DRF Report Viz

1. Install and load libraries

knitr::opts_chunk$set(echo = TRUE)
knitr::opts_chunk$set(message = FALSE)
knitr::opts_chunk$set(warning = FALSE)

options(scipen = 999) 

# install.packages("readxl")
# install.packages("writexl")
# install.packages("dplyr")
# install.packages("ggplot2")
# install.packages("stringr")
# install.packages("tidyr")

library(readxl)
library(writexl)
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, union

library(ggplot2)
library(stringr)
library(tidyr)

2.1 Import the data for % bar chart

# import GDP share data
GDP_share <- read_excel("Share of GDP in agriculture.xls", sheet = "Data", range = "A4:BP270")

# import employment share data
employment_share <- read_excel("Share of employment in agriculture.xls", sheet = "Data", range = "A4:BO270")

# lending to agriculture share data will be manually added

2.2 Slice the data sets for % bar chart

GDP_slice <- GDP_share %>%
  select(`Country Name`, `2023`) %>%
  filter(`Country Name` %in% c("Kenya", "Rwanda", "Madagascar", "Burkina Faso")) %>% 
  rename(GDP_share_2023 = `2023`)

employ_slice <- employment_share %>% 
  select(`Country Name`, `2022`) %>% 
  filter(`Country Name` %in% c("Kenya", "Rwanda", "Madagascar", "Burkina Faso")) %>% 
  rename(employ_share_2023 = `2022`)

# join data sets for GDP and employment rate, manually add bank lending data
report_data <- GDP_slice %>%
  left_join(employ_slice, by = c("Country Name" = "Country Name")) %>% 
  mutate(
    bank_lending_ag = c(3.5, 3.6, NA, 2) #Burkina, Kenya, Madagascar, Rwanda (manfully added)
         )

2.3 Data Viz for % bar chart

# pivot table to generate viz
data_long <- report_data %>% 
  pivot_longer(cols = - `Country Name`,
               names_to = "Indicator",
               values_to = "Percentage") %>%
  mutate(
    label_text = ifelse(is.na(Percentage), "NA", sprintf("%.1f", Percentage)),
    y_for_label = ifelse(is.na(Percentage), 0, Percentage)  # use 0 as the placeholder height
  )

# plot the bar chart
plot <- ggplot(data = data_long,
       mapping = aes(x = `Country Name`, y = Percentage, fill = Indicator)) +
  geom_bar(
    stat = "identity",
    position = position_dodge(width = 0.8),
    width = 0.7
  ) +
  geom_text(
    aes(y = y_for_label, label = label_text),
    position = position_dodge(width = 0.8),
    vjust = -1,
    size = 7
  ) +
  scale_fill_manual(
    values = c(
      "GDP_share_2023" = "darkblue",
      "employ_share_2023" = "gray50",
      "bank_lending_ag" = "orange"
      ),
    labels = c(
      "% of commercial bank lending to agriculture",
      "% workforce in agriculture",
      "agriculture % contribution to GDP"
      ),
    guide = guide_legend(nrow = 2)  # Specify two rows for the legend
    ) +
  scale_y_continuous(expand = expansion(mult = c(0, 0.1))) +
  labs(
    title = "Agriculture Production as a Share of Employment, GDP, Bank Lending (%, 2023)",
    x = "",
    y = "",
    fill = ""
  ) +
  theme_minimal() +
  theme(
    legend.position = "bottom",
    legend.text = element_text(size = 18),
    axis.text.x = element_text(hjust = 0.5, face = "bold", size = 20),
    axis.text.y = element_blank(),
    panel.grid = element_blank(),
    plot.title = element_text(face = "bold", size = 18, margin = margin(b = 20)),
    plot.margin = margin(t = 10)
  )

ggsave("ag_shares.png", width = 10, height = 8)