Loading the Gapminder Data

There are two different ways to load the gapminder data: 1) using a defined function, or 2) using the older gapminder dataset that is embedded in the Plotly library.

---

1. User-defined function

Here's the one function to load the Gapminder data based on the Systema Globalis dataset.

/ !pip install plotly // uncomment if using Google Colab
import numpy as np
import pandas as pd
import plotly.express as px

def load_gapminder_data():
    """Create a pandas DataFrame with some of the key indicators from the 
    Open Numbers Systema Globalis dataset."""

    # pin to a specific github tag
    base_url = "https://raw.githubusercontent.com/open-numbers/ddf--gapminder--systema_globalis/v1.20.1/"
    
    # load income per person
    df_income = pd.read_csv(base_url + "ddf--datapoints--income_per_person_gdppercapita_ppp_inflation_adjusted--by--geo--time.csv")

    # load life expectancy
    df_life_expectancy = pd.read_csv(base_url + "ddf--datapoints--life_expectancy_at_birth_with_projections--by--geo--time.csv")

    # load population size
    df_population = pd.read_csv(base_url + "ddf--datapoints--population_total--by--geo--time.csv")

    # load child mortality
    df_child_mortality = pd.read_csv(base_url + "ddf--datapoints--child_mortality_0_5_year_olds_dying_per_1000_born--by--geo--time.csv")

    # load country attributes
    df_countries = pd.read_csv(base_url + "ddf--entities--geo--country.csv")

    # rename some columns in the countries dataframe to help with merging
    df_countries = (
        df_countries
        [["country", "name", "world_4region", "world_6region"]]
        .rename(columns={"country": "geo", "name": "country"})
    )

    # capitalise regions
    df_countries["world_4region"] = df_countries["world_4region"].str.capitalize()

    # join all indicators into a single dataframe
    df_gapminder = pd.merge(df_population, df_income, on=["geo", "time"])
    df_gapminder = pd.merge(df_gapminder, df_life_expectancy, on=["geo", "time"])
    df_gapminder = pd.merge(df_gapminder, df_child_mortality, on=["geo", "time"])
    df_gapminder = pd.merge(df_gapminder, df_countries, on="geo")

    # rename some columns to be more concise
    df_gapminder = df_gapminder.rename(
        columns={
            "time": "year",
            "population_total": "population",
            "income_per_person_gdppercapita_ppp_inflation_adjusted": "income_per_person",
            "life_expectancy_at_birth_with_projections": "life_expectancy",
            "child_mortality_0_5_year_olds_dying_per_1000_born": "child_mortality",
        }
    )

    # keep only data between 1950 and 2021 - it's less jumpy
    df_gapminder = df_gapminder.query("1950 <= year <= 2021").reset_index(drop=True)

    # tidy up columns
    df_gapminder.drop(columns=["geo"], inplace=True)
    df_gapminder.insert(0, "country", df_gapminder.pop("country"))  # move country column to the front

    return df_gapminder

df_gapminder = load_gapminder_data()
df_gapminder

---

2. Import data from Plotly

The Plotly library also has a gapminder dataset that ends in 2007.

import plotly.express as px
import pandas as pd

df = px.data.gapminder()