data_cleaning

library(tidyverse)
library(dplyr)
library(readxl)
library(here)

# Read the excel

path_to_data <- here("00_data_raw", "2019-2024 Africa The Big Deal_Database_20240401.xlsx")

# Read the second sheet

raw_data <-
  read_excel(path = path_to_data, sheet = "Deals 2019-2024")

# Standardize column names

colnames(raw_data) <- gsub(" ", "_", tolower(colnames(raw_data)))

ranamed_data <- raw_data |>
  rename(startup_name = `start-up_name`, 
         woman_cofounder = `woman_co-founder`,
         employees = `#_of_employees_(linkedin)`,
         deal_size = `amount_raised_$m`,
         valuation = `valuation_$m`
         )

# Drop columns

selected_data <- ranamed_data |>
  select(deal_year, startup_name, country, launch, description, sector, climate_tech, woman_cofounder, employees, deal_size, bracket, type, exit, valuation) |>
  filter(country %in% c("Ethiopia", "Rwanda", "Uganda", "Tanzania"))

View(selected_data)

write_csv(selected_data, here("02_data_processed", "Startups in East Africa.csv"))