- 
  pop |> 
  mutate_at(5, function(x) as.numeric(gsub(",", ".", x))) |> 
  mutate(
    pop = round(pop/1000000, digits = 1)
  ) |> 
  mutate(
    iso2 = tolower(iso2)
  )

# Merge Data Tables ############################################################
gdp_lfe <- merge(df_gdp, df_lfe, by = c("country", "year", "cc"), all.x = TRUE, all.y = TRUE)
df <- merge(gdp_lfe, df_pop, by = c("country", "year", "cc"), all = TRUE)

colnames(df) <- c("country", "year",  "cc", "gdp_per_cap", "life_exp", "mdh", "pop")

Show some sample rows

Code

# oder  {r, df_print = "paged"} # funktioniert
# ohne chunk option oben:
rmarkdown::paged_table(sample_n(df, 10)) # show sample 10 rows

Plotting with ggplot2 & gganimate

Code

# Create Plot
p <- ggplot(data = df) +
  geom_flag(aes(
    x = gdp_per_cap,
    y = life_exp,
    size = pop,
    country = mdh
  )) +
  scale_country() +
  scale_size(range = c(5, 15)) +
  geom_text(aes(x = 17000, y = 46, label = "plotted by FS/ tg: @R4Pythonistas"),
            stat = "unique",
            size = 3, color = "red") +
  scale_y_continuous(
    limits = c(45,90),breaks = seq(45, 90, 5),
    expand = expansion(c(0.02, 0.02))
  ) +
  scale_x_continuous(
    limits = c(0, 20000), breaks = seq(0, 20000, 2000),
    labels = function(x) paste0(x/1000, "k"),
    expand = expansion(c(0.02, 0.02))) +
  guides(size = "none") 
  

# fOrmat and (animate)

p <- 
  p +
  labs(
    title = "MDH mamlakatlarida o'rtacha umr ko'rish va aholi jon boshiga YaIM, 1990-2024",
    caption = paste(
    "DataSources: International Monetary Fund(IMF), World Bank, Our World in Dat, World Population Review\nplotted by Fazliddin Sultonov"),
    x = "YaIM jon boshiga (k = Ming)",
    y = "Kutiladigan o'rta yosh") +
  # geom_label(aes(label = paste("Yil:", year)),
  #            x = 15000, y = 60, size = 8, fill = "white", col = "gray")+  #
  theme(
    plot.title = element_text(
      color = "tomato", size = 10, face = "bold", hjust = 0.5),
    plot.caption = element_text(
      color = "dodgerblue", size = 8, face = "bold.italic"),
    plot.background = element_rect(fill = "floralwhite"), 
    panel.background = element_rect(fill = "aliceblue"),
    legend.background = element_rect(fill = "lightblue")
  ) #+
 # transition_reveal(year)

p <- p +
  transition_reveal(year) +
  geom_label(aes(label = paste("Yil:", year)),
             x = 17000, y = 87, size = 8, fill = "floralwhite", col = "lightblue")
  # labs(title = "Yil: {frame_time}") 

# Animate Plot
p_anim <- 
  p |>
  animate(
    duration = 20,
    fps = 10,
    start_pause = 5,
    end_pause = 15,
    hight = 460,
    with = 860,
    renderer = av_renderer() # for video ffmpeg_renderer()
  )

p_anim

Plotting with ggplot2 & plotly

Code

# plotly with ggplot ===========================================================

plt <- ggplot(data = df,aes(
  x = gdp_per_cap,
  y = life_exp,
  colour = country
  )) +
  #geom_rect(alpha = 0.5, frame = year) +
  geom_point(aes(size = pop, frame = year)) +
  scale_size(range = c(4, 12)) +
  scale_y_continuous(
    limits = c(45,90),breaks = seq(45, 90, 5),
    expand = expansion(c(0.02, 0.02))
  ) +
  scale_x_continuous(
    limits = c(0, 20000), breaks = seq(0, 20000, 2000),
    labels = function(x) paste0(x/1000, "k"),
    expand = expansion(c(0.02, 0.02)))+
  labs(
  title = "MDH mamlakatlarida o'rtacha umr ko'rish va\n aholi jon boshiga YaIM, 1990-2024",
  x = "YaIM jon boshiga (k = Ming)",
  y = "Kutiladigan o'rta yosh") +
  theme(
    plot.title = element_text(
      color = "tomato", size = 12, face = "bold", hjust = 0.0),
    plot.caption = element_text(
      color = "dodgerblue", size = 8, face = "bold.italic"),
    plot.background = element_rect(fill = "floralwhite"), 
    panel.background = element_rect(fill = "aliceblue"),
    legend.background = element_rect(fill = "lightblue")
  )

# layout
fig <- 
  ggplotly(plt) |> 
  layout(
    legend=list(title =list(text = " GUS")),
    margin = list(l = 50, r = 50, b = 100, t = 50),
    annotations = list(
      x = 1, y = 0.02, text = "DataSources: International Monetary Fund(IMF), World Bank, Our World in Dat, World Population Review", 
           showarrow = F, xref='paper', yref='paper', 
           xanchor='right', yanchor='auto', xshift=0, yshift=0,
           font=list(size=10, color="red")),
    images = list(
      list(source = "gallery_img/cis.png",
           xref = "x",
           yref = "y",
           x = 100,
           y = 79,
           sizex = 2,
           sizey = 2,
           sizing = "stretch",
           opacity = 0.4,
           layer = "below")
      )
  )

# animation options
fig <- 
  fig |> 
  animation_opts(
    easing = "elastic", redraw = FALSE
  ) |> 
  animation_slider(
    currentvalue = list(prefix = "Yil: ", font = list(color="red"))
  )
# show plot
fig

show the code

import pandas as pd
from IPython.display import display, Markdown, HTML
data = pd.DataFrame(r.df)

#data.head(10)

# display(Markdown(data.to_markdown(index = False)))   # jupyter
# Markdown(pdata.head(10).to_markdown(index = False)) # reticulate
HTML(data.head(10).to_html())                         # html

	country	year	cc	gdp_per_cap	life_exp	mdh	pop
0	Armenia	1990	ARM	634.6	68.8	am	3.6
1	Armenia	1991	ARM	572.2	68.6	am	3.6
2	Armenia	1992	ARM	356.1	68.6	am	3.6
3	Armenia	1993	ARM	347.5	68.8	am	3.5
4	Armenia	1994	ARM	389.8	69.1	am	3.4
5	Armenia	1995	ARM	441.9	69.3	am	3.3
6	Armenia	1996	ARM	484.1	69.8	am	3.3
7	Armenia	1997	ARM	501.2	69.9	am	3.2
8	Armenia	1998	ARM	584.4	70.5	am	3.2
9	Armenia	1999	ARM	575.6	70.3	am	3.2

show the code

import plotly.express as px
import pandas as pd
data = pd.DataFrame(r.df)

px.scatter(data, x="gdp_per_cap", y="life_exp", animation_frame="year", 
  animation_group="country",  size="pop", color="country", hover_name="country",
  log_x=True, size_max=45, range_x=[100,20000], range_y=[45,90])