How to Automatically Build Stopwords

zipfs_law_autostopwords_6.py

# Data viz
plotnine.options.figure_size = (10, 4.8)
(
    ggplot(
        data = df[:20]
    )+
    geom_bar(
        aes(
            x = 'word',
            y = 'actual_freq'
        ),
        stat = 'identity',
        width = 0.5,
        fill = '#981220'
    )+
    geom_line(
        aes(
            x = 'word',
            y = 'zipf_freq',
            group = 1
        ),
        size = 1
    )+
    scale_x_discrete(
        limits = df[:20]['word'].tolist()
    )+
    labs(
        title = 'Most Common Words in English Literature'
    )+
    xlab(
        xlab = 'Word'
    )+
    ylab(
        ylab = 'Frequency'
    )+
    theme_minimal()+
    theme(
        axis_text_x = element_text(
            rotation = 90,
            hjust = 0.25
        )
    )
)