co2_plot.py

from pathlib import Path

from matplotlib import pyplot as plt
import pandas as pd
import requests
import seaborn as sn

DATA_PATH = Path('data')


def main():
    co2_per_person = load_google_doc('phAwcNAVuyj1gkNuUEXOGag')
    has_high_peak = co2_per_person.max() > 40
    top_co2 = co2_per_person[co2_per_person.columns[has_high_peak]]

    related_countries = ['Canada', 'United States', 'United Kingdom']
    related_co2 = co2_per_person[related_countries]

    sn.set()
    ax = plt.subplot(211)
    top_co2.plot(ax=ax)
    ax.set_ylabel('MT per capita')

    ax = plt.subplot(212, sharex=ax)
    related_co2.plot(ax=ax)
    ax.lines[0].set_linewidth(3)
    ax.set_ylabel('MT per capita')

    plt.suptitle('Carbon Dioxide Emissions')
    plt.tight_layout(rect=[0, 0, 1, 0.95])
    plt.show()


def load_google_doc(key):
    target = DATA_PATH / f'google_{key}.csv'

    if not target.exists():
        response = requests.get('https://docs.google.com/spreadsheet/pub',
                                params=dict(key=key, output='csv'))
        response.raise_for_status()
        with target.open('wb') as target_file:
            for chunk in response.iter_content(chunk_size=16*1024):
                target_file.write(chunk)

    data_frame = pd.read_csv(target, index_col=0)
    column_names = data_frame.columns.values
    column_names = column_names.astype(int)
    data_frame.columns = column_names
    data_frame = data_frame.T
    data_frame.index.names = ['Year']
    return data_frame


main()