Data Analysis

library(tidyverse)
library(here)

# Read the data

data <- read.csv(file = "02_data_processed/Startups in East Africa.csv")

# Q1: How many cleantech deals are there in East Africa?

ggplot(data) +
  aes(x = deal_year, fill = climate_tech) +
  geom_histogram(bins = 11L) +
  scale_fill_manual(values = c(`Climate Tech` = "#7FC97F")) +
  labs(
    x = "Year",
    y = "Number of deals",
    title = "Cleantech Deals in East Africa (2019-2024)",
    subtitle = "Cleantech takes a significant portion",
    caption = "Source: Africa the Big Deal | Insight: Lexi"
  ) +
  theme_minimal() +
  theme(legend.position = "none")

# Q2: What is the cleantech landscape in East Africa?

data %>%
 filter(!is.na(climate_tech)) %>%
 ggplot() +
  aes(x = deal_year, fill = sector) +
  geom_histogram(bins = 11L) +
  scale_fill_brewer(palette = "GnBu", direction = 1) +
  labs(
    x = "Year",
    y = "Number of deal",
    title = "Cleantech Landscape in East Africa (2019-2024)",
    subtitle = "Uganda and Tanzania are taking lead",
    caption = "Source: Africa the Big Deal | Insight: Lexi",
    fill = "Sector"
  ) +
  theme_minimal() +
  facet_wrap(vars(country), ncol = 4L)

# Q3: How large are the cleantech deals in East Africa?

data %>%
 filter(!is.na(climate_tech)) %>%
 filter(!(bracket %in% "n.a")) %>%
 filter(!(type %in% c("Debt", 
"Venture Round", "Grant"))) %>%
 ggplot() +
  aes(x = deal_year, fill = type) +
  geom_histogram(bins = 15L) +
  scale_fill_brewer(palette = "GnBu", direction = 1) +
  labs(
    x = "Year",
    y = "Number of deals",
    title = "Cleantech Funding Rounds in East Africa (2019-2024)",
    subtitle = "Late stage deals are rare",
    caption = "Source: Africa the Big Deal | Insight: Lexi",
    fill = "Round"
  ) +
  theme_minimal()