How to Automatically Build Stopwords

zipfs_law_autostopwords_7.py

# Data viz
plotnine.options.figure_size = (10, 4.8)
(
    ggplot(
        data = df
    )+
    geom_line(
        aes(
            x = 'rank',
            y = 'zipf_freq',
            group = 1
        ),
        size = 1,
        color = '#981220'
    )+
    geom_point(
        aes(
            x = 'rank',
            y = 'zipf_freq',
            group = 1
        ),
        size = 1.5
    )+
    labs(
        title = 'Zipf Distribution in English Literature'
    )+
    xlab(
        xlab = 'Rank'
    )+
    ylab(
        ylab = 'Frequency of words'
    )+
    theme_minimal()
)