In [157]:
make_link = F.udf(lambda rev_id: f"<a href='https://en.wikipedia.org/w/index.php?&diff={rev_id}'>diff link</a>", 'string')
limit_links = F.udf(lambda links: links[:10], 'array<string>')

(joined_mediakiki_revisions
     .where(F.col('wiki_db')=='enwiki')
     .where(F.col('missing_event'))
     .withColumn('link', make_link('rev_id'))
     .groupBy(parent_0_col, 'wmf_raw.mediawiki_revision.rev_minor_edit')
     .agg(
         F.collect_list('link').alias('links')
     )
     .withColumn('links', limit_links('links'))
     .displayHtml(20))