In [1]:
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
# import getDataFile from parent helpers folder
import sys
sys.path.append('..')
import helpers.ttpy as helpers
In [2]:
democracies = helpers.getDataFile(date="2024-11-05", filename="democracy_data.csv")
democracies.columns
Out[2]:
Index(['country_name', 'country_code', 'year', 'regime_category_index',
       'regime_category', 'is_monarchy', 'is_commonwealth', 'monarch_name',
       'monarch_accession_year', 'monarch_birthyear', 'is_female_monarch',
       'is_democracy', 'is_presidential', 'president_name',
       'president_accesion_year', 'president_birthyear', 'is_interim_phase',
       'is_female_president', 'is_colony', 'colony_of',
       'colony_administrated_by', 'is_communist', 'has_regime_change_lag',
       'spatial_democracy', 'parliament_chambers', 'has_proportional_voting',
       'election_system', 'lower_house_members', 'upper_house_members',
       'third_house_members', 'has_new_constitution', 'has_full_suffrage',
       'suffrage_restriction', 'electoral_category_index',
       'electoral_category', 'spatial_electoral', 'has_alternation',
       'is_multiparty', 'has_free_and_fair_election',
       'parliamentary_election_year', 'election_month', 'election_year',
       'has_postponed_election'],
      dtype='object')
In [3]:
populations = helpers.getDataFile("population.csv", url = "https://raw.githubusercontent.com/datasets/population/refs/heads/main/data/population.csv")
populations.columns
Out[3]:
Index(['Country Name', 'Country Code', 'Year', 'Value'], dtype='object')
In [4]:
# Merge the two files on the country code and year
democracypop = pd.merge(democracies, populations, left_on=['country_code', 'year'], 
                        right_on=['Country Code', 'Year'], how='inner')

popsum = (democracypop.groupby(['year','is_democracy'])['Value'].sum()).to_frame().reset_index()

# Create the graph

plt.figure(figsize=(16, 8))
plt.style.use('dark_background')
custom_palette = {False: 'teal', True: 'lime'}
lineplt = sns.lineplot(data=popsum, x='year', y='Value', hue='is_democracy', 
                       palette=custom_palette, linewidth = 4, hue_order=[True, False])

lineplt.set_title("Global Population by Democracy Status", fontsize=30)
lineplt.set_ylabel("Population (in billions)", fontsize=18)
lineplt.set_xlabel("Year", fontsize=18)
lineplt.axvline(1998, color="#666")
lineplt.axvline(1984, color="#666")
lineplt.axvline(2007, color="#666")
plt.text(1998, popsum['Value'].max()/4, '1998: Indonesia and \nNigeria switch', rotation=45, verticalalignment='bottom', color='#666', fontsize=18)
plt.text(1984, popsum['Value'].max()/4, '1984: Brazil and \nUruguay switch', rotation=45, verticalalignment='bottom', color='#666', fontsize=18)
plt.text(2007, popsum['Value'].max()/4,' 2007: Thailand alternates, \nPakistan switches',  rotation=45, verticalalignment='bottom', color='#666', fontsize=18)

plt.xticks(fontsize=14)
plt.yticks(fontsize=14)

plt.legend(title='Democratic Status', fontsize = 18, title_fontsize = 14)

plt.figtext(0.99, 0.04, '@paulusm@scholar.social #TidyTuesday', 
            horizontalalignment='right', fontsize=14, alpha=0.7, fontstyle='italic')
plt.figtext(0.99, 0.01, 'Data : Bjørnskov & Rode (2020; democracies); World Bank (populations)', 
            horizontalalignment='right', fontsize=14, alpha=0.7 , fontstyle='italic')

plt.show()

C:\Users\pd2-matthews\AppData\Local\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
C:\Users\pd2-matthews\AppData\Local\anaconda3\Lib\site-packages\seaborn\_oldcore.py:1119: FutureWarning: use_inf_as_na option is deprecated and will be removed in a future version. Convert inf values to NaN before operating instead.
  with pd.option_context('mode.use_inf_as_na', True):
No description has been provided for this image
In [5]:
# Identify significant events in the data

findcontributionA = democracypop[((democracypop['year'] == 2007) & (democracypop['is_democracy'] == False))]
findcontributionB = democracypop[((democracypop['year'] == 2008) & (democracypop['is_democracy'] == True))]
findcontribution = pd.merge(findcontributionA, findcontributionB, on='country_code', how='inner')
findcontribution = findcontribution[['country_name_x', 'year_x', 'is_democracy_x', 'Value_x', 'year_y', 'is_democracy_y', 'Value_y']]
findcontribution
Out[5]:
country_name_x year_x is_democracy_x Value_x year_y is_democracy_y Value_y
0 Bhutan 2007 False 681614 2008 True 689737
1 Malaysia 2007 False 27092604 2008 True 27664296
2 Nepal 2007 False 26713655 2008 True 26881544
3 Pakistan 2007 False 181924521 2008 True 185931955
4 Thailand 2007 False 66826754 2008 True 67328239