Country

Indicator

Value type

Values present

Persistence to last grade of primary, female (% of cohort)

Source: worldbank.org, 01.09.2025

Year: 2009

Country	Value	Value change, %	Rank
Angola	26.9	+4.4%	97
Albania	95.4	+1.12%	39
Argentina	93.8	+0.96%	46
Armenia	97.8	+0.417%	24
Azerbaijan	97.5	+0.871%	26
Burundi	61.1	-4.41%	83
Benin	51.4	-18.9%	89
Burkina Faso	66.6	-6.9%	79
Bangladesh	70.6	+6.91%	73
Bulgaria	97.1	+3.8%	29
Bahamas	87.7	+0.34%	57
Bosnia & Herzegovina	98.4		19
Belize	91.4	-4.95%	50
Bolivia	84.6		63
Brunei	96.3	+0.151%	35
Bhutan	91.7	-3.34%	49
Central African Republic	38.9	-4.5%	92
Cameroon	65.4	-5.25%	81
Congo - Kinshasa	51.1	-30.2%	90
Colombia	85.1	-4.62%	62
Costa Rica	90	-5.83%	56
Cuba	96.1	+0.682%	36
Czechia	99.1	-0.73%	13
Germany	96.8	+0.725%	33
Dominica	90.4	+2.02%	55
Denmark	99.2	-0.345%	11
Algeria	97.1	+2.55%	28
Ecuador	91.3	-0.481%	51
Egypt	96.6	+2.53%	34
Eritrea	66.9	-7.06%	78
Estonia	97.6	-0.983%	25
Ethiopia	37.5	-9.28%	93
Finland	99.9	+0.638%	2
Georgia	98.6	+4.46%	18
Guinea	56.2	-0.672%	87
Equatorial Guinea	64.3	+14.4%	82
Guatemala	67.9	-13.9%	76
Hong Kong SAR China	99.2	-0.286%	9
Honduras	83.8	+12%	65
Croatia	99.6	+0.35%	5
Hungary	98	+0.147%	23
Iran	93.5	-2.61%	47
Iceland	98.7	+0.279%	17
Italy	99.8	-0.169%	3
Kazakhstan	99.1	-0.095%	12
Kyrgyzstan	97.3	+0.609%	27
St. Kitts & Nevis	69.6	+2.32%	75
South Korea	99.3	+0.605%	8
Kuwait	96	-3.02%	38
Laos	71.5	+3.14%	72
St. Lucia	90.6	-4.68%	53
Liechtenstein	78.1	-6.85%	67
Lesotho	76.8	+5.68%	69
Lithuania	98.4	-0.238%	20
Latvia	94.5	-1.18%	43
Morocco	90.4	+15.4%	54
Moldova	97	+1.48%	32
Madagascar	35.4	-29.8%	94
Mexico	95.2	+0.0612%	40
Mali	75.7	-1.38%	70
Myanmar (Burma)	77.5	+11.9%	68
Mozambique	33.7	-4.64%	95
Mauritius	97	-1.18%	31
Malawi	53.6	+28.4%	88
Namibia	87	+2.08%	58
Niger	60.4	-4.95%	85
Nigeria	66.6	-16.2%	80
Norway	98.9	-0.179%	15
Pakistan	58.9	-1.6%	86
Panama	93.8	+6.68%	45
Peru	91	+3.91%	52
Poland	99.5	+1.8%	7
Paraguay	83.9	+4.52%	64
Romania	97.1	+2.82%	30
Rwanda	39	-2.88%	91
Sudan	72.4		71
Senegal	61.1	+3.85%	84
El Salvador	87	+11.4%	59
Serbia	98.7	+1.51%	16
Suriname	78.7	-21%	66
Slovakia	98.4	+0.508%	21
Slovenia	98.9	-0.45%	14
Sweden	99.6	+0.287%	6
Eswatini	86.7	+17.9%	60
Syria	94.9	+0.702%	42
Chad	27	+8.03%	96
Togo	67.2	+8.34%	77
Tajikistan	99.2	-0.0119%	10
Timor-Leste	70.3	-9.76%	74
Trinidad & Tobago	92.1	-0.726%	48
Tunisia	95.1	-0.356%	41
Turkey	100	+7.5%	1
Tanzania	86.7	+12.8%	61
Ukraine	98.1	+0.204%	22
Uruguay	96	-0.954%	37
Uzbekistan	99.8	+0.86%	4
Venezuela	94.2	-0.551%	44

Python
R

                    
# 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.PRM.PRSL.FE.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.PRM.PRSL.FE.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))

Compare

Persistence to last grade of primary, female (% of cohort)

Year: 2009

Acquire full dataset with Python or R from source