Demo Notebook

import requests
import polars as pl
import polars.selectors as cs
from plotnine import *
from great_tables import *

Data Retrieval

res = []
url = 'https://www.federalregister.gov/api/v1/documents.json?fields[]=document_number&fields[]=excerpts&fields[]=page_length&fields[]=president&fields[]=publication_date&fields[]=raw_text_url&fields[]=signing_date&fields[]=title&fields[]=toc_subject&fields[]=topics&per_page=20&conditions[publication_date][gte]=2005-01-20&conditions[presidential_document_type][]=executive_order&conditions[president][]=george-w-bush&conditions[president][]=barack-obama&conditions[president][]=donald-trump&conditions[president][]=joe-biden&conditions[president][]=donald-trump'

while url != '':

    # retrieve results
    response = requests.get(url)
    response.raise_for_status()
    res_temp = response.json()
    res += [res_temp]

    # get next url
    url = res_temp.get('next_page_url','')

Data Cleaning

df_res = (
    pl.DataFrame(res)
    .select('results')
    .explode('results')
    .unnest('results')
    .unnest('president')
)
df_res.glimpse()

Rows: 969
Columns: 11
$ document_number         <str> '2025-14212', '2025-14217', '2025-14218', '2025-13925', '2025-12961', '2025-12962', '2025-12774', '2025-12775', '2025-12505', '2025-12506'
$ excerpts               <null> None, None, None, None, None, None, None, None, None, None
$ page_length             <i64> 4, 3, 3, 3, 2, 2, 3, 2, 1, 5
$ identifier              <str> 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump'
$ name                    <str> 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump'
$ publication_date        <str> '2025-07-28', '2025-07-28', '2025-07-28', '2025-07-23', '2025-07-10', '2025-07-10', '2025-07-09', '2025-07-09', '2025-07-03', '2025-07-03'
$ raw_text_url            <str> 'https://www.federalregister.gov/documents/full_text/text/2025/07/28/2025-14212.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/28/2025-14217.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/28/2025-14218.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/23/2025-13925.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/10/2025-12961.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/10/2025-12962.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/09/2025-12774.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/09/2025-12775.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/03/2025-12505.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/03/2025-12506.txt'
$ signing_date            <str> '2025-07-23', '2025-07-23', '2025-07-23', '2025-07-17', '2025-07-07', '2025-07-07', '2025-07-03', '2025-07-03', '2025-06-30', '2025-06-30'
$ title                   <str> 'Accelerating Federal Permitting of Data Center Infrastructure', 'Preventing Woke AI in the Federal Government', 'Promoting the Export of the American AI Technology Stack', 'Creating Schedule G in the Excepted Service', 'Ending Market Distorting Subsidies for Unreliable, Foreign-Controlled Energy Sources', 'Extending the Modification of the Reciprocal Tariff Rates', "Establishing the President's Make America Beautiful Again Commission", 'Making America Beautiful Again by Improving Our National Parks', 'Establishing a White House Office for Special Peace Missions', 'Providing for the Revocation of Syria Sanctions'
$ toc_subject             <str> None, 'Government Agencies and Employees', None, 'Government Agencies and Employees', None, None, None, None, None, None
$ topics           <list[null]> [], [], [], [], [], [], [], [], [], []

Rows: 969
Columns: 11
$ document_number         <str> '2025-14212', '2025-14217', '2025-14218', '2025-13925', '2025-12961', '2025-12962', '2025-12774', '2025-12775', '2025-12505', '2025-12506'
$ excerpts               <null> None, None, None, None, None, None, None, None, None, None
$ page_length             <i64> 4, 3, 3, 3, 2, 2, 3, 2, 1, 5
$ identifier              <str> 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump', 'donald-trump'
$ name                    <str> 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump', 'Donald Trump'
$ publication_date        <str> '2025-07-28', '2025-07-28', '2025-07-28', '2025-07-23', '2025-07-10', '2025-07-10', '2025-07-09', '2025-07-09', '2025-07-03', '2025-07-03'
$ raw_text_url            <str> 'https://www.federalregister.gov/documents/full_text/text/2025/07/28/2025-14212.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/28/2025-14217.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/28/2025-14218.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/23/2025-13925.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/10/2025-12961.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/10/2025-12962.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/09/2025-12774.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/09/2025-12775.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/03/2025-12505.txt', 'https://www.federalregister.gov/documents/full_text/text/2025/07/03/2025-12506.txt'
$ signing_date            <str> '2025-07-23', '2025-07-23', '2025-07-23', '2025-07-17', '2025-07-07', '2025-07-07', '2025-07-03', '2025-07-03', '2025-06-30', '2025-06-30'
$ title                   <str> 'Accelerating Federal Permitting of Data Center Infrastructure', 'Preventing Woke AI in the Federal Government', 'Promoting the Export of the American AI Technology Stack', 'Creating Schedule G in the Excepted Service', 'Ending Market Distorting Subsidies for Unreliable, Foreign-Controlled Energy Sources', 'Extending the Modification of the Reciprocal Tariff Rates', "Establishing the President's Make America Beautiful Again Commission", 'Making America Beautiful Again by Improving Our National Parks', 'Establishing a White House Office for Special Peace Missions', 'Providing for the Revocation of Syria Sanctions'
$ toc_subject             <str> None, 'Government Agencies and Employees', None, 'Government Agencies and Employees', None, None, None, None, None, None
$ topics           <list[null]> [], [], [], [], [], [], [], [], [], []

# lookup table

term = [1,2,1,2,1,1,2]
start_year = [2001, 2005, 2009, 2013, 2017, 2021, 2025]
start_date = [f'{year}-01-20' for year in start_year]
end_date = start_date[1:] + ['2029-01-20']
president_lname = ['Bush']*2 + ['Obama']*2 + ['Trump'] + ['Biden'] + ['Trump']
df_lkup = pl.DataFrame([term, start_year, start_date, end_date, president_lname], 
                       schema = ['term','start_year','start_date', 'end_date', 'president_lname'],
                       orient = 'col')
df_lkup