index.qmd

---
title: "World Economic Report"
message: false
warning: false
---

```{r}
# import libraries
library(tidyverse)
library(readxl)
library(RColorBrewer)
library(viridis)
library(patchwork)
library(skimr)
```

### Data Preparation and QA

```{r}
# Load world bank data
world_bank = read_xlsx(path = "WorldBank.xlsx")
head(world_bank)

# Check data types
glimpse(world_bank)
```

```{r}
# Calculate population 
world_bank <- world_bank %>% 
mutate(`Population (M)` = (`GDP (USD)` / `GDP per capita (USD)`) / 1e6)
head(world_bank)

# Review missing values as % of total DataFrame
colSums(is.na(world_bank)) / nrow(world_bank) *100

# Summary of the Dataset
skim(world_bank) 
  
```

```{r}
# Filter for the year 2014
world_bank_2014 = world_bank %>%
  filter(Year == 2014)

head(world_bank_2014)

# Load HDI table
hdi = read_csv("HDI.csv")
head(hdi)

# select only iso3 and hdi_2014 columns
hdi_2014 = hdi %>% 
  select(iso3, hdi_2014)

# rename iso3 column 
hdi_2014 = hdi_2014 %>%
  rename(`Country Code` = iso3)

# Join 2014 data with the HDI table
wb_hdi_2014 = full_join(world_bank_2014, hdi_2014)
head(wb_hdi_2014)

# Review missing values as % of total DataFrame
colSums(is.na(wb_hdi_2014)) / nrow(wb_hdi_2014)*100


```

### Prepare data for visualization

```{r}
# Summarize GDP by Year and Region
gdp_pivot = world_bank %>% 
  group_by(Year, Region) %>%
  summarise(`GDP (Trillions)` = sum(`GDP (USD)`, na.rm = TRUE)/ 1e12)

head(gdp_pivot)

# Summarize Population by Year and Region
pop_pivot = world_bank %>% 
  group_by(Year, Region) %>% 
  summarise(`Population (Billions)` = sum(`Population (M)`, na.rm = TRUE)/1e3)
                                          
                                            
head(pop_pivot)

# remove missing values from Region and hdi_2014 columns
wb_hdi_2014 = wb_hdi_2014 %>% 
  filter(!is.na(Region) & !is.na(hdi_2014))

# Summarize HDI by Region
wb_hdi_by_region <- wb_hdi_2014 %>% 
  group_by(Region) %>% 
  summarise(avg_hdi = mean(hdi_2014)) %>% 
  arrange(desc(avg_hdi))

wb_hdi_by_region
```

### Data Visualization

#### Create initial graphs for later integration into a final one-page infographic report

```{r}
# Plot GDP over time by Region
ggplot(gdp_pivot, aes(x = Year, y = `GDP (Trillions)`, fill = Region)) +
  geom_area() + 
  labs(x = "Year", y = "GDP (Trillions)")

# Plot Population over time by Region
pop_pivot %>%
  ggplot(aes(x = Year, y = `Population (Billions)`, fill = Region)) +
  geom_area()  +
  labs(x = "Year", y = "Population (Billions)")
  
# Prepare bubble chart data
bubble_chart_data = wb_hdi_2014 %>% 
  filter(!is.na(`Life expectancy at birth (years)`),
         !is.na(`GDP per capita (USD)`),
         !is.na(`Population (M)`))

# Calculate min and max population values
min_population = min(bubble_chart_data$`Population (M)`)
max_population = max(bubble_chart_data$`Population (M)`)

# Bubble chart: Life expectancy vs GDP per capita
ggplot(bubble_chart_data, 
       aes(x = `Life expectancy at birth (years)`, 
           y = `GDP per capita (USD)`, 
           size = `Population (M)`, 
           color = Region)) +
  scale_size_continuous(range = c(1, 15), 
                        limits = c(min_population, max_population), 
                        breaks = c(250, 500, 750, 1000, 1250)) +
  scale_y_log10(labels = scales::comma) +
  geom_point(alpha = 0.60)

ggplot(wb_hdi_by_region, 
       aes(x = reorder(Region, avg_hdi), y = avg_hdi)) +
  geom_bar(stat = "identity", fill = "steelblue3", alpha = 0.7) +
  coord_flip()

# Filter out Iceland
wb_hdi_2014 <- wb_hdi_2014 %>% filter(`Country Name` != "Iceland")

# Electric Power Consumption vs. GDP per Capita
plot5 = wb_hdi_2014 %>%
  ggplot(aes(x = `Electric power consumption (kWh per capita)`   , 
             y = `GDP per capita (USD)`, 
             color = hdi_2014)) +
  geom_point(alpha = 0.6, size = 3) +
    coord_cartesian(ylim = c(0,125000), xlim = c(0, 20000))
```

### Build final report

#### Combine visualizations into a single report style graphic

```{r}
# Define a custom theme
custom_theme <- theme_minimal() +
  theme( text = element_text(family = "Times New Roman"),
    axis.text = element_text(size = 12, colour = "#000000"),
    axis.title = element_text(size = 13),
    panel.grid = element_blank(),
    axis.line = element_line(size = 0.5, color = "black"),
    axis.ticks = element_line(size = 0.5, color = "black"))

# Apply the custom theme globally
theme_set(custom_theme)
```

```{r}
plot1 = ggplot(gdp_pivot, aes(x = Year, y = `GDP (Trillions)`,
                              fill = Region)) + 
  geom_area(alpha = 0.8, colour = "white") + 
  scale_fill_brewer(palette = "Set2") +
  scale_y_continuous(expand = c(0, 0)) +
  labs(x = NULL, y = "GDP (Trillions)") +
  theme(legend.title = element_blank(),
        legend.position = c(0.02, 1),
        legend.justification = c(0, 1), # Anchor to the top-right 
        legend.margin = margin(0, 0, 0, 0))

plot1

plot2 = ggplot(pop_pivot, aes(x = Year, y = `Population (Billions)`, fill = Region)) + 
  geom_area(alpha = 0.8, colour = "white") + 
  scale_fill_brewer(palette = "Set2") +
  labs(x = NULL, y = "Population (Billions)") +
  scale_y_continuous(breaks = seq(0, 7, by = 1),
                     expand = c(0, 0)) +
  theme(legend.position = "none",
        plot.margin = margin(t = 20, r = 80, b = 20, l = 20))
plot2

plot3 = ggplot(bubble_chart_data, aes(x = `Life expectancy at birth (years)`, y = `GDP per capita (USD)`, 
                                      size = `Population (M)`, color = Region)) +
  scale_size_continuous(range = c(1, 15),
                        limits = c(min_population, max_population), breaks = c(250, 500, 750, 1000, 1250)) +
  scale_color_brewer(palette = "Set2") +
  scale_x_continuous(breaks = seq(50, 85, by = 5)) +
  scale_y_log10(labels = scales::comma) +
  geom_point(alpha = 0.8) +
  theme(plot.margin = margin(t = 20, r = 80, b = 20, l = 10),
        legend.text = element_text(size = 10),
        legend.position = c(0, 1), # Position the legend at the top left
        legend.justification = c(0, 1),
        legend.direction = "horizontal") + # Set legend direction to horizontal
  guides(colour = "none")

plot3

plot4 = ggplot(wb_hdi_by_region, aes(reorder(Region, avg_hdi), avg_hdi, fill = Region)) +
  geom_col(alpha = 0.8) + 
  scale_fill_brewer(palette = "Set2") + 
  labs(x = "Region", y = "Human Development Index (HDI)") +
  scale_y_continuous(breaks = seq(0, 0.8, by = 0.2),
                     expand = c(0, 0)) +
  theme(axis.text.x = element_blank(),
        axis.ticks.x = element_blank(),
        legend.position = "none")

plot4

plot5 = ggplot(wb_hdi_2014, aes(x = `Electric power consumption (kWh per capita)`, y = `GDP per capita (USD)`, 
                                color = hdi_2014)) + 
  geom_point(alpha = 0.8, size = 3) + 
  scale_color_viridis(option = "H", direction = -1, 
                      breaks = seq(0.4, 0.9, by = 0.1), 
                      guide = guide_legend(override.aes = list(size = 4, shape = 16))) + 
  coord_cartesian(ylim = c(0, 125000), xlim = c(0, 20000)) + 
  scale_y_continuous(labels = scales::comma) + 
  scale_x_continuous(labels = scales::comma) +
  theme(plot.margin = margin(t = 20, r = 80, b = 80, l = 20))

plot5
```

```{r}
 # Combine all plots using patchwork package
combined_plot = (plot1 | plot2) / 
                 plot3 /
                 (plot4 | plot5) +
  plot_annotation(title = "World Economic Report (1960-2018)",
                  theme = theme(plot.title = element_text(hjust = 0.5, size = 18, face = "bold", margin = margin(t = 7, r = 0, b = 20, l = 0))))

# Save the combined plot
ggsave("econ_dev_report.png", combined_plot, width = 10.5, height = 13.5, units = "in", bg = "white")

# Final edit with Canva
```