Educational attainment, Doctoral or equivalent, population 25+, total (%) (cumulative)

Source: worldbank.org, 03.09.2025

Year: 2023

Flag Country Value Value change, % Rank
Australia Australia 1.69 -8.52% 11
Austria Austria 0.459 +14.2% 21
Azerbaijan Azerbaijan 0.36 +6.45% 22
Burkina Faso Burkina Faso 0.0852 -69.6% 35
Bahrain Bahrain 0.61 +1.67% 18
Bahamas Bahamas 18.7 +34.4% 2
Bosnia & Herzegovina Bosnia & Herzegovina 0.206 -1.93% 30
Bolivia Bolivia 0.0576 +9.39% 38
Brazil Brazil 0.282 +1.78% 25
Botswana Botswana 0.301 -22.2% 24
Switzerland Switzerland 3.25 +3.44% 5
Chile Chile 0.22 +1.84% 29
Colombia Colombia 0.149 +6.05% 32
Costa Rica Costa Rica 2.88 +90% 6
Dominican Republic Dominican Republic 0.224 +108% 28
France France 1.07 +16.7% 12
United Kingdom United Kingdom 1.92 +2.24% 10
Georgia Georgia 0.54 +34.9% 19
Guatemala Guatemala 0.0225 -64.6% 40
Honduras Honduras 0.338 -12.7% 23
Indonesia Indonesia 0.0476 +10.5% 39
India India 3.49 +10.3% 4
Jordan Jordan 0.94 +30.6% 13
South Korea South Korea 0.909 +13.6% 14
Moldova Moldova 0.184 +53% 31
Mexico Mexico 0.135 +8.21% 33
North Macedonia North Macedonia 9.92 +2,713% 3
Mongolia Mongolia 0.27 -1.37% 26
Panama Panama 0.261 +27.3% 27
Peru Peru 2.11 +8.65% 9
Portugal Portugal 0.63 -14.5% 17
Russia Russia 24.4 -2.52% 1
Rwanda Rwanda 0.0666 -26% 37
Saudi Arabia Saudi Arabia 0.897 -10.5% 15
El Salvador El Salvador 0.651 +23.5% 16
Serbia Serbia 0.511 +7.56% 20
Thailand Thailand 0.118 -9.34% 34
Uruguay Uruguay 2.44 -3.47% 7
United States United States 2.2 +2.58% 8
Vietnam Vietnam 0.0685 +21.4% 36 

                    
# Install missing packages
import sys
import subprocess

def install(package):
subprocess.check_call([sys.executable, "-m", "pip", "install", package])

# Required packages
for package in ['wbdata', 'country_converter']:
try:
__import__(package)
except ImportError:
install(package)

# Import libraries
import wbdata
import country_converter as coco
from datetime import datetime

# Define World Bank indicator code
dataset_code = 'SE.TER.CUAT.DO.ZS'

# Download data from World Bank API
data = wbdata.get_dataframe({dataset_code: 'value'},
date=(datetime(1960, 1, 1), datetime.today()),
parse_dates=True,
keep_levels=True).reset_index()

# Extract year
data['year'] = data['date'].dt.year

# Convert country names to ISO codes using country_converter
cc = coco.CountryConverter()
data['iso2c'] = cc.convert(names=data['country'], to='ISO2', not_found=None)
data['iso3c'] = cc.convert(names=data['country'], to='ISO3', not_found=None)

# Filter out rows where ISO codes could not be matched — likely not real countries
data = data[data['iso2c'].notna() & data['iso3c'].notna()]

# Sort for calculation
data = data.sort_values(['iso3c', 'year'])

# Calculate YoY absolute and percent change
data['value_change'] = data.groupby('iso3c')['value'].diff()
data['value_change_percent'] = data.groupby('iso3c')['value'].pct_change() * 100

# Calculate ranks (higher GDP per capita = better rank)
data['rank'] = data.groupby('year')['value'].rank(ascending=False, method='dense')

# Calculate rank change from previous year
data['rank_change'] = data.groupby('iso3c')['rank'].diff()

# Select desired columns
final_df = data[['country', 'iso2c', 'iso3c', 'year', 'value',
'value_change', 'value_change_percent', 'rank', 'rank_change']].copy()

# Optional: Add labels as metadata (could be useful for export or UI)
column_labels = {
'country': 'Country name',
'iso2c': 'ISO 2-letter country code',
'iso3c': 'ISO 3-letter country code',
'year': 'Year',
'value': 'GDP per capita (current US$)',
'value_change': 'Year-over-Year change in value',
'value_change_percent': 'Year-over-Year percent change in value',
'rank': 'Country rank by GDP per capita (higher = richer)',
'rank_change': 'Change in rank from previous year'
}

# Display first few rows
print(final_df.head(10))

# Optional: Save to CSV
#final_df.to_csv("gdp_per_capita_cleaned.csv", index=False)
                    
                
                    
# Check and install required packages
required_packages <- c("WDI", "countrycode", "dplyr")

for (pkg in required_packages) {
  if (!requireNamespace(pkg, quietly = TRUE)) {
    install.packages(pkg)
  }
}

# Load the necessary libraries
library(WDI)
library(dplyr)
library(countrycode)

# Define the dataset code (World Bank indicator code)
dataset_code <- 'SE.TER.CUAT.DO.ZS'

# Download data using WDI package
dat <- WDI(indicator = dataset_code)

# Filter only countries using 'is_country' from countrycode
# This uses iso2c to identify whether the entry is a recognized country
dat <- dat %>%
  filter(countrycode(iso2c, origin = 'iso2c', destination = 'country.name', warn = FALSE) %in%
           countrycode::codelist$country.name.en)

# Ensure dataset is ordered by country and year
dat <- dat %>%
  arrange(iso3c, year)

# Rename the dataset_code column to "value" for easier manipulation
dat <- dat %>%
  rename(value = !!dataset_code)

# Calculate year-over-year (YoY) change and percentage change
dat <- dat %>%
  group_by(iso3c) %>%
  mutate(
    value_change = value - lag(value),                              # Absolute change from previous year
    value_change_percent = 100 * (value - lag(value)) / lag(value) # Percent change from previous year
  ) %>%
  ungroup()

# Calculate rank by year (higher value => higher rank)
dat <- dat %>%
  group_by(year) %>%
  mutate(rank = dense_rank(desc(value))) %>% # Rank countries by descending value
  ungroup()

# Calculate rank change (positive = moved up, negative = moved down)
dat <- dat %>%
  group_by(iso3c) %>%
  mutate(rank_change = rank - lag(rank)) %>% # Change in rank compared to previous year
  ungroup()

# Select and reorder final columns
final_data <- dat %>%
  select(
    country,
    iso2c,
    iso3c,
    year,
    value,
    value_change,
    value_change_percent,
    rank,
    rank_change
  )

# Add labels (variable descriptions)
attr(final_data$country, "label") <- "Country name"
attr(final_data$iso2c, "label") <- "ISO 2-letter country code"
attr(final_data$iso3c, "label") <- "ISO 3-letter country code"
attr(final_data$year, "label") <- "Year"
attr(final_data$value, "label") <- "GDP per capita (current US$)"
attr(final_data$value_change, "label") <- "Year-over-Year change in value"
attr(final_data$value_change_percent, "label") <- "Year-over-Year percent change in value"
attr(final_data$rank, "label") <- "Country rank by GDP per capita (higher = richer)"
attr(final_data$rank_change, "label") <- "Change in rank from previous year"

# Print the first few rows of the final dataset
print(head(final_data, 10))