requirements.txt

requests
pandas

Vaccinations.ipynb

vaccinations.py

import requests
import json
import pandas
from urllib import parse

API_URL = 'https://coronavirus.data.gov.uk/api/'
INITIAL_PATH = '/v1/data?filters=areaType=nation&structure=%7B%22areaType%22:%22areaType%22,%22areaName%22:%22areaName%22,%22areaCode%22:%22areaCode%22,%22date%22:%22date%22,%22cumPeopleVaccinatedFirstDoseByPublishDate%22:%22cumPeopleVaccinatedFirstDoseByPublishDate%22,%22cumPeopleVaccinatedSecondDoseByPublishDate%22:%22cumPeopleVaccinatedSecondDoseByPublishDate%22%7D&format=json'

def fetch(path):
    url = parse.urljoin(API_URL, path)
    response = requests.get(url)
    response.raise_for_status()

    response_json = response.json()
    return response_json['length'], response_json['data'], response_json['pagination']['current'], response_json['pagination']['last'], response_json['pagination']['next']


def fetch_all():
    next_path = INITIAL_PATH
    while True:
        length, data, current_path, last_path, next_path = fetch(next_path[1:])
        if len(data) == length:
            break
        elif current_path == last_path:
            raise Exception('reached end of pages')            
        elif next_path is None:
            raise Exception('no next page')
    return pandas.DataFrame(data).set_index('date').rename({
        'cumPeopleVaccinatedFirstDoseByPublishDate': 'cumFirstDoses',
        'cumPeopleVaccinatedSecondDoseByPublishDate': 'cumSecondDoses',
    }, axis='columns')

df = fetch_all()

df['cumTotal'] = df['cumFirstDoses'] + df['cumSecondDoses']
grouped = df.groupby('date').sum()
diffs = grouped.diff().rename(lambda name: 'n{}'.format(name[1:]), axis='columns')
grouped.merge(diffs, on='date')